diff --git "a/novel-translation/03_Qwen2-0.5B_1.5B-4bit.ipynb" "b/novel-translation/03_Qwen2-0.5B_1.5B-4bit.ipynb" new file mode 100644--- /dev/null +++ "b/novel-translation/03_Qwen2-0.5B_1.5B-4bit.ipynb" @@ -0,0 +1,5098 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "application/vnd.databricks.v1+cell": { + "cellMetadata": {}, + "inputWidgets": {}, + "nuid": "0ea8b46b-839b-445b-8043-ccdf4e920ace", + "showTitle": false, + "title": "" + } + }, + "outputs": [], + "source": [ + "%load_ext autoreload\n", + "%autoreload 2" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "application/vnd.databricks.v1+cell": { + "cellMetadata": {}, + "inputWidgets": {}, + "nuid": "6d394937-6c99-4a7c-9d32-7600a280032f", + "showTitle": false, + "title": "" + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "workding dir: /home/inflaton/code/projects/courses/novel-translation\n" + ] + } + ], + "source": [ + "import os\n", + "import sys\n", + "from pathlib import Path\n", + "\n", + "workding_dir = str(Path.cwd().parent)\n", + "os.chdir(workding_dir)\n", + "sys.path.append(workding_dir)\n", + "print(\"workding dir:\", workding_dir)" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": { + "application/vnd.databricks.v1+cell": { + "cellMetadata": {}, + "inputWidgets": {}, + "nuid": "9f67ec60-2f24-411c-84eb-0dd664b44775", + "showTitle": false, + "title": "" + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "loading env vars from: /home/inflaton/code/projects/courses/novel-translation/.env\n" + ] + }, + { + "data": { + "text/plain": [ + "True" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from dotenv import find_dotenv, load_dotenv\n", + "\n", + "found_dotenv = find_dotenv(\".env\")\n", + "\n", + "if len(found_dotenv) == 0:\n", + " found_dotenv = find_dotenv(\".env.example\")\n", + "print(f\"loading env vars from: {found_dotenv}\")\n", + "load_dotenv(found_dotenv, override=True)" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": { + "application/vnd.databricks.v1+cell": { + "cellMetadata": {}, + "inputWidgets": {}, + "nuid": "f1597656-8042-4878-9d3b-9ebfb8dd86dc", + "showTitle": false, + "title": "" + } + }, + "outputs": [ + { + "data": { + "text/plain": [ + "('unsloth/Qwen2-0.5B-Instruct-bnb-4bit',\n", + " True,\n", + " None,\n", + " None,\n", + " 2048,\n", + " 10,\n", + " None,\n", + " 'datasets/mac/mac.tsv',\n", + " 'results/mac-results.csv')" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "import os\n", + "\n", + "model_name = os.getenv(\"MODEL_NAME\")\n", + "token = os.getenv(\"HF_TOKEN\") or None\n", + "load_in_4bit = os.getenv(\"LOAD_IN_4BIT\") == \"true\"\n", + "local_model = os.getenv(\"LOCAL_MODEL\")\n", + "hub_model = os.getenv(\"HUB_MODEL\")\n", + "num_train_epochs = int(os.getenv(\"NUM_TRAIN_EPOCHS\") or 0)\n", + "data_path = os.getenv(\"DATA_PATH\")\n", + "results_path = os.getenv(\"RESULTS_PATH\")\n", + "\n", + "max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!\n", + "dtype = (\n", + " None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+\n", + ")\n", + "\n", + "model_name, load_in_4bit, local_model, hub_model, max_seq_length, num_train_epochs, dtype, data_path, results_path" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Fri Jun 21 08:19:33 2024 \n", + "+---------------------------------------------------------------------------------------+\n", + "| NVIDIA-SMI 545.23.07 Driver Version: 546.12 CUDA Version: 12.3 |\n", + "|-----------------------------------------+----------------------+----------------------+\n", + "| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |\n", + "| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |\n", + "| | | MIG M. |\n", + "|=========================================+======================+======================|\n", + "| 0 NVIDIA GeForce RTX 4080 ... On | 00000000:01:00.0 On | N/A |\n", + "| N/A 52C P8 5W / 150W | 1156MiB / 12282MiB | 20% Default |\n", + "| | | N/A |\n", + "+-----------------------------------------+----------------------+----------------------+\n", + " \n", + "+---------------------------------------------------------------------------------------+\n", + "| Processes: |\n", + "| GPU GI CI PID Type Process name GPU Memory |\n", + "| ID ID Usage |\n", + "|=======================================================================================|\n", + "| No running processes found |\n", + "+---------------------------------------------------------------------------------------+\n" + ] + } + ], + "source": [ + "!nvidia-smi" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Current Directory:\n", + "/home/inflaton/code/projects/courses/novel-translation\n", + "Tuning unsloth/Qwen2-0.5B-Instruct-bnb-4bit\n", + "πŸ¦₯ Unsloth: Will patch your computer to enable 2x faster free finetuning.\n", + "[nltk_data] Downloading package wordnet to /home/inflaton/nltk_data...\n", + "[nltk_data] Package wordnet is already up-to-date!\n", + "[nltk_data] Downloading package punkt to /home/inflaton/nltk_data...\n", + "[nltk_data] Package punkt is already up-to-date!\n", + "[nltk_data] Downloading package omw-1.4 to /home/inflaton/nltk_data...\n", + "[nltk_data] Package omw-1.4 is already up-to-date!\n", + "loading /home/inflaton/code/projects/courses/novel-translation/translation_engine.py\n", + "loading env vars from: /home/inflaton/code/projects/courses/novel-translation/.env\n", + "unsloth/Qwen2-0.5B-Instruct-bnb-4bit True 2048 10 None datasets/mac/mac.tsv results/mac-results.csv True True True\n", + "(1) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "0.0 GB of memory reserved.\n", + "loading model: unsloth/Qwen2-0.5B-Instruct-bnb-4bit\n", + "==((====))== Unsloth: Fast Qwen2 patching release 2024.6\n", + " \\\\ /| GPU: NVIDIA GeForce RTX 4080 Laptop GPU. Max memory: 11.994 GB. Platform = Linux.\n", + "O^O/ \\_/ \\ Pytorch: 2.3.0. CUDA = 8.9. CUDA Toolkit = 12.1.\n", + "\\ / Bfloat16 = TRUE. Xformers = 0.0.26.post1. FA = False.\n", + " \"-____-\" Free Apache license: http://github.com/unslothai/unsloth\n", + "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n", + "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n", + "(2) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "0.633 GB of memory reserved.\n", + "loading train/test data files\n", + "DatasetDict({\n", + " train: Dataset({\n", + " features: ['chinese', 'english', 'text', 'prompt'],\n", + " num_rows: 4528\n", + " })\n", + " test: Dataset({\n", + " features: ['chinese', 'english', 'text', 'prompt'],\n", + " num_rows: 1133\n", + " })\n", + "})\n", + "Evaluating base model: unsloth/Qwen2-0.5B-Instruct-bnb-4bit\n", + "100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1133/1133 [41:53<00:00, 2.22s/it]\n", + " chinese ... unsloth/Qwen2-0.5B-Instruct-bnb-4bit\n", + "0 老耿端衷ζžͺοΌŒηœ―ηΌθ΅·δΈ€εͺδΈ‰θ§’ηœΌοΌŒδΈ€ζ‚ζ‰³ζœΊε“δΊ†ζžͺοΌŒε†°ι›Ήθˆ¬ηš„ι‡‘ιΊ»ι›€εŠˆε“©ε•ͺε•¦εΎ€δΈ‹θ½οΌŒι“η ‚ε­εœ¨ζŸ³ζžι—΄ι£ž... ... Old Teng raised his gun and looked up at a pai...\n", + "\n", + "[1 rows x 3 columns]\n", + "(3) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "3.023 GB of memory reserved.\n", + "Unsloth 2024.6 patched 24 layers with 0 QKV layers, 24 O layers and 24 MLP layers.\n", + "(4) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "3.023 GB of memory reserved.\n", + "==((====))== Unsloth - 2x faster free finetuning | Num GPUs = 1\n", + " \\\\ /| Num examples = 4,528 | Num Epochs = 10\n", + "O^O/ \\_/ \\ Batch size per device = 2 | Gradient Accumulation steps = 4\n", + "\\ / Total batch size = 8 | Total steps = 5,660\n", + " \"-____-\" Number of trainable parameters = 8,798,208\n", + "{'loss': 1.9401, 'grad_norm': 0.9639493823051453, 'learning_rate': 0.00019664014146772768, 'epoch': 0.18}\n", + "{'loss': 1.7762, 'grad_norm': 0.807873547077179, 'learning_rate': 0.0001931034482758621, 'epoch': 0.35}\n", + "{'loss': 1.7147, 'grad_norm': 0.9143684506416321, 'learning_rate': 0.00018956675508399648, 'epoch': 0.53}\n", + "{'loss': 1.7154, 'grad_norm': 0.753039538860321, 'learning_rate': 0.00018603006189213086, 'epoch': 0.71}\n", + "{'loss': 1.6864, 'grad_norm': 0.8280349373817444, 'learning_rate': 0.00018249336870026527, 'epoch': 0.88}\n", + "{'loss': 1.6079, 'grad_norm': 0.8070634603500366, 'learning_rate': 0.00017895667550839965, 'epoch': 1.06}\n", + "{'loss': 1.492, 'grad_norm': 0.906767725944519, 'learning_rate': 0.00017541998231653406, 'epoch': 1.24}\n", + "{'loss': 1.5407, 'grad_norm': 0.9825711250305176, 'learning_rate': 0.00017188328912466844, 'epoch': 1.41}\n", + "{'loss': 1.4724, 'grad_norm': 1.0809648036956787, 'learning_rate': 0.00016834659593280285, 'epoch': 1.59}\n", + "{'loss': 1.4687, 'grad_norm': 0.9906221032142639, 'learning_rate': 0.00016480990274093723, 'epoch': 1.77}\n", + "{'loss': 1.5277, 'grad_norm': 1.0263370275497437, 'learning_rate': 0.00016127320954907164, 'epoch': 1.94}\n", + "{'loss': 1.3495, 'grad_norm': 1.1578023433685303, 'learning_rate': 0.000157736516357206, 'epoch': 2.12}\n", + "{'loss': 1.2153, 'grad_norm': 1.1819669008255005, 'learning_rate': 0.0001541998231653404, 'epoch': 2.3}\n", + "{'loss': 1.2577, 'grad_norm': 1.3301641941070557, 'learning_rate': 0.0001506631299734748, 'epoch': 2.47}\n", + "{'loss': 1.2556, 'grad_norm': 1.3167439699172974, 'learning_rate': 0.0001471264367816092, 'epoch': 2.65}\n", + "{'loss': 1.2661, 'grad_norm': 1.1702375411987305, 'learning_rate': 0.0001435897435897436, 'epoch': 2.83}\n", + "{'loss': 1.235, 'grad_norm': 1.1984246969223022, 'learning_rate': 0.000140053050397878, 'epoch': 3.0}\n", + "{'loss': 0.9804, 'grad_norm': 1.4932502508163452, 'learning_rate': 0.0001365163572060124, 'epoch': 3.18}\n", + "{'loss': 0.9925, 'grad_norm': 1.5164968967437744, 'learning_rate': 0.00013297966401414678, 'epoch': 3.36}\n", + "{'loss': 0.9981, 'grad_norm': 1.529332160949707, 'learning_rate': 0.0001294429708222812, 'epoch': 3.53}\n", + "{'loss': 0.9808, 'grad_norm': 1.5573309659957886, 'learning_rate': 0.00012590627763041555, 'epoch': 3.71}\n", + "{'loss': 1.0228, 'grad_norm': 1.630372166633606, 'learning_rate': 0.00012236958443854996, 'epoch': 3.89}\n", + "{'loss': 0.9318, 'grad_norm': 1.5458662509918213, 'learning_rate': 0.00011883289124668435, 'epoch': 4.06}\n", + "{'loss': 0.7395, 'grad_norm': 1.7877501249313354, 'learning_rate': 0.00011529619805481875, 'epoch': 4.24}\n", + "{'loss': 0.7408, 'grad_norm': 1.831641435623169, 'learning_rate': 0.00011175950486295315, 'epoch': 4.42}\n", + "{'loss': 0.7743, 'grad_norm': 2.053892135620117, 'learning_rate': 0.00010822281167108754, 'epoch': 4.59}\n", + "{'loss': 0.7734, 'grad_norm': 2.142253875732422, 'learning_rate': 0.00010468611847922194, 'epoch': 4.77}\n", + "{'loss': 0.7944, 'grad_norm': 2.088791847229004, 'learning_rate': 0.00010114942528735633, 'epoch': 4.95}\n", + "{'loss': 0.6303, 'grad_norm': 1.8649368286132812, 'learning_rate': 9.761273209549072e-05, 'epoch': 5.12}\n", + "{'loss': 0.5557, 'grad_norm': 1.5683393478393555, 'learning_rate': 9.407603890362513e-05, 'epoch': 5.3}\n", + "{'loss': 0.56, 'grad_norm': 1.6868833303451538, 'learning_rate': 9.053934571175951e-05, 'epoch': 5.48}\n", + "{'loss': 0.5884, 'grad_norm': 1.896024465560913, 'learning_rate': 8.70026525198939e-05, 'epoch': 5.65}\n", + "{'loss': 0.5797, 'grad_norm': 2.199939489364624, 'learning_rate': 8.34659593280283e-05, 'epoch': 5.83}\n", + "{'loss': 0.5782, 'grad_norm': 1.5285065174102783, 'learning_rate': 7.99292661361627e-05, 'epoch': 6.01}\n", + "{'loss': 0.3976, 'grad_norm': 2.0019567012786865, 'learning_rate': 7.639257294429708e-05, 'epoch': 6.18}\n", + "{'loss': 0.411, 'grad_norm': 1.8241479396820068, 'learning_rate': 7.285587975243147e-05, 'epoch': 6.36}\n", + "{'loss': 0.4288, 'grad_norm': 2.22087025642395, 'learning_rate': 6.931918656056587e-05, 'epoch': 6.54}\n", + "{'loss': 0.4213, 'grad_norm': 1.6254255771636963, 'learning_rate': 6.578249336870027e-05, 'epoch': 6.71}\n", + "{'loss': 0.4276, 'grad_norm': 1.4894341230392456, 'learning_rate': 6.224580017683466e-05, 'epoch': 6.89}\n", + "{'loss': 0.3844, 'grad_norm': 1.7346247434616089, 'learning_rate': 5.870910698496905e-05, 'epoch': 7.07}\n", + "{'loss': 0.2934, 'grad_norm': 1.558210015296936, 'learning_rate': 5.517241379310345e-05, 'epoch': 7.24}\n", + "{'loss': 0.3127, 'grad_norm': 1.2885392904281616, 'learning_rate': 5.163572060123785e-05, 'epoch': 7.42}\n", + "{'loss': 0.3137, 'grad_norm': 1.7340631484985352, 'learning_rate': 4.809902740937224e-05, 'epoch': 7.6}\n", + "{'loss': 0.3042, 'grad_norm': 1.8956586122512817, 'learning_rate': 4.4562334217506634e-05, 'epoch': 7.77}\n", + "{'loss': 0.3177, 'grad_norm': 1.6758400201797485, 'learning_rate': 4.1025641025641023e-05, 'epoch': 7.95}\n", + "{'loss': 0.2466, 'grad_norm': 1.4491084814071655, 'learning_rate': 3.7488947833775426e-05, 'epoch': 8.13}\n", + "{'loss': 0.226, 'grad_norm': 1.810203194618225, 'learning_rate': 3.3952254641909815e-05, 'epoch': 8.3}\n", + "{'loss': 0.2294, 'grad_norm': 1.1841636896133423, 'learning_rate': 3.041556145004421e-05, 'epoch': 8.48}\n", + "{'loss': 0.2356, 'grad_norm': 1.1479746103286743, 'learning_rate': 2.6878868258178604e-05, 'epoch': 8.66}\n", + "{'loss': 0.2364, 'grad_norm': 1.9742052555084229, 'learning_rate': 2.3342175066313e-05, 'epoch': 8.83}\n", + "{'loss': 0.2392, 'grad_norm': 1.2130563259124756, 'learning_rate': 1.9805481874447392e-05, 'epoch': 9.01}\n", + "{'loss': 0.181, 'grad_norm': 1.0886257886886597, 'learning_rate': 1.6268788682581788e-05, 'epoch': 9.19}\n", + "{'loss': 0.1906, 'grad_norm': 1.0989885330200195, 'learning_rate': 1.273209549071618e-05, 'epoch': 9.36}\n", + "{'loss': 0.1877, 'grad_norm': 1.1791963577270508, 'learning_rate': 9.195402298850575e-06, 'epoch': 9.54}\n", + "{'loss': 0.1881, 'grad_norm': 1.712857961654663, 'learning_rate': 5.658709106984969e-06, 'epoch': 9.72}\n", + "{'loss': 0.1891, 'grad_norm': 0.9620760083198547, 'learning_rate': 2.1220159151193635e-06, 'epoch': 9.89}\n", + "{'train_runtime': 5102.7155, 'train_samples_per_second': 8.874, 'train_steps_per_second': 1.109, 'train_loss': 0.7989002002001652, 'epoch': 10.0}\n", + "100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 5660/5660 [1:25:02<00:00, 1.11it/s]\n", + "(5) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "5102.7155 seconds used for training.\n", + "85.05 minutes used for training.\n", + "Peak reserved memory = 3.023 GB.\n", + "Peak reserved memory for training = 0.0 GB.\n", + "Peak reserved memory % of max memory = 25.204 %.\n", + "Peak reserved memory for training % of max memory = 0.0 %.\n", + "Evaluating fine-tuned model: unsloth/Qwen2-0.5B-Instruct-bnb-4bit\n", + "100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1133/1133 [36:52<00:00, 1.95s/it]\n", + " chinese ... unsloth/Qwen2-0.5B-Instruct-bnb-4bit(finetuned)\n", + "0 老耿端衷ζžͺοΌŒηœ―ηΌθ΅·δΈ€εͺδΈ‰θ§’ηœΌοΌŒδΈ€ζ‚ζ‰³ζœΊε“δΊ†ζžͺοΌŒε†°ι›Ήθˆ¬ηš„ι‡‘ιΊ»ι›€εŠˆε“©ε•ͺε•¦εΎ€δΈ‹θ½οΌŒι“η ‚ε­εœ¨ζŸ³ζžι—΄ι£ž... ... Old Geng raised his rifle, squinted his eyes, ...\n", + "\n", + "[1 rows x 4 columns]\n", + "(6) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "3.023 GB of memory reserved.\n", + "Unsloth: Merging 4bit and LoRA weights to 4bit...\n", + "This might take 5 minutes...\n", + "Done.\n", + "Unsloth: Saving tokenizer... Done.\n", + "Unsloth: Saving model... This might take 10 minutes for Llama-7b... Done.\n", + "make: Entering directory '/home/inflaton/code/projects/courses/novel-translation/llama.cpp'\n", + "I ccache not found. Consider installing it for faster compilation.\n", + "I llama.cpp build info: \n", + "I UNAME_S: Linux\n", + "I UNAME_P: x86_64\n", + "I UNAME_M: x86_64\n", + "I CFLAGS: -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_OPENMP -DGGML_USE_LLAMAFILE -std=c11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wshadow -Wstrict-prototypes -Wpointer-arith -Wmissing-prototypes -Werror=implicit-int -Werror=implicit-function-declaration -pthread -march=native -mtune=native -fopenmp -Wdouble-promotion \n", + "I CXXFLAGS: -std=c++11 -fPIC -O3 -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wmissing-declarations -Wmissing-noreturn -pthread -fopenmp -march=native -mtune=native -Wno-array-bounds -Wno-format-truncation -Wextra-semi -I. -Icommon -D_XOPEN_SOURCE=600 -D_GNU_SOURCE -DNDEBUG -DGGML_USE_OPENMP -DGGML_USE_LLAMAFILE \n", + "I NVCCFLAGS: -std=c++11 -O3 \n", + "I LDFLAGS: \n", + "I CC: cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\n", + "I CXX: c++ (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0\n", + "\n", + "rm -vrf *.o tests/*.o *.so *.a *.dll common/build-info.cpp *.dot *.gcno tests/*.gcno *.gcda tests/*.gcda *.gcov tests/*.gcov lcov-report gcovr-report libllava.a llama-baby-llama llama-batched llama-batched-bench llama-bench llama-benchmark-matmult llama-cli llama-convert-llama2c-to-ggml llama-embedding llama-eval-callback llama-export-lora llama-finetune llama-gbnf-validator llama-gguf llama-gguf-split llama-gritlm llama-imatrix llama-infill llama-llava-cli llama-lookahead llama-lookup llama-lookup-create llama-lookup-merge llama-lookup-stats llama-parallel llama-passkey llama-perplexity llama-q8dot llama-quantize llama-quantize-stats llama-retrieval llama-save-load-state llama-server llama-simple llama-speculative llama-tokenize llama-train-text-from-scratch llama-vdot llama-cvector-generator tests/test-c.o tests/test-autorelease tests/test-backend-ops tests/test-double-float tests/test-grad0 tests/test-grammar-integration tests/test-grammar-parser tests/test-json-schema-to-grammar tests/test-llama-grammar tests/test-model-load-cancel tests/test-opt tests/test-quantize-fns tests/test-quantize-perf tests/test-rope tests/test-sampling tests/test-tokenizer-0 tests/test-tokenizer-1-bpe tests/test-tokenizer-1-spm\n", + "rm -vrf ggml-cuda/*.o\n", + "rm -vrf ggml-cuda/template-instances/*.o\n", + "find examples pocs -type f -name \"*.o\" -delete\n", + "make: Leaving directory '/home/inflaton/code/projects/courses/novel-translation/llama.cpp'\n", + "Unsloth: Merging 4bit and LoRA weights to 16bit...\n", + "Unsloth: Will use up to 30.26 out of 47.05 RAM for saving.\n", + "100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 24/24 [00:00<00:00, 43.09it/s]\n", + "Unsloth: Saving tokenizer... Done.\n", + "Unsloth: Saving model... This might take 5 minutes for Llama-7b...\n", + "Done.\n", + "Unsloth: Converting qwen2 model. Can use fast conversion = False.\n", + "==((====))== Unsloth: Conversion from QLoRA to GGUF information\n", + " \\\\ /| [0] Installing llama.cpp will take 3 minutes.\n", + "O^O/ \\_/ \\ [1] Converting HF to GUUF 16bits will take 3 minutes.\n", + "\\ / [2] Converting GGUF 16bits to ['q5_k_m'] will take 10 minutes each.\n", + " \"-____-\" In total, you will have to wait at least 16 minutes.\n", + "\n", + "Unsloth: [0] Installing llama.cpp. This will take 3 minutes...\n", + "Unsloth: [1] Converting model at models/Qwen2-0.5B-Instruct-bnb-4bit-MAC-q5_k_m into bf16 GGUF format.\n", + "The output location will be ./models/Qwen2-0.5B-Instruct-bnb-4bit-MAC-q5_k_m/unsloth.BF16.gguf\n", + "This will take 3 minutes...\n", + "INFO:hf-to-gguf:Loading model: Qwen2-0.5B-Instruct-bnb-4bit-MAC-q5_k_m\n", + "INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only\n", + "INFO:hf-to-gguf:Set model parameters\n", + "INFO:hf-to-gguf:gguf: context length = 32768\n", + "INFO:hf-to-gguf:gguf: embedding length = 896\n", + "INFO:hf-to-gguf:gguf: feed forward length = 4864\n", + "INFO:hf-to-gguf:gguf: head count = 14\n", + "INFO:hf-to-gguf:gguf: key-value head count = 2\n", + "INFO:hf-to-gguf:gguf: rope theta = 1000000.0\n", + "INFO:hf-to-gguf:gguf: rms norm epsilon = 1e-06\n", + "INFO:hf-to-gguf:gguf: file type = 32\n", + "INFO:hf-to-gguf:Set model tokenizer\n", + "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n", + "INFO:gguf.vocab:Adding 151387 merge(s).\n", + "INFO:gguf.vocab:Setting special token type eos to 151645\n", + "INFO:gguf.vocab:Setting special token type pad to 151643\n", + "INFO:gguf.vocab:Setting special token type bos to 151643\n", + "INFO:gguf.vocab:Setting chat_template to {% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\n", + "You are a helpful assistant.<|im_end|>\n", + "' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n", + "' + message['content'] + '<|im_end|>' + '\n", + "'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n", + "' }}{% endif %}\n", + "INFO:hf-to-gguf:Exporting model to 'models/Qwen2-0.5B-Instruct-bnb-4bit-MAC-q5_k_m/unsloth.BF16.gguf'\n", + "INFO:hf-to-gguf:gguf: loading model part 'model.safetensors'\n", + "INFO:hf-to-gguf:token_embd.weight, torch.bfloat16 --> BF16, shape = {896, 151936}\n", + "INFO:hf-to-gguf:blk.0.attn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.0.ffn_down.weight, torch.bfloat16 --> BF16, shape = {4864, 896}\n", + "INFO:hf-to-gguf:blk.0.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.0.ffn_up.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.0.ffn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.0.attn_k.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.0.attn_k.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.0.attn_output.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.0.attn_q.bias, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.0.attn_q.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.0.attn_v.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.0.attn_v.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.1.attn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.1.ffn_down.weight, torch.bfloat16 --> BF16, shape = {4864, 896}\n", + "INFO:hf-to-gguf:blk.1.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.1.ffn_up.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.1.ffn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.1.attn_k.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.1.attn_k.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.1.attn_output.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.1.attn_q.bias, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.1.attn_q.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.1.attn_v.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.1.attn_v.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.10.attn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.10.ffn_down.weight, torch.bfloat16 --> BF16, shape = {4864, 896}\n", + "INFO:hf-to-gguf:blk.10.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.10.ffn_up.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.10.ffn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.10.attn_k.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.10.attn_k.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.10.attn_output.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.10.attn_q.bias, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.10.attn_q.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.10.attn_v.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.10.attn_v.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.11.attn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.11.ffn_down.weight, torch.bfloat16 --> BF16, shape = {4864, 896}\n", + "INFO:hf-to-gguf:blk.11.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.11.ffn_up.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.11.ffn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.11.attn_k.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.11.attn_k.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.11.attn_output.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.11.attn_q.bias, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.11.attn_q.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.11.attn_v.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.11.attn_v.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.12.attn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.12.ffn_down.weight, torch.bfloat16 --> BF16, shape = {4864, 896}\n", + "INFO:hf-to-gguf:blk.12.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.12.ffn_up.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.12.ffn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.12.attn_k.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.12.attn_k.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.12.attn_output.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.12.attn_q.bias, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.12.attn_q.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.12.attn_v.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.12.attn_v.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.13.attn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.13.ffn_down.weight, torch.bfloat16 --> BF16, shape = {4864, 896}\n", + "INFO:hf-to-gguf:blk.13.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.13.ffn_up.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.13.ffn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.13.attn_k.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.13.attn_k.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.13.attn_output.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.13.attn_q.bias, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.13.attn_q.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.13.attn_v.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.13.attn_v.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.14.attn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.14.ffn_down.weight, torch.bfloat16 --> BF16, shape = {4864, 896}\n", + "INFO:hf-to-gguf:blk.14.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.14.ffn_up.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.14.ffn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.14.attn_k.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.14.attn_k.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.14.attn_output.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.14.attn_q.bias, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.14.attn_q.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.14.attn_v.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.14.attn_v.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.15.attn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.15.ffn_down.weight, torch.bfloat16 --> BF16, shape = {4864, 896}\n", + "INFO:hf-to-gguf:blk.15.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.15.ffn_up.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.15.ffn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.15.attn_k.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.15.attn_k.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.15.attn_output.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.15.attn_q.bias, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.15.attn_q.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.15.attn_v.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.15.attn_v.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.16.attn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.16.ffn_down.weight, torch.bfloat16 --> BF16, shape = {4864, 896}\n", + "INFO:hf-to-gguf:blk.16.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.16.ffn_up.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.16.ffn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.16.attn_k.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.16.attn_k.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.16.attn_output.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.16.attn_q.bias, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.16.attn_q.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.16.attn_v.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.16.attn_v.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.17.attn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.17.ffn_down.weight, torch.bfloat16 --> BF16, shape = {4864, 896}\n", + "INFO:hf-to-gguf:blk.17.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.17.ffn_up.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.17.ffn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.17.attn_k.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.17.attn_k.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.17.attn_output.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.17.attn_q.bias, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.17.attn_q.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.17.attn_v.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.17.attn_v.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.18.attn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.18.ffn_down.weight, torch.bfloat16 --> BF16, shape = {4864, 896}\n", + "INFO:hf-to-gguf:blk.18.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.18.ffn_up.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.18.ffn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.18.attn_k.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.18.attn_k.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.18.attn_output.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.18.attn_q.bias, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.18.attn_q.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.18.attn_v.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.18.attn_v.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.19.attn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.19.ffn_down.weight, torch.bfloat16 --> BF16, shape = {4864, 896}\n", + "INFO:hf-to-gguf:blk.19.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.19.ffn_up.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.19.ffn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.19.attn_k.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.19.attn_k.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.19.attn_output.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.19.attn_q.bias, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.19.attn_q.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.19.attn_v.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.19.attn_v.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.2.attn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.2.ffn_down.weight, torch.bfloat16 --> BF16, shape = {4864, 896}\n", + "INFO:hf-to-gguf:blk.2.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.2.ffn_up.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.2.ffn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.2.attn_k.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.2.attn_k.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.2.attn_output.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.2.attn_q.bias, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.2.attn_q.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.2.attn_v.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.2.attn_v.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.20.attn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.20.ffn_down.weight, torch.bfloat16 --> BF16, shape = {4864, 896}\n", + "INFO:hf-to-gguf:blk.20.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.20.ffn_up.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.20.ffn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.20.attn_k.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.20.attn_k.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.20.attn_output.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.20.attn_q.bias, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.20.attn_q.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.20.attn_v.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.20.attn_v.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.21.attn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.21.ffn_down.weight, torch.bfloat16 --> BF16, shape = {4864, 896}\n", + "INFO:hf-to-gguf:blk.21.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.21.ffn_up.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.21.ffn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.21.attn_k.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.21.attn_k.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.21.attn_output.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.21.attn_q.bias, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.21.attn_q.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.21.attn_v.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.21.attn_v.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.22.attn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.22.ffn_down.weight, torch.bfloat16 --> BF16, shape = {4864, 896}\n", + "INFO:hf-to-gguf:blk.22.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.22.ffn_up.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.22.ffn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.22.attn_k.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.22.attn_k.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.22.attn_output.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.22.attn_q.bias, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.22.attn_q.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.22.attn_v.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.22.attn_v.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.23.attn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.23.ffn_down.weight, torch.bfloat16 --> BF16, shape = {4864, 896}\n", + "INFO:hf-to-gguf:blk.23.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.23.ffn_up.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.23.ffn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.23.attn_k.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.23.attn_k.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.23.attn_output.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.23.attn_q.bias, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.23.attn_q.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.23.attn_v.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.23.attn_v.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.3.attn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.3.ffn_down.weight, torch.bfloat16 --> BF16, shape = {4864, 896}\n", + "INFO:hf-to-gguf:blk.3.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.3.ffn_up.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.3.ffn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.3.attn_k.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.3.attn_k.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.3.attn_output.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.3.attn_q.bias, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.3.attn_q.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.3.attn_v.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.3.attn_v.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.4.attn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.4.ffn_down.weight, torch.bfloat16 --> BF16, shape = {4864, 896}\n", + "INFO:hf-to-gguf:blk.4.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.4.ffn_up.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.4.ffn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.4.attn_k.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.4.attn_k.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.4.attn_output.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.4.attn_q.bias, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.4.attn_q.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.4.attn_v.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.4.attn_v.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.5.attn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.5.ffn_down.weight, torch.bfloat16 --> BF16, shape = {4864, 896}\n", + "INFO:hf-to-gguf:blk.5.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.5.ffn_up.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.5.ffn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.5.attn_k.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.5.attn_k.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.5.attn_output.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.5.attn_q.bias, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.5.attn_q.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.5.attn_v.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.5.attn_v.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.6.attn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.6.ffn_down.weight, torch.bfloat16 --> BF16, shape = {4864, 896}\n", + "INFO:hf-to-gguf:blk.6.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.6.ffn_up.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.6.ffn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.6.attn_k.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.6.attn_k.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.6.attn_output.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.6.attn_q.bias, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.6.attn_q.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.6.attn_v.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.6.attn_v.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.7.attn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.7.ffn_down.weight, torch.bfloat16 --> BF16, shape = {4864, 896}\n", + "INFO:hf-to-gguf:blk.7.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.7.ffn_up.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.7.ffn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.7.attn_k.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.7.attn_k.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.7.attn_output.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.7.attn_q.bias, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.7.attn_q.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.7.attn_v.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.7.attn_v.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.8.attn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.8.ffn_down.weight, torch.bfloat16 --> BF16, shape = {4864, 896}\n", + "INFO:hf-to-gguf:blk.8.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.8.ffn_up.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.8.ffn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.8.attn_k.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.8.attn_k.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.8.attn_output.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.8.attn_q.bias, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.8.attn_q.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.8.attn_v.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.8.attn_v.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.9.attn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.9.ffn_down.weight, torch.bfloat16 --> BF16, shape = {4864, 896}\n", + "INFO:hf-to-gguf:blk.9.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.9.ffn_up.weight, torch.bfloat16 --> BF16, shape = {896, 4864}\n", + "INFO:hf-to-gguf:blk.9.ffn_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.9.attn_k.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.9.attn_k.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:blk.9.attn_output.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.9.attn_q.bias, torch.bfloat16 --> F32, shape = {896}\n", + "INFO:hf-to-gguf:blk.9.attn_q.weight, torch.bfloat16 --> BF16, shape = {896, 896}\n", + "INFO:hf-to-gguf:blk.9.attn_v.bias, torch.bfloat16 --> F32, shape = {128}\n", + "INFO:hf-to-gguf:blk.9.attn_v.weight, torch.bfloat16 --> BF16, shape = {896, 128}\n", + "INFO:hf-to-gguf:output_norm.weight, torch.bfloat16 --> F32, shape = {896}\n", + "Writing: 0%| | 0.00/988M [00:00\n", + " main()\n", + " File \"/home/inflaton/code/projects/courses/novel-translation/llama.cpp/convert-hf-to-gguf.py\", line 2881, in main\n", + " model_instance.write()\n", + " File \"/home/inflaton/code/projects/courses/novel-translation/llama.cpp/convert-hf-to-gguf.py\", line 331, in write\n", + " self.gguf_writer.write_tensors_to_file(progress=True)\n", + " File \"/home/inflaton/code/projects/courses/novel-translation/llama.cpp/gguf-py/gguf/gguf_writer.py\", line 312, in write_tensors_to_file\n", + " ti.tensor.tofile(self.fout)\n", + " File \"/home/inflaton/code/projects/courses/novel-translation/llama.cpp/gguf-py/gguf/lazy.py\", line 233, in tofile\n", + " eager = LazyNumpyTensor.to_eager(self)\n", + " File \"/home/inflaton/code/projects/courses/novel-translation/llama.cpp/gguf-py/gguf/lazy.py\", line 193, in to_eager\n", + " return cls._recurse_apply(t, simple_to_eager)\n", + " File \"/home/inflaton/code/projects/courses/novel-translation/llama.cpp/gguf-py/gguf/lazy.py\", line 109, in _recurse_apply\n", + " return fn(o)\n", + " File \"/home/inflaton/code/projects/courses/novel-translation/llama.cpp/gguf-py/gguf/lazy.py\", line 185, in simple_to_eager\n", + " lt._data = lt._func(lt._args)\n", + " File \"/home/inflaton/code/projects/courses/novel-translation/llama.cpp/gguf-py/gguf/lazy.py\", line 158, in \n", + " return cls(meta=cls.eager_to_meta(res), lazy=shared_lazy, args=args, func=lambda a: fn(*a, **kwargs))\n", + " File \"/home/inflaton/code/projects/courses/novel-translation/llama.cpp/gguf-py/gguf/quants.py\", line 52, in __quantize_bf16_array\n", + " return __apply_over_grouped_rows(__compute_fp32_to_bf16, arr=n, otype=np.int16, oshape=n.shape)\n", + " File \"/home/inflaton/code/projects/courses/novel-translation/llama.cpp/gguf-py/gguf/quants.py\", line 47, in __apply_over_grouped_rows\n", + " np.concatenate([func(group).ravel() for group in np.array_split(rows, n_groups)], axis=0, out=out)\n", + " File \"/home/inflaton/code/projects/courses/novel-translation/llama.cpp/gguf-py/gguf/quants.py\", line 47, in \n", + " np.concatenate([func(group).ravel() for group in np.array_split(rows, n_groups)], axis=0, out=out)\n", + " File \"/home/inflaton/code/projects/courses/novel-translation/llama.cpp/gguf-py/gguf/quants.py\", line 30, in __compute_fp32_to_bf16\n", + " n = np.where((n & 0x7fffffff) > 0x7f800000, (n & 0xffff0000) | (64 << 16), n)\n", + "OverflowError: Python integer 4294901760 out of bounds for int32\n", + "Writing: 0%| | 0.00/988M [00:00\n", + " save_model(model, tokenizer)\n", + " File \"/home/inflaton/code/projects/courses/novel-translation/translation_engine.py\", line 219, in save_model\n", + " model.save_pretrained_gguf(\n", + " File \"/home/inflaton/miniconda3/envs/unsloth_env/lib/python3.10/site-packages/unsloth/save.py\", line 1527, in unsloth_save_pretrained_gguf\n", + " all_file_locations = save_to_gguf(model_type, model_dtype, is_sentencepiece_model,\n", + " File \"/home/inflaton/miniconda3/envs/unsloth_env/lib/python3.10/site-packages/unsloth/save.py\", line 1113, in save_to_gguf\n", + " raise RuntimeError(\n", + "RuntimeError: Unsloth: Quantization failed! You might have to compile llama.cpp yourself, then run this again.\n", + "You do not need to close this Python program. Run the following commands in a new terminal:\n", + "You must run this in the same folder as you're saving your model.\n", + "git clone --recursive https://github.com/ggerganov/llama.cpp\n", + "cd llama.cpp && make clean && make all -j\n", + "Once that's done, redo the quantization.\n", + "Tuning unsloth/Qwen2-1.5B-Instruct-bnb-4bit\n", + "πŸ¦₯ Unsloth: Will patch your computer to enable 2x faster free finetuning.\n", + "[nltk_data] Downloading package wordnet to /home/inflaton/nltk_data...\n", + "[nltk_data] Package wordnet is already up-to-date!\n", + "[nltk_data] Downloading package punkt to /home/inflaton/nltk_data...\n", + "[nltk_data] Package punkt is already up-to-date!\n", + "[nltk_data] Downloading package omw-1.4 to /home/inflaton/nltk_data...\n", + "[nltk_data] Package omw-1.4 is already up-to-date!\n", + "loading /home/inflaton/code/projects/courses/novel-translation/translation_engine.py\n", + "loading env vars from: /home/inflaton/code/projects/courses/novel-translation/.env\n", + "unsloth/Qwen2-1.5B-Instruct-bnb-4bit True 2048 10 None datasets/mac/mac.tsv results/mac-results.csv True True True\n", + "(1) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "0.0 GB of memory reserved.\n", + "loading model: unsloth/Qwen2-1.5B-Instruct-bnb-4bit\n", + "==((====))== Unsloth: Fast Qwen2 patching release 2024.6\n", + " \\\\ /| GPU: NVIDIA GeForce RTX 4080 Laptop GPU. Max memory: 11.994 GB. Platform = Linux.\n", + "O^O/ \\_/ \\ Pytorch: 2.3.0. CUDA = 8.9. CUDA Toolkit = 12.1.\n", + "\\ / Bfloat16 = TRUE. Xformers = 0.0.26.post1. FA = False.\n", + " \"-____-\" Free Apache license: http://github.com/unslothai/unsloth\n", + "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n", + "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n", + "(2) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "1.516 GB of memory reserved.\n", + "loading train/test data files\n", + "DatasetDict({\n", + " train: Dataset({\n", + " features: ['chinese', 'english', 'text', 'prompt'],\n", + " num_rows: 4528\n", + " })\n", + " test: Dataset({\n", + " features: ['chinese', 'english', 'text', 'prompt'],\n", + " num_rows: 1133\n", + " })\n", + "})\n", + "Evaluating base model: unsloth/Qwen2-1.5B-Instruct-bnb-4bit\n", + "100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1133/1133 [59:36<00:00, 3.16s/it]\n", + " chinese ... unsloth/Qwen2-1.5B-Instruct-bnb-4bit\n", + "0 老耿端衷ζžͺοΌŒηœ―ηΌθ΅·δΈ€εͺδΈ‰θ§’ηœΌοΌŒδΈ€ζ‚ζ‰³ζœΊε“δΊ†ζžͺοΌŒε†°ι›Ήθˆ¬ηš„ι‡‘ιΊ»ι›€εŠˆε“©ε•ͺε•¦εΎ€δΈ‹θ½οΌŒι“η ‚ε­εœ¨ζŸ³ζžι—΄ι£ž... ... Oldθ€Ώζ‹Ώθ΅·ζžͺοΌŒηœ―η€ηœΌη›δΈ€ζ‚ζ‰³ζœΊε°±ε“δΊ†ζžͺοΌŒι‡‘ιΊ»ι›€ε™Όι‡Œε•ͺε•¦ηš„εΎ€δΈ‹ζŽ‰οΌŒι“η ‚ε­εœ¨ζŸ³ζžι—΄ι£žζΊ…οΌŒε‘ε‡Ίβ€œ...\n", + "\n", + "[1 rows x 5 columns]\n", + "(3) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "3.945 GB of memory reserved.\n", + "Unsloth 2024.6 patched 28 layers with 0 QKV layers, 28 O layers and 28 MLP layers.\n", + "(4) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "3.945 GB of memory reserved.\n", + "==((====))== Unsloth - 2x faster free finetuning | Num GPUs = 1\n", + " \\\\ /| Num examples = 4,528 | Num Epochs = 10\n", + "O^O/ \\_/ \\ Batch size per device = 2 | Gradient Accumulation steps = 4\n", + "\\ / Total batch size = 8 | Total steps = 5,660\n", + " \"-____-\" Number of trainable parameters = 18,464,768\n", + "{'loss': 1.7416, 'grad_norm': 0.6486354470252991, 'learning_rate': 0.00019664014146772768, 'epoch': 0.18}\n", + "{'loss': 1.568, 'grad_norm': 0.6254323124885559, 'learning_rate': 0.0001931034482758621, 'epoch': 0.35}\n", + "{'loss': 1.5159, 'grad_norm': 0.6513530015945435, 'learning_rate': 0.00018956675508399648, 'epoch': 0.53}\n", + "{'loss': 1.5169, 'grad_norm': 0.5732458233833313, 'learning_rate': 0.00018603006189213086, 'epoch': 0.71}\n", + "{'loss': 1.4958, 'grad_norm': 0.5724458694458008, 'learning_rate': 0.00018249336870026527, 'epoch': 0.88}\n", + " 9%|β–ˆβ–ˆβ–ˆβ–Ž | 500/5660 [12:05<2:13:34, 1.55s/it]/home/inflaton/miniconda3/envs/unsloth_env/lib/python3.10/site-packages/peft/utils/other.py:611: UserWarning: Unable to fetch remote file due to the following error (MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /unsloth/Qwen2-1.5B-Instruct-bnb-4bit/resolve/main/config.json (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -3] Temporary failure in name resolution)\"))'), '(Request ID: 73fef4ae-41d2-4b61-b3af-92f4996c5ae6)') - silently ignoring the lookup for the file config.json in unsloth/Qwen2-1.5B-Instruct-bnb-4bit.\n", + " warnings.warn(\n", + "/home/inflaton/miniconda3/envs/unsloth_env/lib/python3.10/site-packages/peft/utils/save_and_load.py:195: UserWarning: Could not find a config file in unsloth/Qwen2-1.5B-Instruct-bnb-4bit - will assume that the vocabulary was not modified.\n", + " warnings.warn(\n", + "{'loss': 1.4181, 'grad_norm': 0.6020762324333191, 'learning_rate': 0.00017895667550839965, 'epoch': 1.06}\n", + "{'loss': 1.2977, 'grad_norm': 0.7245773077011108, 'learning_rate': 0.00017541998231653406, 'epoch': 1.24}\n", + "{'loss': 1.3392, 'grad_norm': 0.6871509552001953, 'learning_rate': 0.00017188328912466844, 'epoch': 1.41}\n", + "{'loss': 1.2784, 'grad_norm': 0.89788419008255, 'learning_rate': 0.00016834659593280285, 'epoch': 1.59}\n", + "{'loss': 1.2796, 'grad_norm': 0.8698562383651733, 'learning_rate': 0.00016480990274093723, 'epoch': 1.77}\n", + " 18%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 1000/5660 [25:03<1:52:33, 1.45s/it]/home/inflaton/miniconda3/envs/unsloth_env/lib/python3.10/site-packages/peft/utils/other.py:611: UserWarning: Unable to fetch remote file due to the following error (MaxRetryError('HTTPSConnectionPool(host=\\'huggingface.co\\', port=443): Max retries exceeded with url: /unsloth/Qwen2-1.5B-Instruct-bnb-4bit/resolve/main/config.json (Caused by NameResolutionError(\": Failed to resolve \\'huggingface.co\\' ([Errno -3] Temporary failure in name resolution)\"))'), '(Request ID: aec2499a-0591-44e8-bbc9-1568ebca28ce)') - silently ignoring the lookup for the file config.json in unsloth/Qwen2-1.5B-Instruct-bnb-4bit.\n", + " warnings.warn(\n", + "/home/inflaton/miniconda3/envs/unsloth_env/lib/python3.10/site-packages/peft/utils/save_and_load.py:195: UserWarning: Could not find a config file in unsloth/Qwen2-1.5B-Instruct-bnb-4bit - will assume that the vocabulary was not modified.\n", + " warnings.warn(\n", + "{'loss': 1.3317, 'grad_norm': 0.8551518321037292, 'learning_rate': 0.00016127320954907164, 'epoch': 1.94}\n", + "{'loss': 1.1279, 'grad_norm': 0.9991661310195923, 'learning_rate': 0.000157736516357206, 'epoch': 2.12}\n", + "{'loss': 0.9962, 'grad_norm': 1.0851796865463257, 'learning_rate': 0.0001541998231653404, 'epoch': 2.3}\n", + "{'loss': 1.03, 'grad_norm': 1.223488450050354, 'learning_rate': 0.0001506631299734748, 'epoch': 2.47}\n", + "{'loss': 1.0346, 'grad_norm': 1.1075948476791382, 'learning_rate': 0.0001471264367816092, 'epoch': 2.65}\n", + "{'loss': 1.0356, 'grad_norm': 1.0564122200012207, 'learning_rate': 0.0001435897435897436, 'epoch': 2.83}\n", + "{'loss': 1.0085, 'grad_norm': 0.8879927396774292, 'learning_rate': 0.000140053050397878, 'epoch': 3.0}\n", + "{'loss': 0.6982, 'grad_norm': 1.2948524951934814, 'learning_rate': 0.0001365163572060124, 'epoch': 3.18}\n", + "{'loss': 0.7112, 'grad_norm': 1.411033034324646, 'learning_rate': 0.00013297966401414678, 'epoch': 3.36}\n", + "{'loss': 0.7143, 'grad_norm': 1.2779042720794678, 'learning_rate': 0.0001294429708222812, 'epoch': 3.53}\n", + "{'loss': 0.7048, 'grad_norm': 1.4070408344268799, 'learning_rate': 0.00012590627763041555, 'epoch': 3.71}\n", + "{'loss': 0.7431, 'grad_norm': 1.2386316061019897, 'learning_rate': 0.00012236958443854996, 'epoch': 3.89}\n", + "{'loss': 0.6442, 'grad_norm': 1.4571985006332397, 'learning_rate': 0.00011883289124668435, 'epoch': 4.06}\n", + "{'loss': 0.4587, 'grad_norm': 1.3495371341705322, 'learning_rate': 0.00011529619805481875, 'epoch': 4.24}\n", + "{'loss': 0.4463, 'grad_norm': 1.4228668212890625, 'learning_rate': 0.00011175950486295315, 'epoch': 4.42}\n", + "{'loss': 0.4788, 'grad_norm': 1.4749239683151245, 'learning_rate': 0.00010822281167108754, 'epoch': 4.59}\n", + "{'loss': 0.4788, 'grad_norm': 1.9813690185546875, 'learning_rate': 0.00010468611847922194, 'epoch': 4.77}\n", + "{'loss': 0.4853, 'grad_norm': 1.4942362308502197, 'learning_rate': 0.00010114942528735633, 'epoch': 4.95}\n", + "{'loss': 0.358, 'grad_norm': 1.398263692855835, 'learning_rate': 9.761273209549072e-05, 'epoch': 5.12}\n", + "{'loss': 0.2917, 'grad_norm': 1.148834228515625, 'learning_rate': 9.407603890362513e-05, 'epoch': 5.3}\n", + "{'loss': 0.2974, 'grad_norm': 1.8417447805404663, 'learning_rate': 9.053934571175951e-05, 'epoch': 5.48}\n", + "{'loss': 0.316, 'grad_norm': 1.3501039743423462, 'learning_rate': 8.70026525198939e-05, 'epoch': 5.65}\n", + "{'loss': 0.3081, 'grad_norm': 1.3924249410629272, 'learning_rate': 8.34659593280283e-05, 'epoch': 5.83}\n", + "{'loss': 0.3056, 'grad_norm': 0.7402265071868896, 'learning_rate': 7.99292661361627e-05, 'epoch': 6.01}\n", + "{'loss': 0.1918, 'grad_norm': 1.6596429347991943, 'learning_rate': 7.639257294429708e-05, 'epoch': 6.18}\n", + "{'loss': 0.2038, 'grad_norm': 1.4057574272155762, 'learning_rate': 7.285587975243147e-05, 'epoch': 6.36}\n", + "{'loss': 0.2068, 'grad_norm': 1.0855220556259155, 'learning_rate': 6.931918656056587e-05, 'epoch': 6.54}\n", + "{'loss': 0.2067, 'grad_norm': 1.2501165866851807, 'learning_rate': 6.578249336870027e-05, 'epoch': 6.71}\n", + "{'loss': 0.2132, 'grad_norm': 1.1509685516357422, 'learning_rate': 6.224580017683466e-05, 'epoch': 6.89}\n", + "{'loss': 0.1937, 'grad_norm': 0.7672592401504517, 'learning_rate': 5.870910698496905e-05, 'epoch': 7.07}\n", + "{'loss': 0.1486, 'grad_norm': 0.8496847152709961, 'learning_rate': 5.517241379310345e-05, 'epoch': 7.24}\n", + "{'loss': 0.156, 'grad_norm': 0.8369797468185425, 'learning_rate': 5.163572060123785e-05, 'epoch': 7.42}\n", + "{'loss': 0.1561, 'grad_norm': 0.8741617202758789, 'learning_rate': 4.809902740937224e-05, 'epoch': 7.6}\n", + "{'loss': 0.1574, 'grad_norm': 0.69870924949646, 'learning_rate': 4.4562334217506634e-05, 'epoch': 7.77}\n", + "{'loss': 0.1585, 'grad_norm': 0.7949297428131104, 'learning_rate': 4.1025641025641023e-05, 'epoch': 7.95}\n", + "{'loss': 0.1358, 'grad_norm': 0.47111940383911133, 'learning_rate': 3.7488947833775426e-05, 'epoch': 8.13}\n", + "{'loss': 0.1299, 'grad_norm': 0.6585063934326172, 'learning_rate': 3.3952254641909815e-05, 'epoch': 8.3}\n", + "{'loss': 0.1309, 'grad_norm': 0.4326067566871643, 'learning_rate': 3.041556145004421e-05, 'epoch': 8.48}\n", + "{'loss': 0.1325, 'grad_norm': 0.3893156349658966, 'learning_rate': 2.6878868258178604e-05, 'epoch': 8.66}\n", + "{'loss': 0.1334, 'grad_norm': 0.968989908695221, 'learning_rate': 2.3342175066313e-05, 'epoch': 8.83}\n", + "{'loss': 0.1335, 'grad_norm': 0.48122939467430115, 'learning_rate': 1.9805481874447392e-05, 'epoch': 9.01}\n", + "{'loss': 0.1172, 'grad_norm': 0.4522119462490082, 'learning_rate': 1.6268788682581788e-05, 'epoch': 9.19}\n", + "{'loss': 0.1181, 'grad_norm': 0.5501106977462769, 'learning_rate': 1.273209549071618e-05, 'epoch': 9.36}\n", + "{'loss': 0.1194, 'grad_norm': 0.46891143918037415, 'learning_rate': 9.195402298850575e-06, 'epoch': 9.54}\n", + "{'loss': 0.12, 'grad_norm': 0.5252432823181152, 'learning_rate': 5.658709106984969e-06, 'epoch': 9.72}\n", + "{'loss': 0.1228, 'grad_norm': 0.4517185688018799, 'learning_rate': 2.1220159151193635e-06, 'epoch': 9.89}\n", + "{'train_runtime': 8395.4379, 'train_samples_per_second': 5.393, 'train_steps_per_second': 0.674, 'train_loss': 0.5991904156789342, 'epoch': 10.0}\n", + "100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 5660/5660 [2:19:55<00:00, 1.48s/it]\n", + "(5) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "8395.4379 seconds used for training.\n", + "139.92 minutes used for training.\n", + "Peak reserved memory = 3.945 GB.\n", + "Peak reserved memory for training = 0.0 GB.\n", + "Peak reserved memory % of max memory = 32.891 %.\n", + "Peak reserved memory for training % of max memory = 0.0 %.\n", + "Evaluating fine-tuned model: unsloth/Qwen2-1.5B-Instruct-bnb-4bit\n", + "100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 1133/1133 [50:44<00:00, 2.69s/it]\n", + " chinese ... unsloth/Qwen2-1.5B-Instruct-bnb-4bit(finetuned)\n", + "0 老耿端衷ζžͺοΌŒηœ―ηΌθ΅·δΈ€εͺδΈ‰θ§’ηœΌοΌŒδΈ€ζ‚ζ‰³ζœΊε“δΊ†ζžͺοΌŒε†°ι›Ήθˆ¬ηš„ι‡‘ιΊ»ι›€εŠˆε“©ε•ͺε•¦εΎ€δΈ‹θ½οΌŒι“η ‚ε­εœ¨ζŸ³ζžι—΄ι£ž... ... Old Geng raised his pistol, squinted, and fire...\n", + "\n", + "[1 rows x 6 columns]\n", + "(6) GPU = NVIDIA GeForce RTX 4080 Laptop GPU. Max memory = 11.994 GB.\n", + "3.945 GB of memory reserved.\n", + "Unsloth: Merging 4bit and LoRA weights to 4bit...\n", + "This might take 5 minutes...\n", + "Done.\n", + "Unsloth: Saving tokenizer... Done.\n", + "Unsloth: Saving model... This might take 10 minutes for Llama-7b... Done.\n", + "Unsloth: Merging 4bit and LoRA weights to 16bit...\n", + "Unsloth: Will use up to 29.87 out of 47.05 RAM for saving.\n", + "100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 28/28 [00:00<00:00, 42.85it/s]\n", + "Unsloth: Saving tokenizer... Done.\n", + "Unsloth: Saving model... This might take 5 minutes for Llama-7b...\n", + "Done.\n", + "Unsloth: Converting qwen2 model. Can use fast conversion = False.\n", + "==((====))== Unsloth: Conversion from QLoRA to GGUF information\n", + " \\\\ /| [0] Installing llama.cpp will take 3 minutes.\n", + "O^O/ \\_/ \\ [1] Converting HF to GUUF 16bits will take 3 minutes.\n", + "\\ / [2] Converting GGUF 16bits to ['q5_k_m'] will take 10 minutes each.\n", + " \"-____-\" In total, you will have to wait at least 16 minutes.\n", + "\n", + "Unsloth: [0] Installing llama.cpp. This will take 3 minutes...\n", + "Unsloth: [1] Converting model at models/Qwen2-1.5B-Instruct-bnb-4bit-MAC-q5_k_m into bf16 GGUF format.\n", + "The output location will be ./models/Qwen2-1.5B-Instruct-bnb-4bit-MAC-q5_k_m/unsloth.BF16.gguf\n", + "This will take 3 minutes...\n", + "INFO:hf-to-gguf:Loading model: Qwen2-1.5B-Instruct-bnb-4bit-MAC-q5_k_m\n", + "INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only\n", + "INFO:hf-to-gguf:Set model parameters\n", + "INFO:hf-to-gguf:gguf: context length = 32768\n", + "INFO:hf-to-gguf:gguf: embedding length = 1536\n", + "INFO:hf-to-gguf:gguf: feed forward length = 8960\n", + "INFO:hf-to-gguf:gguf: head count = 12\n", + "INFO:hf-to-gguf:gguf: key-value head count = 2\n", + "INFO:hf-to-gguf:gguf: rope theta = 1000000.0\n", + "INFO:hf-to-gguf:gguf: rms norm epsilon = 1e-06\n", + "INFO:hf-to-gguf:gguf: file type = 32\n", + "INFO:hf-to-gguf:Set model tokenizer\n", + "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n", + "INFO:gguf.vocab:Adding 151387 merge(s).\n", + "INFO:gguf.vocab:Setting special token type eos to 151645\n", + "INFO:gguf.vocab:Setting special token type pad to 151643\n", + "INFO:gguf.vocab:Setting special token type bos to 151643\n", + "INFO:gguf.vocab:Setting chat_template to {% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\n", + "You are a helpful assistant.<|im_end|>\n", + "' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n", + "' + message['content'] + '<|im_end|>' + '\n", + "'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n", + "' }}{% endif %}\n", + "INFO:hf-to-gguf:Exporting model to 'models/Qwen2-1.5B-Instruct-bnb-4bit-MAC-q5_k_m/unsloth.BF16.gguf'\n", + "INFO:hf-to-gguf:gguf: loading model part 'model.safetensors'\n", + "INFO:hf-to-gguf:token_embd.weight, torch.bfloat16 --> BF16, shape = {1536, 151936}\n", + "INFO:hf-to-gguf:blk.0.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.0.ffn_down.weight, torch.bfloat16 --> BF16, shape = {8960, 1536}\n", + "INFO:hf-to-gguf:blk.0.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.0.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.0.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.0.attn_k.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.0.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.0.attn_output.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.0.attn_q.bias, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.0.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.0.attn_v.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.0.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.1.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.1.ffn_down.weight, torch.bfloat16 --> BF16, shape = {8960, 1536}\n", + "INFO:hf-to-gguf:blk.1.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.1.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.1.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.1.attn_k.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.1.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.1.attn_output.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.1.attn_q.bias, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.1.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.1.attn_v.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.1.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.10.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.10.ffn_down.weight, torch.bfloat16 --> BF16, shape = {8960, 1536}\n", + "INFO:hf-to-gguf:blk.10.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.10.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.10.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.10.attn_k.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.10.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.10.attn_output.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.10.attn_q.bias, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.10.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.10.attn_v.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.10.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.11.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.11.ffn_down.weight, torch.bfloat16 --> BF16, shape = {8960, 1536}\n", + "INFO:hf-to-gguf:blk.11.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.11.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.11.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.11.attn_k.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.11.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.11.attn_output.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.11.attn_q.bias, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.11.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.11.attn_v.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.11.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.12.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.12.ffn_down.weight, torch.bfloat16 --> BF16, shape = {8960, 1536}\n", + "INFO:hf-to-gguf:blk.12.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.12.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.12.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.12.attn_k.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.12.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.12.attn_output.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.12.attn_q.bias, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.12.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.12.attn_v.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.12.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.13.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.13.ffn_down.weight, torch.bfloat16 --> BF16, shape = {8960, 1536}\n", + "INFO:hf-to-gguf:blk.13.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.13.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.13.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.13.attn_k.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.13.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.13.attn_output.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.13.attn_q.bias, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.13.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.13.attn_v.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.13.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.14.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.14.ffn_down.weight, torch.bfloat16 --> BF16, shape = {8960, 1536}\n", + "INFO:hf-to-gguf:blk.14.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.14.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.14.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.14.attn_k.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.14.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.14.attn_output.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.14.attn_q.bias, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.14.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.14.attn_v.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.14.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.15.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.15.ffn_down.weight, torch.bfloat16 --> BF16, shape = {8960, 1536}\n", + "INFO:hf-to-gguf:blk.15.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.15.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.15.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.15.attn_k.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.15.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.15.attn_output.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.15.attn_q.bias, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.15.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.15.attn_v.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.15.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.16.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.16.ffn_down.weight, torch.bfloat16 --> BF16, shape = {8960, 1536}\n", + "INFO:hf-to-gguf:blk.16.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.16.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.16.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.16.attn_k.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.16.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.16.attn_output.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.16.attn_q.bias, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.16.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.16.attn_v.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.16.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.17.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.17.ffn_down.weight, torch.bfloat16 --> BF16, shape = {8960, 1536}\n", + "INFO:hf-to-gguf:blk.17.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.17.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.17.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.17.attn_k.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.17.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.17.attn_output.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.17.attn_q.bias, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.17.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.17.attn_v.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.17.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.18.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.18.ffn_down.weight, torch.bfloat16 --> BF16, shape = {8960, 1536}\n", + "INFO:hf-to-gguf:blk.18.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.18.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.18.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.18.attn_k.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.18.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.18.attn_output.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.18.attn_q.bias, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.18.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.18.attn_v.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.18.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.19.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.19.ffn_down.weight, torch.bfloat16 --> BF16, shape = {8960, 1536}\n", + "INFO:hf-to-gguf:blk.19.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.19.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.19.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.19.attn_k.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.19.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.19.attn_output.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.19.attn_q.bias, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.19.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.19.attn_v.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.19.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.2.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.2.ffn_down.weight, torch.bfloat16 --> BF16, shape = {8960, 1536}\n", + "INFO:hf-to-gguf:blk.2.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.2.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.2.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.2.attn_k.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.2.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.2.attn_output.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.2.attn_q.bias, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.2.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.2.attn_v.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.2.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.20.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.20.ffn_down.weight, torch.bfloat16 --> BF16, shape = {8960, 1536}\n", + "INFO:hf-to-gguf:blk.20.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.20.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.20.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.20.attn_k.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.20.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.20.attn_output.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.20.attn_q.bias, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.20.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.20.attn_v.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.20.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.21.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.21.ffn_down.weight, torch.bfloat16 --> BF16, shape = {8960, 1536}\n", + "INFO:hf-to-gguf:blk.21.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.21.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.21.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.21.attn_k.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.21.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.21.attn_output.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.21.attn_q.bias, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.21.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.21.attn_v.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.21.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.22.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.22.ffn_down.weight, torch.bfloat16 --> BF16, shape = {8960, 1536}\n", + "INFO:hf-to-gguf:blk.22.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.22.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.22.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.22.attn_k.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.22.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.22.attn_output.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.22.attn_q.bias, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.22.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.22.attn_v.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.22.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.23.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.23.ffn_down.weight, torch.bfloat16 --> BF16, shape = {8960, 1536}\n", + "INFO:hf-to-gguf:blk.23.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.23.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.23.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.23.attn_k.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.23.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.23.attn_output.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.23.attn_q.bias, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.23.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.23.attn_v.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.23.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.24.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.24.ffn_down.weight, torch.bfloat16 --> BF16, shape = {8960, 1536}\n", + "INFO:hf-to-gguf:blk.24.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.24.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.24.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.24.attn_k.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.24.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.24.attn_output.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.24.attn_q.bias, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.24.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.24.attn_v.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.24.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.25.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.25.ffn_down.weight, torch.bfloat16 --> BF16, shape = {8960, 1536}\n", + "INFO:hf-to-gguf:blk.25.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.25.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.25.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.25.attn_k.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.25.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.25.attn_output.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.25.attn_q.bias, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.25.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.25.attn_v.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.25.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.26.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.26.ffn_down.weight, torch.bfloat16 --> BF16, shape = {8960, 1536}\n", + "INFO:hf-to-gguf:blk.26.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.26.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.26.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.26.attn_k.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.26.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.26.attn_output.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.26.attn_q.bias, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.26.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.26.attn_v.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.26.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.27.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.27.ffn_down.weight, torch.bfloat16 --> BF16, shape = {8960, 1536}\n", + "INFO:hf-to-gguf:blk.27.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.27.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.27.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.27.attn_k.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.27.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.27.attn_output.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.27.attn_q.bias, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.27.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.27.attn_v.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.27.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.3.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.3.ffn_down.weight, torch.bfloat16 --> BF16, shape = {8960, 1536}\n", + "INFO:hf-to-gguf:blk.3.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.3.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.3.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.3.attn_k.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.3.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.3.attn_output.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.3.attn_q.bias, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.3.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.3.attn_v.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.3.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.4.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.4.ffn_down.weight, torch.bfloat16 --> BF16, shape = {8960, 1536}\n", + "INFO:hf-to-gguf:blk.4.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.4.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.4.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.4.attn_k.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.4.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.4.attn_output.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.4.attn_q.bias, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.4.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.4.attn_v.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.4.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.5.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.5.ffn_down.weight, torch.bfloat16 --> BF16, shape = {8960, 1536}\n", + "INFO:hf-to-gguf:blk.5.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.5.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.5.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.5.attn_k.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.5.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.5.attn_output.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.5.attn_q.bias, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.5.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.5.attn_v.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.5.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.6.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.6.ffn_down.weight, torch.bfloat16 --> BF16, shape = {8960, 1536}\n", + "INFO:hf-to-gguf:blk.6.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.6.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.6.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.6.attn_k.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.6.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.6.attn_output.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.6.attn_q.bias, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.6.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.6.attn_v.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.6.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.7.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.7.ffn_down.weight, torch.bfloat16 --> BF16, shape = {8960, 1536}\n", + "INFO:hf-to-gguf:blk.7.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.7.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.7.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.7.attn_k.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.7.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.7.attn_output.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.7.attn_q.bias, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.7.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.7.attn_v.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.7.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.8.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.8.ffn_down.weight, torch.bfloat16 --> BF16, shape = {8960, 1536}\n", + "INFO:hf-to-gguf:blk.8.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.8.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.8.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.8.attn_k.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.8.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.8.attn_output.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.8.attn_q.bias, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.8.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.8.attn_v.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.8.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.9.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.9.ffn_down.weight, torch.bfloat16 --> BF16, shape = {8960, 1536}\n", + "INFO:hf-to-gguf:blk.9.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.9.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1536, 8960}\n", + "INFO:hf-to-gguf:blk.9.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.9.attn_k.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.9.attn_k.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:blk.9.attn_output.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.9.attn_q.bias, torch.bfloat16 --> F32, shape = {1536}\n", + "INFO:hf-to-gguf:blk.9.attn_q.weight, torch.bfloat16 --> BF16, shape = {1536, 1536}\n", + "INFO:hf-to-gguf:blk.9.attn_v.bias, torch.bfloat16 --> F32, shape = {256}\n", + "INFO:hf-to-gguf:blk.9.attn_v.weight, torch.bfloat16 --> BF16, shape = {1536, 256}\n", + "INFO:hf-to-gguf:output_norm.weight, torch.bfloat16 --> F32, shape = {1536}\n", + "Writing: 0%| | 0.00/3.09G [00:00\n", + " main()\n", + " File \"/home/inflaton/code/projects/courses/novel-translation/llama.cpp/convert-hf-to-gguf.py\", line 2881, in main\n", + " model_instance.write()\n", + " File \"/home/inflaton/code/projects/courses/novel-translation/llama.cpp/convert-hf-to-gguf.py\", line 331, in write\n", + " self.gguf_writer.write_tensors_to_file(progress=True)\n", + " File \"/home/inflaton/code/projects/courses/novel-translation/llama.cpp/gguf-py/gguf/gguf_writer.py\", line 312, in write_tensors_to_file\n", + " ti.tensor.tofile(self.fout)\n", + " File \"/home/inflaton/code/projects/courses/novel-translation/llama.cpp/gguf-py/gguf/lazy.py\", line 233, in tofile\n", + " eager = LazyNumpyTensor.to_eager(self)\n", + " File \"/home/inflaton/code/projects/courses/novel-translation/llama.cpp/gguf-py/gguf/lazy.py\", line 193, in to_eager\n", + " return cls._recurse_apply(t, simple_to_eager)\n", + " File \"/home/inflaton/code/projects/courses/novel-translation/llama.cpp/gguf-py/gguf/lazy.py\", line 109, in _recurse_apply\n", + " return fn(o)\n", + " File \"/home/inflaton/code/projects/courses/novel-translation/llama.cpp/gguf-py/gguf/lazy.py\", line 185, in simple_to_eager\n", + " lt._data = lt._func(lt._args)\n", + " File \"/home/inflaton/code/projects/courses/novel-translation/llama.cpp/gguf-py/gguf/lazy.py\", line 158, in \n", + " return cls(meta=cls.eager_to_meta(res), lazy=shared_lazy, args=args, func=lambda a: fn(*a, **kwargs))\n", + " File \"/home/inflaton/code/projects/courses/novel-translation/llama.cpp/gguf-py/gguf/quants.py\", line 52, in __quantize_bf16_array\n", + " return __apply_over_grouped_rows(__compute_fp32_to_bf16, arr=n, otype=np.int16, oshape=n.shape)\n", + " File \"/home/inflaton/code/projects/courses/novel-translation/llama.cpp/gguf-py/gguf/quants.py\", line 47, in __apply_over_grouped_rows\n", + " np.concatenate([func(group).ravel() for group in np.array_split(rows, n_groups)], axis=0, out=out)\n", + " File \"/home/inflaton/code/projects/courses/novel-translation/llama.cpp/gguf-py/gguf/quants.py\", line 47, in \n", + " np.concatenate([func(group).ravel() for group in np.array_split(rows, n_groups)], axis=0, out=out)\n", + " File \"/home/inflaton/code/projects/courses/novel-translation/llama.cpp/gguf-py/gguf/quants.py\", line 30, in __compute_fp32_to_bf16\n", + " n = np.where((n & 0x7fffffff) > 0x7f800000, (n & 0xffff0000) | (64 << 16), n)\n", + "OverflowError: Python integer 4294901760 out of bounds for int32\n", + "Writing: 0%| | 0.00/3.09G [00:00\n", + " save_model(model, tokenizer)\n", + " File \"/home/inflaton/code/projects/courses/novel-translation/translation_engine.py\", line 219, in save_model\n", + " File \"/home/inflaton/miniconda3/envs/unsloth_env/lib/python3.10/site-packages/unsloth/save.py\", line 1527, in unsloth_save_pretrained_gguf\n", + " all_file_locations = save_to_gguf(model_type, model_dtype, is_sentencepiece_model,\n", + " File \"/home/inflaton/miniconda3/envs/unsloth_env/lib/python3.10/site-packages/unsloth/save.py\", line 1113, in save_to_gguf\n", + " raise RuntimeError(\n", + "RuntimeError: Unsloth: Quantization failed! You might have to compile llama.cpp yourself, then run this again.\n", + "You do not need to close this Python program. Run the following commands in a new terminal:\n", + "You must run this in the same folder as you're saving your model.\n", + "git clone --recursive https://github.com/ggerganov/llama.cpp\n", + "cd llama.cpp && make clean && make all -j\n", + "Once that's done, redo the quantization.\n" + ] + } + ], + "source": [ + "!./tune-small.sh" + ] + } + ], + "metadata": { + "accelerator": "GPU", + "application/vnd.databricks.v1+notebook": { + "dashboards": [], + "environmentMetadata": null, + "language": "python", + "notebookMetadata": { + "pythonIndentUnit": 4 + }, + "notebookName": "07_MAC_+_Qwen2-7B-Instructi_Unsloth_train", + "widgets": {} + }, + "colab": { + "gpuType": "T4", + "provenance": [] + }, + "kernelspec": { + "display_name": "Python 3", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.10.14" + }, + "widgets": { + "application/vnd.jupyter.widget-state+json": { + "036fc5746f43416db18c19ad8fd36677": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "06e806c82c7b4cbea31c5358dd9c3434": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "087b76a8b7514269b1f0ab29b062e444": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_a069d2ab23824f29aa320ac256e2cfe9", + "placeholder": "​", + "style": "IPY_MODEL_06e806c82c7b4cbea31c5358dd9c3434", + "value": "Map (num_proc=2): 100%" + } + }, + "09b76013aa9e45efb6deb23a7a0d0925": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_dea41c5260884aa6879b5e1d1697b14f", + "placeholder": "​", + "style": "IPY_MODEL_89965917796a4f81b899fdc7685f33df", + "value": "config.json: 100%" + } + }, + "0a92c56bfa134ef583220d7ef0b13e17": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "0c34be936c8145d3ab41282f30a70713": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "0f8b6bfe16894500838793f2491d403f": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "177c78fce95d4b4ab33057c5a048d693": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "1f44c9ce1adf470cbb19784493ed209f": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_0c34be936c8145d3ab41282f30a70713", + "placeholder": "​", + "style": "IPY_MODEL_0a92c56bfa134ef583220d7ef0b13e17", + "value": "model.safetensors: 100%" + } + }, + "201b59ccd9f845e197029b57e424aefc": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "2157f01726d748f8a9ae4a00664430da": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "21db8a77b00d4a4e82fdfa608657531f": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "26e4202cca81496a90d15a0dd4ca9cf1": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_ba90fdb8822d47dab7ba203bee297f37", + "IPY_MODEL_61560ff6a36b44f4a9dfdae5c52791d4", + "IPY_MODEL_95fbe66647904c06a20f640630d6dc0e" + ], + "layout": "IPY_MODEL_57182a263d324a3dbf1471c74290a0d5" + } + }, + "27155728b6b84cb199c91c940095d0a8": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_6b91feeed5464877991ac2c207aebe7c", + "IPY_MODEL_cca8113c54c0495daedce1327bf9c68b", + "IPY_MODEL_2e63a29e2f7247bba5beede9a568c99f" + ], + "layout": "IPY_MODEL_5c9d781c28944f3eb86e2a6d44efdf18" + } + }, + "271ddaa553a042d09b6db7b450643d8f": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "2a58d04b428c46f4b3dbadd3bc6cd529": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "2d18ddf6482c4d97829ac0e5a7b9868f": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_9f679ad3ec7f4fe8ad0510ffb57bc2ab", + "IPY_MODEL_f2df530d22c74977b249dd9fb5f4829b", + "IPY_MODEL_89b2ef0dbfea47ab8e6f8d659e3351d1" + ], + "layout": "IPY_MODEL_3056b148aa9f4e6e8aa3b61d26886255" + } + }, + "2e5087c76f98437cb5dc729230358cba": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "2e63a29e2f7247bba5beede9a568c99f": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_b993eaec6b224440bf80c0958c6fb536", + "placeholder": "​", + "style": "IPY_MODEL_de868e26e7154f62aa86223a539ad421", + "value": " 464/464 [00:00<00:00, 27.1kB/s]" + } + }, + "2f6c70dd266c4816bfad3fd3d192929a": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "30307300bc4e4baf96560e30969a82b6": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_e36a3f9eff0e4cf68834d66b0213ae96", + "placeholder": "​", + "style": "IPY_MODEL_a0037bdccf254159becde630bee3d1db", + "value": "generation_config.json: 100%" + } + }, + "3056b148aa9f4e6e8aa3b61d26886255": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "30cdc32298134cb0be4d41615b9e5774": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "3572201bd4d74a58b7a665f9bdfdcdba": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "35b0e8c26d6640e9bd0ed7b242a423d8": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_2e5087c76f98437cb5dc729230358cba", + "max": 51760, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_036fc5746f43416db18c19ad8fd36677", + "value": 51760 + } + }, + "36166c7bcb854b34aca1f41a5d6ea50b": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "370692d819df41828b48c4ad446f977b": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "39b29a75374b45c0a22506010be2b84e": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_30cdc32298134cb0be4d41615b9e5774", + "max": 1179, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_47928317548c454bba6358ab132e8dee", + "value": 1179 + } + }, + "3cf2dd993b5e4d3daecf61e4bab5a404": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_087b76a8b7514269b1f0ab29b062e444", + "IPY_MODEL_35b0e8c26d6640e9bd0ed7b242a423d8", + "IPY_MODEL_54ad89e05fd74576b9b8b5b5a10eaf8d" + ], + "layout": "IPY_MODEL_a41dc44766444a998bec2d777f249d23" + } + }, + "43dec2ede91341f5af60eb522e18e984": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "4463edd481c1467f914c7dcd6c6e6ffc": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "47928317548c454bba6358ab132e8dee": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "49277aeeac16434a865a4d12308b1abc": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "4ae7e449e4ea4c729b5f34607c18ebae": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "4b2061b8a73c43ffb0c2f83daf0d0183": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "4c4c88d4c701450692fa0f6b0c5764b0": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "4c666f4ace3943f8b80ecd20e7503236": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "4ccedf0d93094e63b57a0f8a434fba06": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_4463edd481c1467f914c7dcd6c6e6ffc", + "max": 44307561, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_6d3b9a05db0b4dadb638c686faa0c40a", + "value": 44307561 + } + }, + "4dcf6ff672d24983a1877a8431709aa9": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_5807d5fb827d490fb3bc698f801ffff5", + "placeholder": "​", + "style": "IPY_MODEL_c4f2b06a82fd4987b8b659524a7b503b", + "value": "Generating train split: 100%" + } + }, + "4ea63adfce694725bdba878aef709dd3": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "5234566b1bfc4655b8d582ea5b46ed9f": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "54ad89e05fd74576b9b8b5b5a10eaf8d": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_fdb1941405ed4e4aa06019933892deb3", + "placeholder": "​", + "style": "IPY_MODEL_668d5377ca56426a99753867e6e24862", + "value": " 51760/51760 [01:02<00:00, 1131.51 examples/s]" + } + }, + "56aee4853b7740e6a977254f5d1fa66d": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "57182a263d324a3dbf1471c74290a0d5": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "5807d5fb827d490fb3bc698f801ffff5": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "5c9d781c28944f3eb86e2a6d44efdf18": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "5f40db8173dd4d76b6ef5ed6d9ec8b6e": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "61560ff6a36b44f4a9dfdae5c52791d4": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_db19fc8d37db4e45a5790a876836d8c4", + "max": 11610, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_36166c7bcb854b34aca1f41a5d6ea50b", + "value": 11610 + } + }, + "6578fd7acdb54c4c93528ea431fd0144": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_370692d819df41828b48c4ad446f977b", + "placeholder": "​", + "style": "IPY_MODEL_a0bf9160eb2647409b3200270914b90f", + "value": " 50.6k/50.6k [00:00<00:00, 2.71MB/s]" + } + }, + "668d5377ca56426a99753867e6e24862": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "697f027529b54ee9956bae78a11e0611": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "69ac12aec0714318bf2c83d4f4e745f5": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "6b2012c3f88547af8884a9ea90e3164b": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_938f45f1b3e24118b815d96ae34ba86a", + "placeholder": "​", + "style": "IPY_MODEL_9367047a800747f79c6b225d92397846", + "value": " 44.3M/44.3M [00:01<00:00, 31.0MB/s]" + } + }, + "6b91feeed5464877991ac2c207aebe7c": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_4b2061b8a73c43ffb0c2f83daf0d0183", + "placeholder": "​", + "style": "IPY_MODEL_69ac12aec0714318bf2c83d4f4e745f5", + "value": "special_tokens_map.json: 100%" + } + }, + "6d3b9a05db0b4dadb638c686faa0c40a": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "6dbbedeca9314e66ae50e44ffa31a414": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "6e34619b45934040b6092e6fb01ea7fe": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "71ce208e20d6483abb9ed923510c86d7": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_d69dc491b3ab44d7852b21873ed7bb7f", + "placeholder": "​", + "style": "IPY_MODEL_f401d53bf28e44eb906bce6c05412662", + "value": " 51760/51760 [00:01<00:00, 45512.81 examples/s]" + } + }, + "7358cdad832342c983e31efb8754ab78": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "73e352a3404f4c7dad0737f57d29e92f": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_988a0e8c1f89446086858da0a891a79c", + "IPY_MODEL_4ccedf0d93094e63b57a0f8a434fba06", + "IPY_MODEL_6b2012c3f88547af8884a9ea90e3164b" + ], + "layout": "IPY_MODEL_7e29cb8dd4df4d5b94407cd8fd3f2011" + } + }, + "74501720ac7e4dbb911a4a99b3633bc6": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "78e5400bff924a92a4cc61c4ff18b182": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_b9b313fd861948f5aba25b24b1518d30", + "placeholder": "​", + "style": "IPY_MODEL_4c666f4ace3943f8b80ecd20e7503236", + "value": " 1.18k/1.18k [00:00<00:00, 31.3kB/s]" + } + }, + "7975adbc2ec5489ea7fa0167e620d85c": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_6e34619b45934040b6092e6fb01ea7fe", + "max": 51760, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_271ddaa553a042d09b6db7b450643d8f", + "value": 51760 + } + }, + "7e29cb8dd4df4d5b94407cd8fd3f2011": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "810ff6c0e17d4fa09a30fef27eacff90": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "89965917796a4f81b899fdc7685f33df": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "89b2ef0dbfea47ab8e6f8d659e3351d1": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_b8908fa0df3743ecb9d12983a739104f", + "placeholder": "​", + "style": "IPY_MODEL_177c78fce95d4b4ab33057c5a048d693", + "value": " 9.09M/9.09M [00:00<00:00, 32.6MB/s]" + } + }, + "8b3505352a5a42bf910428c40ce40465": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_49277aeeac16434a865a4d12308b1abc", + "placeholder": "​", + "style": "IPY_MODEL_2157f01726d748f8a9ae4a00664430da", + "value": " 5.70G/5.70G [01:02<00:00, 30.1MB/s]" + } + }, + "8fc142b628fb40568730234de1cafde2": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_4ae7e449e4ea4c729b5f34607c18ebae", + "max": 172, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_3572201bd4d74a58b7a665f9bdfdcdba", + "value": 172 + } + }, + "9367047a800747f79c6b225d92397846": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "938f45f1b3e24118b815d96ae34ba86a": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "95fbe66647904c06a20f640630d6dc0e": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_b0a370dc20654b279b9680692e34418e", + "placeholder": "​", + "style": "IPY_MODEL_cfeb365ddf7548d58b2557f22737fcf5", + "value": " 11.6k/11.6k [00:00<00:00, 716kB/s]" + } + }, + "988a0e8c1f89446086858da0a891a79c": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_ad2be500fc164c0f86f33e914ef8e6a0", + "placeholder": "​", + "style": "IPY_MODEL_5234566b1bfc4655b8d582ea5b46ed9f", + "value": "Downloading data: 100%" + } + }, + "98c58f23f4d549518832cb2d18f796e8": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_09b76013aa9e45efb6deb23a7a0d0925", + "IPY_MODEL_39b29a75374b45c0a22506010be2b84e", + "IPY_MODEL_78e5400bff924a92a4cc61c4ff18b182" + ], + "layout": "IPY_MODEL_2a58d04b428c46f4b3dbadd3bc6cd529" + } + }, + "99fdbb0300c14c139d1937c646f0cfe7": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_7358cdad832342c983e31efb8754ab78", + "placeholder": "​", + "style": "IPY_MODEL_e9adf418296e436fb48bb9f78885598b", + "value": " 51760/51760 [00:01<00:00, 38665.95 examples/s]" + } + }, + "9f679ad3ec7f4fe8ad0510ffb57bc2ab": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_4ea63adfce694725bdba878aef709dd3", + "placeholder": "​", + "style": "IPY_MODEL_74501720ac7e4dbb911a4a99b3633bc6", + "value": "tokenizer.json: 100%" + } + }, + "a0037bdccf254159becde630bee3d1db": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "a069d2ab23824f29aa320ac256e2cfe9": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "a0bf9160eb2647409b3200270914b90f": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "a41dc44766444a998bec2d777f249d23": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "a8464a4c711e4e00aafdfc919b60d07e": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_fb995c740590427b882572c81d4e848c", + "placeholder": "​", + "style": "IPY_MODEL_201b59ccd9f845e197029b57e424aefc", + "value": " 172/172 [00:00<00:00, 12.0kB/s]" + } + }, + "a9f0cc51fc3d4d7b874c32dcf1c5bdf2": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "ad2be500fc164c0f86f33e914ef8e6a0": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "b0240cd9a4554b29ae11f8051984a1c6": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_edaf890370314a218f138015faa0b05d", + "placeholder": "​", + "style": "IPY_MODEL_697f027529b54ee9956bae78a11e0611", + "value": "Map: 100%" + } + }, + "b0a370dc20654b279b9680692e34418e": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "b518dcee69074b87be73957cd810e7ed": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_d891f8d0b1fc462f8008d02bb2a15692", + "placeholder": "​", + "style": "IPY_MODEL_cced8fd7e998472794f3f3e3018956a5", + "value": "tokenizer_config.json: 100%" + } + }, + "b8908fa0df3743ecb9d12983a739104f": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "b993eaec6b224440bf80c0958c6fb536": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "b9b313fd861948f5aba25b24b1518d30": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "ba90fdb8822d47dab7ba203bee297f37": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_0f8b6bfe16894500838793f2491d403f", + "placeholder": "​", + "style": "IPY_MODEL_bb19f6c747754682a514373a3a0535ba", + "value": "Downloading readme: 100%" + } + }, + "bb19f6c747754682a514373a3a0535ba": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "bc883d4cf13e4f8b8a4fe5f410cb6efd": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_e9159e03e61f4f56978ece9c3bca49b2", + "max": 51760, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_810ff6c0e17d4fa09a30fef27eacff90", + "value": 51760 + } + }, + "c161d94df0f04feba9542237e0856c22": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "c22f71b1f85843209d7e5321506b9cb9": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_1f44c9ce1adf470cbb19784493ed209f", + "IPY_MODEL_f1addc4479d849879e743cf9089e6540", + "IPY_MODEL_8b3505352a5a42bf910428c40ce40465" + ], + "layout": "IPY_MODEL_4c4c88d4c701450692fa0f6b0c5764b0" + } + }, + "c4f2b06a82fd4987b8b659524a7b503b": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "cca8113c54c0495daedce1327bf9c68b": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_e02f9b7849c64531835eb77b860d1c93", + "max": 464, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_56aee4853b7740e6a977254f5d1fa66d", + "value": 464 + } + }, + "cced8fd7e998472794f3f3e3018956a5": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "cf245afeb1c04f29a24d291608c3d157": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_b518dcee69074b87be73957cd810e7ed", + "IPY_MODEL_e29104486d594b2992d7285e0ef77371", + "IPY_MODEL_6578fd7acdb54c4c93528ea431fd0144" + ], + "layout": "IPY_MODEL_d35db8148a354c56aaac56dbae22536f" + } + }, + "cfe8cae0e22b495bafa221a63d13b283": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "cfeb365ddf7548d58b2557f22737fcf5": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "d1b47d39450d4019ae85c9b2f943eeaf": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_4dcf6ff672d24983a1877a8431709aa9", + "IPY_MODEL_7975adbc2ec5489ea7fa0167e620d85c", + "IPY_MODEL_71ce208e20d6483abb9ed923510c86d7" + ], + "layout": "IPY_MODEL_cfe8cae0e22b495bafa221a63d13b283" + } + }, + "d35db8148a354c56aaac56dbae22536f": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "d69dc491b3ab44d7852b21873ed7bb7f": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "d891f8d0b1fc462f8008d02bb2a15692": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "d8e5318cead340c4adbeaccc05d39225": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" + } + }, + "daf4cd890b35422683d22fd30bc71e83": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_b0240cd9a4554b29ae11f8051984a1c6", + "IPY_MODEL_bc883d4cf13e4f8b8a4fe5f410cb6efd", + "IPY_MODEL_99fdbb0300c14c139d1937c646f0cfe7" + ], + "layout": "IPY_MODEL_c161d94df0f04feba9542237e0856c22" + } + }, + "db19fc8d37db4e45a5790a876836d8c4": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "de868e26e7154f62aa86223a539ad421": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "dea41c5260884aa6879b5e1d1697b14f": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "e02f9b7849c64531835eb77b860d1c93": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "e29104486d594b2992d7285e0ef77371": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_a9f0cc51fc3d4d7b874c32dcf1c5bdf2", + "max": 50641, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_2f6c70dd266c4816bfad3fd3d192929a", + "value": 50641 + } + }, + "e36a3f9eff0e4cf68834d66b0213ae96": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "e9159e03e61f4f56978ece9c3bca49b2": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "e9adf418296e436fb48bb9f78885598b": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "edaf890370314a218f138015faa0b05d": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "f1addc4479d849879e743cf9089e6540": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_43dec2ede91341f5af60eb522e18e984", + "max": 5702746405, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_d8e5318cead340c4adbeaccc05d39225", + "value": 5702746405 + } + }, + "f2df530d22c74977b249dd9fb5f4829b": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_21db8a77b00d4a4e82fdfa608657531f", + "max": 9085698, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_6dbbedeca9314e66ae50e44ffa31a414", + "value": 9085698 + } + }, + "f401d53bf28e44eb906bce6c05412662": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "fb995c740590427b882572c81d4e848c": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + }, + "fce7a61c25ec4390af43d92b7c473a45": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_30307300bc4e4baf96560e30969a82b6", + "IPY_MODEL_8fc142b628fb40568730234de1cafde2", + "IPY_MODEL_a8464a4c711e4e00aafdfc919b60d07e" + ], + "layout": "IPY_MODEL_5f40db8173dd4d76b6ef5ed6d9ec8b6e" + } + }, + "fdb1941405ed4e4aa06019933892deb3": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null + } + } + } + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} \ No newline at end of file