Upload folder using huggingface_hub

README.md

@@ -0,0 +1,136 @@
+---
+language:
+- en
+license: apache-2.0
+base_model: microsoft/WizardLM-2-8x22B
+tags:
+- exl2
+---
+
+# WizardLM-2-8x22B - EXL2 3.75bpw
+
+This is a 3.75bpw EXL2 quant of [microsoft/WizardLM-2-8x22B](https://huggingface.co/microsoft/WizardLM-2-8x22B)
+
+Details about the model can be found at the above model page.
+
+## EXL2 Version
+
+These quants were made with exllamav2 version 0.0.18. Quants made on this version of EXL2 may not work on older versions of the exllamav2 library.
+
+If you have problems loading these models, please update Text Generation WebUI to the latest version.
+
+## Perplexity Scoring
+
+Below are the perplexity scores for the EXL2 models. A lower score is better. 
+
+| Quant Level | Perplexity Score |
+|-------------|------------------|
+| 7.0 | 4.5859 |
+| 6.0 | 4.6252 |
+| 5.5 | 4.6493 |
+| 5.0 | 4.6937 |
+| 4.5 | 4.8029 |
+| 4.0 | 4.9372 |
+| 3.5 | 5.1336 |
+| 3.25 | 5.3636 |
+| 3.0 | 5.5468 |
+| 2.75 | 5.8255 |
+| 2.5 | 6.3362 |
+| 2.25 | 7.7763 |
+
+
+### Perplexity Script
+
+This was the script used for perplexity testing.
+
+```bash
+#!/bin/bash
+
+# Activate the conda environment
+source ~/miniconda3/etc/profile.d/conda.sh
+conda activate exllamav2
+
+DATA_SET=/root/wikitext/wikitext-2-v1.parquet
+
+# Set the model name and bit size
+MODEL_NAME="WizardLM-2-8x22B"
+BIT_PRECISIONS=(6.0 5.5 5.0 4.5 4.0 3.5 3.25 3.0 2.75 2.5 2.25)
+
+# Print the markdown table header
+echo "| Quant Level | Perplexity Score |"
+echo "|-------------|------------------|"
+
+for BIT_PRECISION in "${BIT_PRECISIONS[@]}"
+do
+  LOCAL_FOLDER="/root/models/${MODEL_NAME}_exl2_${BIT_PRECISION}bpw"
+  REMOTE_FOLDER="Dracones/${MODEL_NAME}_exl2_${BIT_PRECISION}bpw"
+
+  if [ ! -d "$LOCAL_FOLDER" ]; then
+    huggingface-cli download --local-dir-use-symlinks=False --local-dir "${LOCAL_FOLDER}" "${REMOTE_FOLDER}" >> /root/download.log 2>&1
+  fi
+
+  output=$(python test_inference.py -m "$LOCAL_FOLDER" -gs 40,40,40,40 -ed "$DATA_SET")
+  score=$(echo "$output" | grep -oP 'Evaluation perplexity: \K[\d.]+')
+  echo "| $BIT_PRECISION | $score |"
+  # rm -rf "${LOCAL_FOLDER}"
+done
+```
+
+
+## Quant Details
+
+This is the script used for quantization.
+
+```bash
+#!/bin/bash
+
+# Activate the conda environment
+source ~/miniconda3/etc/profile.d/conda.sh
+conda activate exllamav2
+
+# Set the model name and bit size
+MODEL_NAME="WizardLM-2-8x22B"
+
+# Define variables
+MODEL_DIR="/mnt/storage/models/$MODEL_NAME"
+OUTPUT_DIR="exl2_$MODEL_NAME"
+MEASUREMENT_FILE="measurements/$MODEL_NAME.json"
+
+# Create the measurement file if needed
+if [ ! -f "$MEASUREMENT_FILE" ]; then
+    echo "Creating $MEASUREMENT_FILE"
+    # Create directories
+    if [ -d "$OUTPUT_DIR" ]; then
+        rm -r "$OUTPUT_DIR"
+    fi
+    mkdir "$OUTPUT_DIR"
+
+    python convert.py -i $MODEL_DIR -o $OUTPUT_DIR -nr -om $MEASUREMENT_FILE
+fi
+
+# Choose one of the below. Either create a single quant for testing or a batch of them.
+# BIT_PRECISIONS=(2.25)
+BIT_PRECISIONS=(5.0 4.5 4.0 3.5 3.0 2.75 2.5 2.25)
+
+for BIT_PRECISION in "${BIT_PRECISIONS[@]}"
+do
+    CONVERTED_FOLDER="models/${MODEL_NAME}_exl2_${BIT_PRECISION}bpw"
+
+    # If it doesn't already exist, make the quant
+    if [ ! -d "$CONVERTED_FOLDER" ]; then
+
+        echo "Creating $CONVERTED_FOLDER"
+
+        # Create directories
+        if [ -d "$OUTPUT_DIR" ]; then
+            rm -r "$OUTPUT_DIR"
+        fi
+        mkdir "$OUTPUT_DIR"
+        mkdir "$CONVERTED_FOLDER"
+        
+        # Run conversion commands  
+        python convert.py -i $MODEL_DIR -o $OUTPUT_DIR -nr -m $MEASUREMENT_FILE -b $BIT_PRECISION -cf $CONVERTED_FOLDER
+
+    fi
+done
+```

config.json

@@ -0,0 +1,42 @@
+{
+    "_name_or_path": "",
+    "architectures": [
+        "MixtralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 6144,
+    "initializer_range": 0.02,
+    "intermediate_size": 16384,
+    "max_position_embeddings": 65536,
+    "model_type": "mixtral",
+    "num_attention_heads": 48,
+    "num_experts_per_tok": 2,
+    "num_hidden_layers": 56,
+    "num_key_value_heads": 8,
+    "num_local_experts": 8,
+    "output_router_logits": false,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000,
+    "router_aux_loss_coef": 0.001,
+    "router_jitter_noise": 0.0,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.36.2",
+    "use_cache": false,
+    "vocab_size": 32000,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.0.18",
+        "bits": 3.75,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 100,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.36.2"
+}

output-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe437c9a17226122285cf7d9c88f6d6502d2c2e19ccf5babf595deaf13e1efc2
+size 8576875672

output-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50cd2e1c818ac8538e98ae3f2c6891982bbff023edd376b7aa59fcc7cb71e0b7
+size 8556181288

output-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25be19428f051798afabf6a1afd2ee57764cacc807e89d4bbff93746dd3adf58
+size 8542081272

output-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e66e18c2dfc3cecda1bf21f9b9d6abe306eae775b1e5fd88c3b407f23e025343
+size 8561197984

output-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0511ad5eae0f8cf2bd4bffc8012d64505ce56baa581462126f1849035fff48da
+size 8587221576

output-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d5fe20e14d62fcfe28fed84488beab0c50a921e2972ac7bb70bf7950bf25120
+size 8580773160

output-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dda609eaac0d8120ef4fcfe04cf65cfff88b627f69b5fdb4b71894aca0ec2681
+size 8580060880

output-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2da89a9f06272fdfa37e712326645f4d89d4c8a89be7db29e079ee8f672477f9
+size 6302303448

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}