{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/kyrylo/Sem-7/Anlp/Grokking/Minimal/lib/python3.8/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n"
     ]
    }
   ],
   "source": [
    "import torch\n",
    "from transformers import AutoModelForCausalLM, AutoTokenizer\n",
    "from huggingface_hub import hf_hub_download, upload_folder\n",
    "from pathlib import Path"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'tokenizer.json'"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "\n",
    "model_name = \"gpt2\"  # Replace with the Hugging Face model name you want to convert\n",
    "local_dir = \"./\"  #  to store the GGML model\n",
    "\n",
    "model_path = hf_hub_download(repo_id='openai-community/gpt2', filename=\"pytorch_model.bin\", local_dir=local_dir) \n",
    "model_path = hf_hub_download(repo_id='openai-community/gpt2', filename=\"config.json\", local_dir=local_dir) \n",
    "model_path = hf_hub_download(repo_id='openai-community/gpt2', filename=\"tokenizer.json\", local_dir=local_dir) \n",
    "model_path"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_96016/408161957.py:1: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n",
      "  model =torch.load(f'./pytorch_model.bin')\n"
     ]
    }
   ],
   "source": [
    "model =torch.load(f'./pytorch_model.bin')\n",
    "torch.save(model, './pytorch_model.bin',  _use_new_zipfile_serialization=True)\n",
    "# ! rm pytorch_model.bin"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "INFO:hf-to-gguf:Loading model: \n",
      "INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only\n",
      "INFO:hf-to-gguf:Exporting model...\n",
      "INFO:hf-to-gguf:gguf: loading model part 'pytorch_model.bin'\n",
      "INFO:hf-to-gguf:token_embd.weight,         torch.float32 --> Q8_0, shape = {768, 50257}\n",
      "INFO:hf-to-gguf:output.weight,             torch.float32 --> Q8_0, shape = {768, 50257}\n",
      "INFO:hf-to-gguf:position_embd.weight,      torch.float32 --> F32, shape = {768, 1024}\n",
      "INFO:hf-to-gguf:blk.0.attn_norm.weight,    torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.0.attn_norm.bias,      torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.0.attn_qkv.weight,     torch.float32 --> Q8_0, shape = {768, 2304}\n",
      "INFO:hf-to-gguf:blk.0.attn_qkv.bias,       torch.float32 --> F32, shape = {2304}\n",
      "INFO:hf-to-gguf:blk.0.attn_output.weight,  torch.float32 --> Q8_0, shape = {768, 768}\n",
      "INFO:hf-to-gguf:blk.0.attn_output.bias,    torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.0.ffn_norm.weight,     torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.0.ffn_norm.bias,       torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.0.ffn_up.weight,       torch.float32 --> Q8_0, shape = {768, 3072}\n",
      "INFO:hf-to-gguf:blk.0.ffn_up.bias,         torch.float32 --> F32, shape = {3072}\n",
      "INFO:hf-to-gguf:blk.0.ffn_down.weight,     torch.float32 --> Q8_0, shape = {3072, 768}\n",
      "INFO:hf-to-gguf:blk.0.ffn_down.bias,       torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.1.attn_norm.weight,    torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.1.attn_norm.bias,      torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.1.attn_qkv.weight,     torch.float32 --> Q8_0, shape = {768, 2304}\n",
      "INFO:hf-to-gguf:blk.1.attn_qkv.bias,       torch.float32 --> F32, shape = {2304}\n",
      "INFO:hf-to-gguf:blk.1.attn_output.weight,  torch.float32 --> Q8_0, shape = {768, 768}\n",
      "INFO:hf-to-gguf:blk.1.attn_output.bias,    torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.1.ffn_norm.weight,     torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.1.ffn_norm.bias,       torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.1.ffn_up.weight,       torch.float32 --> Q8_0, shape = {768, 3072}\n",
      "INFO:hf-to-gguf:blk.1.ffn_up.bias,         torch.float32 --> F32, shape = {3072}\n",
      "INFO:hf-to-gguf:blk.1.ffn_down.weight,     torch.float32 --> Q8_0, shape = {3072, 768}\n",
      "INFO:hf-to-gguf:blk.1.ffn_down.bias,       torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.2.attn_norm.weight,    torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.2.attn_norm.bias,      torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.2.attn_qkv.weight,     torch.float32 --> Q8_0, shape = {768, 2304}\n",
      "INFO:hf-to-gguf:blk.2.attn_qkv.bias,       torch.float32 --> F32, shape = {2304}\n",
      "INFO:hf-to-gguf:blk.2.attn_output.weight,  torch.float32 --> Q8_0, shape = {768, 768}\n",
      "INFO:hf-to-gguf:blk.2.attn_output.bias,    torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.2.ffn_norm.weight,     torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.2.ffn_norm.bias,       torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.2.ffn_up.weight,       torch.float32 --> Q8_0, shape = {768, 3072}\n",
      "INFO:hf-to-gguf:blk.2.ffn_up.bias,         torch.float32 --> F32, shape = {3072}\n",
      "INFO:hf-to-gguf:blk.2.ffn_down.weight,     torch.float32 --> Q8_0, shape = {3072, 768}\n",
      "INFO:hf-to-gguf:blk.2.ffn_down.bias,       torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.3.attn_norm.weight,    torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.3.attn_norm.bias,      torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.3.attn_qkv.weight,     torch.float32 --> Q8_0, shape = {768, 2304}\n",
      "INFO:hf-to-gguf:blk.3.attn_qkv.bias,       torch.float32 --> F32, shape = {2304}\n",
      "INFO:hf-to-gguf:blk.3.attn_output.weight,  torch.float32 --> Q8_0, shape = {768, 768}\n",
      "INFO:hf-to-gguf:blk.3.attn_output.bias,    torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.3.ffn_norm.weight,     torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.3.ffn_norm.bias,       torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.3.ffn_up.weight,       torch.float32 --> Q8_0, shape = {768, 3072}\n",
      "INFO:hf-to-gguf:blk.3.ffn_up.bias,         torch.float32 --> F32, shape = {3072}\n",
      "INFO:hf-to-gguf:blk.3.ffn_down.weight,     torch.float32 --> Q8_0, shape = {3072, 768}\n",
      "INFO:hf-to-gguf:blk.3.ffn_down.bias,       torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.4.attn_norm.weight,    torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.4.attn_norm.bias,      torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.4.attn_qkv.weight,     torch.float32 --> Q8_0, shape = {768, 2304}\n",
      "INFO:hf-to-gguf:blk.4.attn_qkv.bias,       torch.float32 --> F32, shape = {2304}\n",
      "INFO:hf-to-gguf:blk.4.attn_output.weight,  torch.float32 --> Q8_0, shape = {768, 768}\n",
      "INFO:hf-to-gguf:blk.4.attn_output.bias,    torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.4.ffn_norm.weight,     torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.4.ffn_norm.bias,       torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.4.ffn_up.weight,       torch.float32 --> Q8_0, shape = {768, 3072}\n",
      "INFO:hf-to-gguf:blk.4.ffn_up.bias,         torch.float32 --> F32, shape = {3072}\n",
      "INFO:hf-to-gguf:blk.4.ffn_down.weight,     torch.float32 --> Q8_0, shape = {3072, 768}\n",
      "INFO:hf-to-gguf:blk.4.ffn_down.bias,       torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.5.attn_norm.weight,    torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.5.attn_norm.bias,      torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.5.attn_qkv.weight,     torch.float32 --> Q8_0, shape = {768, 2304}\n",
      "INFO:hf-to-gguf:blk.5.attn_qkv.bias,       torch.float32 --> F32, shape = {2304}\n",
      "INFO:hf-to-gguf:blk.5.attn_output.weight,  torch.float32 --> Q8_0, shape = {768, 768}\n",
      "INFO:hf-to-gguf:blk.5.attn_output.bias,    torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.5.ffn_norm.weight,     torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.5.ffn_norm.bias,       torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.5.ffn_up.weight,       torch.float32 --> Q8_0, shape = {768, 3072}\n",
      "INFO:hf-to-gguf:blk.5.ffn_up.bias,         torch.float32 --> F32, shape = {3072}\n",
      "INFO:hf-to-gguf:blk.5.ffn_down.weight,     torch.float32 --> Q8_0, shape = {3072, 768}\n",
      "INFO:hf-to-gguf:blk.5.ffn_down.bias,       torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.6.attn_norm.weight,    torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.6.attn_norm.bias,      torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.6.attn_qkv.weight,     torch.float32 --> Q8_0, shape = {768, 2304}\n",
      "INFO:hf-to-gguf:blk.6.attn_qkv.bias,       torch.float32 --> F32, shape = {2304}\n",
      "INFO:hf-to-gguf:blk.6.attn_output.weight,  torch.float32 --> Q8_0, shape = {768, 768}\n",
      "INFO:hf-to-gguf:blk.6.attn_output.bias,    torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.6.ffn_norm.weight,     torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.6.ffn_norm.bias,       torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.6.ffn_up.weight,       torch.float32 --> Q8_0, shape = {768, 3072}\n",
      "INFO:hf-to-gguf:blk.6.ffn_up.bias,         torch.float32 --> F32, shape = {3072}\n",
      "INFO:hf-to-gguf:blk.6.ffn_down.weight,     torch.float32 --> Q8_0, shape = {3072, 768}\n",
      "INFO:hf-to-gguf:blk.6.ffn_down.bias,       torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.7.attn_norm.weight,    torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.7.attn_norm.bias,      torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.7.attn_qkv.weight,     torch.float32 --> Q8_0, shape = {768, 2304}\n",
      "INFO:hf-to-gguf:blk.7.attn_qkv.bias,       torch.float32 --> F32, shape = {2304}\n",
      "INFO:hf-to-gguf:blk.7.attn_output.weight,  torch.float32 --> Q8_0, shape = {768, 768}\n",
      "INFO:hf-to-gguf:blk.7.attn_output.bias,    torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.7.ffn_norm.weight,     torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.7.ffn_norm.bias,       torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.7.ffn_up.weight,       torch.float32 --> Q8_0, shape = {768, 3072}\n",
      "INFO:hf-to-gguf:blk.7.ffn_up.bias,         torch.float32 --> F32, shape = {3072}\n",
      "INFO:hf-to-gguf:blk.7.ffn_down.weight,     torch.float32 --> Q8_0, shape = {3072, 768}\n",
      "INFO:hf-to-gguf:blk.7.ffn_down.bias,       torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.8.attn_norm.weight,    torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.8.attn_norm.bias,      torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.8.attn_qkv.weight,     torch.float32 --> Q8_0, shape = {768, 2304}\n",
      "INFO:hf-to-gguf:blk.8.attn_qkv.bias,       torch.float32 --> F32, shape = {2304}\n",
      "INFO:hf-to-gguf:blk.8.attn_output.weight,  torch.float32 --> Q8_0, shape = {768, 768}\n",
      "INFO:hf-to-gguf:blk.8.attn_output.bias,    torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.8.ffn_norm.weight,     torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.8.ffn_norm.bias,       torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.8.ffn_up.weight,       torch.float32 --> Q8_0, shape = {768, 3072}\n",
      "INFO:hf-to-gguf:blk.8.ffn_up.bias,         torch.float32 --> F32, shape = {3072}\n",
      "INFO:hf-to-gguf:blk.8.ffn_down.weight,     torch.float32 --> Q8_0, shape = {3072, 768}\n",
      "INFO:hf-to-gguf:blk.8.ffn_down.bias,       torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.9.attn_norm.weight,    torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.9.attn_norm.bias,      torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.9.attn_qkv.weight,     torch.float32 --> Q8_0, shape = {768, 2304}\n",
      "INFO:hf-to-gguf:blk.9.attn_qkv.bias,       torch.float32 --> F32, shape = {2304}\n",
      "INFO:hf-to-gguf:blk.9.attn_output.weight,  torch.float32 --> Q8_0, shape = {768, 768}\n",
      "INFO:hf-to-gguf:blk.9.attn_output.bias,    torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.9.ffn_norm.weight,     torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.9.ffn_norm.bias,       torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.9.ffn_up.weight,       torch.float32 --> Q8_0, shape = {768, 3072}\n",
      "INFO:hf-to-gguf:blk.9.ffn_up.bias,         torch.float32 --> F32, shape = {3072}\n",
      "INFO:hf-to-gguf:blk.9.ffn_down.weight,     torch.float32 --> Q8_0, shape = {3072, 768}\n",
      "INFO:hf-to-gguf:blk.9.ffn_down.bias,       torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.10.attn_norm.weight,   torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.10.attn_norm.bias,     torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.10.attn_qkv.weight,    torch.float32 --> Q8_0, shape = {768, 2304}\n",
      "INFO:hf-to-gguf:blk.10.attn_qkv.bias,      torch.float32 --> F32, shape = {2304}\n",
      "INFO:hf-to-gguf:blk.10.attn_output.weight, torch.float32 --> Q8_0, shape = {768, 768}\n",
      "INFO:hf-to-gguf:blk.10.attn_output.bias,   torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.10.ffn_norm.weight,    torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.10.ffn_norm.bias,      torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.10.ffn_up.weight,      torch.float32 --> Q8_0, shape = {768, 3072}\n",
      "INFO:hf-to-gguf:blk.10.ffn_up.bias,        torch.float32 --> F32, shape = {3072}\n",
      "INFO:hf-to-gguf:blk.10.ffn_down.weight,    torch.float32 --> Q8_0, shape = {3072, 768}\n",
      "INFO:hf-to-gguf:blk.10.ffn_down.bias,      torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.11.attn_norm.weight,   torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.11.attn_norm.bias,     torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.11.attn_qkv.weight,    torch.float32 --> Q8_0, shape = {768, 2304}\n",
      "INFO:hf-to-gguf:blk.11.attn_qkv.bias,      torch.float32 --> F32, shape = {2304}\n",
      "INFO:hf-to-gguf:blk.11.attn_output.weight, torch.float32 --> Q8_0, shape = {768, 768}\n",
      "INFO:hf-to-gguf:blk.11.attn_output.bias,   torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.11.ffn_norm.weight,    torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.11.ffn_norm.bias,      torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:blk.11.ffn_up.weight,      torch.float32 --> Q8_0, shape = {768, 3072}\n",
      "INFO:hf-to-gguf:blk.11.ffn_up.bias,        torch.float32 --> F32, shape = {3072}\n",
      "INFO:hf-to-gguf:blk.11.ffn_down.weight,    torch.float32 --> Q8_0, shape = {3072, 768}\n",
      "INFO:hf-to-gguf:blk.11.ffn_down.bias,      torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:output_norm.weight,        torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:output_norm.bias,          torch.float32 --> F32, shape = {768}\n",
      "INFO:hf-to-gguf:Set meta model\n",
      "INFO:hf-to-gguf:Set model parameters\n",
      "INFO:hf-to-gguf:Set model tokenizer\n",
      "DEBUG:hf-to-gguf:chktok: [198, 220, 628, 220, 628, 198, 220, 197, 220, 197, 197, 220, 197, 198, 220, 220, 198, 220, 220, 220, 198, 220, 220, 220, 220, 198, 220, 220, 220, 220, 220, 198, 8582, 248, 222, 357, 11265, 8, 30325, 114, 447, 235, 8582, 234, 104, 37929, 357, 48101, 795, 13210, 271, 1673, 36686, 515, 8, 14519, 227, 12520, 99, 247, 8582, 99, 247, 513, 4747, 23460, 513, 20370, 23460, 2091, 23460, 20370, 23460, 24840, 23460, 2091, 20370, 513, 13, 18, 513, 492, 18, 513, 986, 18, 28053, 252, 222, 157, 252, 114, 157, 252, 241, 157, 253, 233, 157, 252, 237, 157, 253, 224, 157, 252, 244, 157, 252, 115, 157, 252, 253, 157, 253, 223, 157, 252, 253, 157, 252, 95, 157, 252, 114, 157, 252, 227, 47249, 223, 5633, 22755, 239, 46349, 111, 28839, 101, 18040, 32432, 98, 43291, 1485, 1415, 24309, 25465, 171, 121, 252, 40103, 1421, 18604, 12466, 121, 16843, 141, 231, 15166, 12466, 121, 16142, 12466, 239, 141, 232, 30143, 140, 111, 16142, 21169, 21727, 31583, 18849, 705, 39115, 6, 33153, 15506, 63, 15931, 15931, 16317, 13896, 3228, 9805, 3548, 314, 1053, 587, 705, 44040, 339, 338, 612, 11, 705, 2200, 345, 1654, 30, 705, 44, 407, 1654, 314, 1183, 787, 340, 11, 705, 35, 345, 588, 617, 8887, 30, 775, 6, 26979, 257, 6, 75, 43]\n",
      "DEBUG:hf-to-gguf:chkhsh: 3ce83efda5659b07b1ad37ca97ca5797ea4285d9b9ab0dc679e4a720c9da7454\n",
      "DEBUG:hf-to-gguf:tokenizer.ggml.pre: 'gpt-2'\n",
      "DEBUG:hf-to-gguf:chkhsh: 3ce83efda5659b07b1ad37ca97ca5797ea4285d9b9ab0dc679e4a720c9da7454\n",
      "INFO:gguf.vocab:Adding 50000 merge(s).\n",
      "INFO:gguf.vocab:Setting special token type bos to 50256\n",
      "INFO:gguf.vocab:Setting special token type eos to 50256\n",
      "INFO:hf-to-gguf:Set model quantization version\n",
      "INFO:gguf.gguf_writer:Writing the following files:\n",
      "INFO:gguf.gguf_writer:gpt2.ggml: n_tensors = 149, total_size = 175.9M\n",
      "Writing: 100%|█████████████████████████████| 176M/176M [00:01<00:00, 129Mbyte/s]\n",
      "INFO:hf-to-gguf:Model successfully exported to gpt2.ggml\n"
     ]
    }
   ],
   "source": [
    "!../llama.cpp/convert_hf_to_gguf.py --outfile {local_dir}/{model_name}.ggml --outtype q8_0 --verbose ./"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from huggingface_hub import create_repo, upload_folder\n",
    "\n",
    "\n",
    "repo_id = \"kyrylokumar/gpt2-quantzed-gguf\" \n",
    "create_repo(repo_id=repo_id, exist_ok=True) # exist_ok=True avoids errors if the repo already exists\n",
    "\n",
    "# Upload the folder\n",
    "local_dir = \"./\" # Path to the directory you want to upload\n",
    "upload_folder(\n",
    "    repo_id=repo_id,\n",
    "    folder_path=local_dir,\n",
    "    commit_message=\"Added extra files\",  # Optional commit message\n",
    "    ignore_patterns=\".git*\",  # Optional: ignore .git files and other patterns\n",
    ")\n",
    "\n",
    "print(f\"Directory '{local_dir}' pushed to: {repo_id}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Minimal",
   "language": "python",
   "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": "3.8.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}