local_inference/4bit_bnb.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Llama-3.1-8B-Instruct in 4-bit bitsandbytes"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's first install the required libraries:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "! pip install transformers[torch] bitsandbytes"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We import the required libraries : "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch\n",
    "from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's load the model. To quantize the model on the fly, we pass a `quantization_config`:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "model_name = \"meta-llama/Meta-Llama-3.1-8B-Instruct\"\n",
    "quantization_config = BitsAndBytesConfig(load_in_4bit=True,\n",
    "                                         bnb_4bit_compute_dtype=torch.bfloat16,\n",
    "                                         bnb_4bit_use_double_quant=True,\n",
    "                                         bnb_4bit_quant_type= \"nf4\"\n",
    "                                         )\n",
    "\n",
    "quantized_model = AutoModelForCausalLM.from_pretrained(\n",
    "\tmodel_name, device_map=\"auto\", torch_dtype=torch.bfloat16, quantization_config=quantization_config)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Then, we need to prepare the inputs: "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "tokenizer = AutoTokenizer.from_pretrained(model_name)\n",
    "input_text = \"What are we having for dinner?\"\n",
    "input_ids = tokenizer(input_text, return_tensors=\"pt\").to(\"cuda\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Finally, we can generate the output ! "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "output = quantized_model.generate(**input_ids, max_new_tokens=10)\n",
    "\n",
    "print(tokenizer.decode(output[0], skip_special_tokens=True))"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "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
}