mistral_fine_tuning.py

# -*- coding: utf-8 -*-
"""Mistral_fine-tuning.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/12WLPo_Aicjhp7sy8zbZmfg5behAZJVYN
"""

!pip install -q -U bitsandbytes
!pip install -q -U git+https://github.com/huggingface/transformers.git
!pip install -q -U git+https://github.com/huggingface/peft.git
!pip install -q -U git+https://github.com/huggingface/accelerate.git
!pip install -q -U datasets scipy ipywidgets matplotlib

from datasets import load_dataset

dataset = load_dataset("Devdeshitha/testdataset1")

from datasets import load_dataset

train_dataset = load_dataset('json', data_files='notes.jsonl', split='train')
eval_dataset = load_dataset('json', data_files='notes_validation.jsonl', split='train')

def formatting_func(example):
    text = f"### Question: {example['input']}\n ### Answer: {example['output']}"
    return text

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig

base_model_id = "mistralai/Mistral-7B-v0.1"
bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_use_double_quant=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.bfloat16
)

model = AutoModelForCausalLM.from_pretrained(base_model_id, quantization_config=bnb_config)

tokenizer = AutoTokenizer.from_pretrained(
    base_model_id,
    padding_side="left",
    add_eos_token=True,
    add_bos_token=True,
)
tokenizer.pad_token = tokenizer.eos_token

def generate_and_tokenize_prompt(prompt):
    return tokenizer(formatting_func(prompt))

tokenized_train_dataset = train_dataset.map(generate_and_tokenize_prompt)
tokenized_val_dataset = eval_dataset.map(generate_and_tokenize_prompt)

max_length = 1024  #This was an appropriate max length for my dataset

def generate_and_tokenize_prompt2(prompt):
    result = tokenizer(
        formatting_func(prompt),
        truncation=True,
        max_length=max_length,
        padding="max_length",
    )
    result["labels"] = result["input_ids"].copy()
    return result

tokenized_train_dataset = train_dataset.map(generate_and_tokenize_prompt2)
tokenized_val_dataset = eval_dataset.map(generate_and_tokenize_prompt2)

print(tokenized_train_dataset[1]['input_ids'])

eval_prompt = "How does consolidating credit cards into a loan work?: "

# Re-init the tokenizer so it doesn't add padding or eos token
tokenizer = AutoTokenizer.from_pretrained(
    base_model_id,
    add_bos_token=True,
)

model_input = tokenizer(eval_prompt, return_tensors="pt").to("cuda")

model.eval()
with torch.no_grad():
    print(tokenizer.decode(model.generate(**model_input, max_new_tokens=512, repetition_penalty=1.15)[0], skip_special_tokens=True))

"""Set Up LoRA

Now, to start our fine-tuning, we have to apply some preprocessing to the model to prepare it for training. For that use the prepare_model_for_kbit_training method from PEFT.

"""