app.py

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, AutoTokenizer

model_name = "TinyPixel/Llama-2-7B-bf16-sharded"

bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.float16,
)

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    quantization_config=bnb_config,
    trust_remote_code=True
)
model.config.use_cache = False

"""Let's also load the tokenizer below"""

tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
tokenizer.pad_token = tokenizer.eos_token

from peft import LoraConfig, get_peft_model

lora_alpha = 16
lora_dropout = 0.1
lora_r = 64

peft_config = LoraConfig(
    lora_alpha=lora_alpha,
    lora_dropout=lora_dropout,
    r=lora_r,
    bias="none",
    task_type="CAUSAL_LM"
)

"""## Loading the trainer

Here we will use the [`SFTTrainer` from TRL library](https://huggingface.co/docs/trl/main/en/sft_trainer) that gives a wrapper around transformers `Trainer` to easily fine-tune models on instruction based datasets using PEFT adapters. Let's first load the training arguments below.
"""

from transformers import TrainingArguments

output_dir = "./results"
per_device_train_batch_size = 4
gradient_accumulation_steps = 4
optim = "paged_adamw_32bit"
save_steps = 100
logging_steps = 10
learning_rate = 2e-4
max_grad_norm = 0.3
max_steps = 100
warmup_ratio = 0.03
lr_scheduler_type = "constant"

training_arguments = TrainingArguments(
    output_dir=output_dir,
    per_device_train_batch_size=per_device_train_batch_size,
    gradient_accumulation_steps=gradient_accumulation_steps,
    optim=optim,
    save_steps=save_steps,
    logging_steps=logging_steps,
    learning_rate=learning_rate,
    fp16=True,
    max_grad_norm=max_grad_norm,
    max_steps=max_steps,
    warmup_ratio=warmup_ratio,
    group_by_length=True,
    lr_scheduler_type=lr_scheduler_type,
)

"""Then finally pass everthing to the trainer"""

from trl import SFTTrainer

max_seq_length = 512

trainer = SFTTrainer(
    model=model,
    train_dataset=dataset,
    peft_config=peft_config,
    dataset_text_field="text",
    max_seq_length=max_seq_length,
    tokenizer=tokenizer,
    args=training_arguments,
)

"""We will also pre-process the model by upcasting the layer norms in float 32 for more stable training"""

for name, module in trainer.model.named_modules():
    if "norm" in name:
        module = module.to(torch.float32)

"""## Train the model

Now let's train the model! Simply call `trainer.train()`
"""

trainer.train()

"""During training, the model should converge nicely as follows:

![image](https://huggingface.co/datasets/trl-internal-testing/example-images/resolve/main/images/loss-falcon-7b.png)

The `SFTTrainer` also takes care of properly saving only the adapters during training instead of saving the entire model.
"""

model_to_save = trainer.model.module if hasattr(trainer.model, 'module') else trainer.model  # Take care of distributed/parallel training
model_to_save.save_pretrained("outputs")

lora_config = LoraConfig.from_pretrained('outputs')
model = get_peft_model(model, lora_config)

dataset['text']

text = "Écrire un texte dans un style baroque sur la glace et le feu ### Assistant: Si j'en luis éton"
device = "cuda:0"

inputs = tokenizer(text, return_tensors="pt").to(device)
outputs = model.generate(**inputs, max_new_tokens=50)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

from huggingface_hub import login
login()

model.push_to_hub("llama2-qlora-finetunined-french")