NeuTrixOmniBe-DPO / README.md
Kukedlc's picture
Update README.md
1b1cf19 verified
|
raw
history blame
1.34 kB
metadata
license: apache-2.0

Modelo entrenado con DPO

Merge de dos modelos

codigo de train:

LoRA configuration

peft_config = LoraConfig( r=16, lora_alpha=16, lora_dropout=0.05, bias="none", task_type="CAUSAL_LM", target_modules=['k_proj', 'gate_proj', 'v_proj', 'up_proj', 'q_proj', 'o_proj', 'down_proj'] )

Model to fine-tune

model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype=torch.float16, load_in_4bit=True ) model.config.use_cache = False

Reference model

ref_model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype=torch.float16, load_in_4bit=True )

Training arguments

training_args = TrainingArguments( per_device_train_batch_size=4, gradient_accumulation_steps=4, gradient_checkpointing=True, learning_rate=5e-5, lr_scheduler_type="cosine", max_steps=200, save_strategy="no", logging_steps=1, output_dir=new_model, optim="paged_adamw_32bit", warmup_steps=100, bf16=True, report_to="wandb", )

Create DPO trainer

dpo_trainer = DPOTrainer( model, ref_model, args=training_args, train_dataset=dataset, tokenizer=tokenizer, peft_config=peft_config, beta=0.1, max_prompt_length=1024, max_length=1536, )

Fine-tune model with DPO

dpo_trainer.train()