File size: 1,371 Bytes
fa4458a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 |
# 0. imports
import torch
from transformers import GPT2Tokenizer
from trl import AutoModelForCausalLMWithValueHead, PPOConfig, PPOTrainer
# 1. load a pretrained model
model = AutoModelForCausalLMWithValueHead.from_pretrained("gpt2")
model_ref = AutoModelForCausalLMWithValueHead.from_pretrained("gpt2")
tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
tokenizer.pad_token = tokenizer.eos_token
# 2. initialize trainer
ppo_config = {"batch_size": 1}
config = PPOConfig(**ppo_config)
ppo_trainer = PPOTrainer(config, model, model_ref, tokenizer)
# 3. encode a query
query_txt = "This morning I went to the "
query_tensor = tokenizer.encode(query_txt, return_tensors="pt").to(model.pretrained_model.device)
# 4. generate model response
generation_kwargs = {
"min_length": -1,
"top_k": 0.0,
"top_p": 1.0,
"do_sample": True,
"pad_token_id": tokenizer.eos_token_id,
"max_new_tokens": 20,
}
response_tensor = ppo_trainer.generate([item for item in query_tensor], return_prompt=False, **generation_kwargs)
response_txt = tokenizer.decode(response_tensor[0])
# 5. define a reward for response
# (this could be any reward such as human feedback or output from another model)
reward = [torch.tensor(1.0, device=model.pretrained_model.device)]
# 6. train model with ppo
train_stats = ppo_trainer.step([query_tensor[0]], [response_tensor[0]], reward)
|