|
--- |
|
datasets: |
|
- IlyaGusev/gpt_roleplay_realm |
|
language: |
|
- en |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
LLaMA 7B fine-tuned on the English part of the `gpt_roleplay_realm` dataset. |
|
|
|
Code example: |
|
``` |
|
from peft import PeftModel, PeftConfig |
|
from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig |
|
|
|
MODEL_NAME = "IlyaGusev/rpr_7b" |
|
DEFAULT_MESSAGE_TEMPLATE = "<s>{role}\n{content}</s>\n" |
|
|
|
class Conversation: |
|
def __init__( |
|
self, |
|
system_prompt, |
|
message_template=DEFAULT_MESSAGE_TEMPLATE, |
|
start_token_id=1, |
|
bot_token_id=9225 |
|
): |
|
self.message_template = message_template |
|
self.start_token_id = start_token_id |
|
self.bot_token_id = bot_token_id |
|
self.messages = [{ |
|
"role": "system", |
|
"content": system_prompt |
|
}] |
|
|
|
def get_start_token_id(self): |
|
return self.start_token_id |
|
|
|
def get_bot_token_id(self): |
|
return self.bot_token_id |
|
|
|
def add_user_message(self, message): |
|
self.messages.append({ |
|
"role": "user", |
|
"content": message |
|
}) |
|
|
|
def add_bot_message(self, message): |
|
self.messages.append({ |
|
"role": "bot", |
|
"content": message |
|
}) |
|
|
|
def get_prompt(self, tokenizer): |
|
final_text = "" |
|
for message in self.messages: |
|
message_text = self.message_template.format(**message) |
|
final_text += message_text |
|
final_text += tokenizer.decode([self.start_token_id, self.bot_token_id]) |
|
return final_text.strip() |
|
|
|
|
|
def generate(model, tokenizer, prompt, generation_config): |
|
data = tokenizer(prompt, return_tensors="pt") |
|
data = {k: v.to(model.device) for k, v in data.items()} |
|
output_ids = model.generate(**data,generation_config=generation_config)[0] |
|
output_ids = output_ids[len(data["input_ids"][0]):] |
|
output = tokenizer.decode(output_ids, skip_special_tokens=True) |
|
return output.strip() |
|
|
|
|
|
config = PeftConfig.from_pretrained(MODEL_NAME) |
|
model = AutoModelForCausalLM.from_pretrained( |
|
config.base_model_name_or_path, |
|
load_in_8bit=True, |
|
torch_dtype=torch.float16, |
|
device_map="auto" |
|
) |
|
model = PeftModel.from_pretrained( |
|
model, |
|
MODEL_NAME, |
|
torch_dtype=torch.float16 |
|
) |
|
model.eval() |
|
|
|
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME) |
|
generation_config = GenerationConfig.from_pretrained(MODEL_NAME) |
|
print(generation_config) |
|
|
|
system_prompt = "You are Chiharu Yamada. Chiharu Yamada is a young, computer engineer-nerd with a knack for problem solving and a passion for technology." |
|
conversation = Conversation(system_prompt=system_prompt) |
|
for inp in inputs: |
|
inp = input() |
|
conversation.add_user_message(inp) |
|
prompt = conversation.get_prompt(tokenizer) |
|
output = generate(model, tokenizer, prompt, generation_config) |
|
conversation.add_bot_message(output) |
|
print(output) |
|
``` |