61 lines
1.4 KiB
Python
61 lines
1.4 KiB
Python
from langchain.llms.base import LLM
|
|
from typing import Optional, List
|
|
from langchain.llms.utils import enforce_stop_tokens
|
|
from transformers import AutoTokenizer, AutoModel
|
|
import torch
|
|
|
|
DEVICE = "cuda"
|
|
DEVICE_ID = "0"
|
|
CUDA_DEVICE = f"{DEVICE}:{DEVICE_ID}" if DEVICE_ID else DEVICE
|
|
|
|
|
|
def torch_gc():
|
|
if torch.cuda.is_available():
|
|
with torch.cuda.device(CUDA_DEVICE):
|
|
torch.cuda.empty_cache()
|
|
torch.cuda.ipc_collect()
|
|
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained(
|
|
"THUDM/chatglm-6b",
|
|
trust_remote_code=True
|
|
)
|
|
model = (
|
|
AutoModel.from_pretrained(
|
|
"THUDM/chatglm-6b",
|
|
trust_remote_code=True)
|
|
.half()
|
|
.cuda()
|
|
)
|
|
|
|
|
|
class ChatGLM(LLM):
|
|
max_token: int = 10000
|
|
temperature: float = 0.1
|
|
top_p = 0.9
|
|
history = []
|
|
|
|
def __init__(self):
|
|
super().__init__()
|
|
|
|
@property
|
|
def _llm_type(self) -> str:
|
|
return "ChatGLM"
|
|
|
|
def _call(self,
|
|
prompt: str,
|
|
stop: Optional[List[str]] = None) -> str:
|
|
response, updated_history = model.chat(
|
|
tokenizer,
|
|
prompt,
|
|
history=self.history,
|
|
max_length=self.max_token,
|
|
temperature=self.temperature,
|
|
)
|
|
torch_gc()
|
|
print("history: ", self.history)
|
|
if stop is not None:
|
|
response = enforce_stop_tokens(response, stop)
|
|
self.history = updated_history
|
|
return response
|