gpt-academicc / request_llm /bridge_qwen.py
qingxu98's picture
"version": 3.48
8a5e8bc
raw
history blame
2.98 kB
model_name = "Qwen"
cmd_to_install = "`pip install -r request_llm/requirements_qwen.txt`"
from transformers import AutoModel, AutoTokenizer
import time
import threading
import importlib
from toolbox import update_ui, get_conf
from multiprocessing import Process, Pipe
from .local_llm_class import LocalLLMHandle, get_local_llm_predict_fns, SingletonLocalLLM
# ------------------------------------------------------------------------------------------------------------------------
# ๐Ÿ”Œ๐Ÿ’ป Local Model
# ------------------------------------------------------------------------------------------------------------------------
@SingletonLocalLLM
class GetONNXGLMHandle(LocalLLMHandle):
def load_model_info(self):
# ๐Ÿƒโ€โ™‚๏ธ๐Ÿƒโ€โ™‚๏ธ๐Ÿƒโ€โ™‚๏ธ ๅญ่ฟ›็จ‹ๆ‰ง่กŒ
self.model_name = model_name
self.cmd_to_install = cmd_to_install
def load_model_and_tokenizer(self):
# ๐Ÿƒโ€โ™‚๏ธ๐Ÿƒโ€โ™‚๏ธ๐Ÿƒโ€โ™‚๏ธ ๅญ่ฟ›็จ‹ๆ‰ง่กŒ
import os, glob
import os
import platform
from modelscope import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
model_id = 'qwen/Qwen-7B-Chat'
revision = 'v1.0.1'
self._tokenizer = AutoTokenizer.from_pretrained(model_id, revision=revision, trust_remote_code=True)
# use fp16
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", revision=revision, trust_remote_code=True, fp16=True).eval()
model.generation_config = GenerationConfig.from_pretrained(model_id, trust_remote_code=True) # ๅฏๆŒ‡ๅฎšไธๅŒ็š„็”Ÿๆˆ้•ฟๅบฆใ€top_p็ญ‰็›ธๅ…ณ่ถ…ๅ‚
self._model = model
return self._model, self._tokenizer
def llm_stream_generator(self, **kwargs):
# ๐Ÿƒโ€โ™‚๏ธ๐Ÿƒโ€โ™‚๏ธ๐Ÿƒโ€โ™‚๏ธ ๅญ่ฟ›็จ‹ๆ‰ง่กŒ
def adaptor(kwargs):
query = kwargs['query']
max_length = kwargs['max_length']
top_p = kwargs['top_p']
temperature = kwargs['temperature']
history = kwargs['history']
return query, max_length, top_p, temperature, history
query, max_length, top_p, temperature, history = adaptor(kwargs)
for response in self._model.chat(self._tokenizer, query, history=history, stream=True):
yield response
def try_to_import_special_deps(self, **kwargs):
# import something that will raise error if the user does not install requirement_*.txt
# ๐Ÿƒโ€โ™‚๏ธ๐Ÿƒโ€โ™‚๏ธ๐Ÿƒโ€โ™‚๏ธ ไธป่ฟ›็จ‹ๆ‰ง่กŒ
import importlib
importlib.import_module('modelscope')
# ------------------------------------------------------------------------------------------------------------------------
# ๐Ÿ”Œ๐Ÿ’ป GPT-Academic Interface
# ------------------------------------------------------------------------------------------------------------------------
predict_no_ui_long_connection, predict = get_local_llm_predict_fns(GetONNXGLMHandle, model_name)