Spaces:
Sleeping
Sleeping
File size: 3,155 Bytes
8a5e8bc |
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 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 |
model_name = "ChatGLM-ONNX"
cmd_to_install = "`pip install -r request_llm/requirements_chatglm_onnx.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
from .chatglmoonx import ChatGLMModel, chat_template
# ------------------------------------------------------------------------------------------------------------------------
# ππ» Local Model
# ------------------------------------------------------------------------------------------------------------------------
@SingletonLocalLLM
class GetONNXGLMHandle(LocalLLMHandle):
def load_model_info(self):
# πββοΈπββοΈπββοΈ εθΏη¨ζ§θ‘
self.model_name = model_name
self.cmd_to_install = cmd_to_install
def load_model_and_tokenizer(self):
# πββοΈπββοΈπββοΈ εθΏη¨ζ§θ‘
import os, glob
if not len(glob.glob("./request_llm/ChatGLM-6b-onnx-u8s8/chatglm-6b-int8-onnx-merged/*.bin")) >= 7: # θ―₯樑εζδΈδΈͺ bin ζδ»Ά
from huggingface_hub import snapshot_download
snapshot_download(repo_id="K024/ChatGLM-6b-onnx-u8s8", local_dir="./request_llm/ChatGLM-6b-onnx-u8s8")
def create_model():
return ChatGLMModel(
tokenizer_path = "./request_llm/ChatGLM-6b-onnx-u8s8/chatglm-6b-int8-onnx-merged/sentencepiece.model",
onnx_model_path = "./request_llm/ChatGLM-6b-onnx-u8s8/chatglm-6b-int8-onnx-merged/chatglm-6b-int8.onnx"
)
self._model = create_model()
return self._model, None
def llm_stream_generator(self, **kwargs):
# πββοΈπββοΈπββοΈ εθΏη¨ζ§θ‘
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)
prompt = chat_template(history, query)
for answer in self._model.generate_iterate(
prompt,
max_generated_tokens=max_length,
top_k=1,
top_p=top_p,
temperature=temperature,
):
yield answer
def try_to_import_special_deps(self, **kwargs):
# import something that will raise error if the user does not install requirement_*.txt
# πββοΈπββοΈπββοΈ εθΏη¨ζ§θ‘
pass
# ------------------------------------------------------------------------------------------------------------------------
# ππ» GPT-Academic Interface
# ------------------------------------------------------------------------------------------------------------------------
predict_no_ui_long_connection, predict = get_local_llm_predict_fns(GetONNXGLMHandle, model_name) |