ymcui / Chinese-LLaMA-Alpaca-3

中文羊驼大模型三期项目 (Chinese Llama-3 LLMs) developed from Meta Llama 3
Apache License 2.0
1.57k stars 142 forks source link

读取模型ggml-model-q8_0.gguf出错 #88

Closed phoenixlucky closed 1 month ago

phoenixlucky commented 2 months ago

提交前必须检查以下项目

问题类型

模型量化和部署

基础模型

Llama-3-Chinese-8B-Instruct(指令模型)

操作系统

Windows

详细描述问题

读取模型ggml-model-q8_0.gguf出错

Traceback (most recent call last):

File "F:\text-generation-webui\modules\ui_model_menu.py", line 248, in load_model_wrapper

shared.model, shared.tokenizer = load_model(selected_model, loader)

                                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\text-generation-webui\modules\models.py", line 94, in load_model

output = load_func_map[loader](model_name)

         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\text-generation-webui\modules\models.py", line 275, in llamacpp_loader

model, tokenizer = LlamaCppModel.from_pretrained(model_file)

                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\text-generation-webui\modules\llamacpp_model.py", line 38, in from_pretrained

Llama = llama_cpp_lib().Llama

        ^^^^^^^^^^^^^^^^^^^^^
AttributeError: 'NoneType' object has no attribute 'Llama'

依赖情况(代码类问题务必提供)

# 请在此处粘贴依赖情况(请粘贴在本代码块里)

运行日志或截图

# 请在此处粘贴运行日志(请粘贴在本代码块里)
ymcui commented 2 months ago

从HuggingFace下载的话可以核对一下SHA256,检查模型是否完整。llama.cpp下加载没有问题。

github-actions[bot] commented 1 month ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your consideration.

github-actions[bot] commented 1 month ago

Closing the issue, since no updates observed. Feel free to re-open if you need any further assistance.