MegEngine / MegEngine/InferLLM

无法加载模型bin或者guff模型

Open
#84 2 comments 0 reactions 0 assignees View on GitHub
Dominant language
C++
Stars
752
Forks
94
PR merge metrics
No merged PRs in 30d

Description

除了官方示例的chinese-alpaca-7b-q4.bin,其他的都会报如下错误。

Assert ' 0 ' failed at file : /home/openkylin/workspace/InferLLM/src/graph/ggml_llama.cpp
line 37 : virtual void inferllm::GgmlLlamaGraph::load(std::shared_ptr, inferllm::LlmParams&, std::shared_ptr),
extra message: unsupported model type.已放弃

然而我将相同的模型用llama.cpp运行没有问题

Contributor guide

No contributing guide indexed for this repository

Research direction

Start at src/graph/ggml_llama.cpp line 37 and reproduce the failure with a model other than chinese-alpaca-7b-q4.bin. Compare the model types accepted there with the model formats that load successfully in llama.cpp. Done means supported bin or GGUF models load without the unsupported-model assertion.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.