search

nomic-ai / gpt4all

GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
https://nomic.ai/gpt4all
MIT License
69.76k stars 7.63k forks source link

Error tensor 'token_embd. weight' not found while loading model #2458

Closed littletiga3 closed 2 months ago

littletiga3 commented 3 months ago

Bug Report

Error tensor 'token_embd. weight' not found while loading model

Steps to Reproduce

1.After successful construction, run chat. exe in qt creator 2.load a model to continue 3.Error llama_model_load: error loading model: check_tensor_dims: tensor 'token_embd. weight' not found

Expected Behavior

The model was loaded correctly

Your Environment

image

michellelyHuang728 commented 3 months ago

Same Question

b4zz4 commented 2 months ago

I have the same problem with flame.cpp.

cebtenzzre commented 2 months ago

You cannot load ggml-vocab-baichuan.gguf. It is not an LLM. It is merely the vocabulary for one without any model weights. Make sure your GPT4All models directory does not contain any such models.