search

qhjqhj00 / MemoRAG

Empowering RAG with a memory-based data interface for all-purpose applications!
Apache License 2.0
1.2k stars 74 forks source link

LlamaForCausalLM.__init__() got an unexpected keyword argument 'beacon_ratio' #26

Closed XinyuDu closed 1 month ago

XinyuDu commented 1 month ago

测试中文模型"shenzhi-wang/Llama3.1-8B-Chinese-Chat"的时候，报‘got an unexpected keyword argument 'beacon_ratio'的错误。

XinyuDu commented 1 month ago

升级最新代码解决了。

jvel07 commented 1 month ago

@XinyuDu did you ever receive the error below after this line of code: pipe.memorize(small_part, save_dir="constitution/", print_stats=True) Error: AttributeError: 'LlamaForCausalLM' object has no attribute 'memory' when loading a different model than TommyChien/memorag-qwen2-7b-inst? Did you try llama3 official HF model?