Lychee X comments

Results 111 comments of


                                            Lychee X

[BUG/Help] <title> 8 or 128 ?

raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError: Error(s) in loading state_dict for PrefixEncoder: size mismatch for embedding.weight: copying a param with shape torch.Size([8, 229376]) from checkpoint, the shape in...

[BUG/Help] <title> 8 or 128 ?

this is a big bug !!!

[BUG/Help] <title> 8 or 128 ?

下载的model怎么继续训练有人知道吗告知一下

fine tune ?? 是不是得用huggingface框架啊？

[BUG] 有没有同学遇到过这个错！！！加载本地txt文件出现这个killed错误，TXT文件有100M左右大小。

超内存了吧，你试试10M的，50M的。你这个是部署的api.py么？

能出一个api部署的描述文档吗

[我也是看不太懂咋请求api](https://github.com/imClumsyPanda/langchain-ChatGLM/issues/465)，postman咋测试啊？对于知识库问答的

OSError: Token is required (`token=True`), but no token found. You need to provide a token or be logged in to Hugging Face with `huggingface-cli login` or `huggingface_hub.login`. See https://huggingface.co/settings/tokens.

pass it your token ??? I have token but how to use it ? @sgugger

[FEATURE]: serving multiple models

this will make it great

gpt2 can't be trained for QA ?

@sgugger this is a bug, not question

[BUG] 安装bug记录

bug记录2:参考[此文档](https://www.heywhale.com/mw/project/643977aa446c45f4592a1e59) ``` local_doc_qa.init_cfg(llm_model=LLM_MODEL, embedding_model=EMBEDDING_MODEL, llm_history_len=LLM_HISTORY_LEN, top_k=VECTOR_SEARCH_TOP_K) ╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮ │ :1 in │ ╰──────────────────────────────────────────────────────────────────────────────────────────────────╯ TypeError: init_cfg() got an unexpected keyword argument 'llm_history_len' ```