Zhengxiao Du's picture

52 7

Zhengxiao Du

zxdu20

·

https://zxdu.xyz

duzx16

AI & ML interests

None yet

Organizations

zxdu20's activity

New activity in THUDM/glm-4-9b-chat 12 months ago

flash_attention_2

#51 opened 12 months ago by

New activity in THUDM/glm-4-9b-chat about 1 year ago

分类模型

#25 opened about 1 year ago by

New activity in THUDM/glm-4v-9b about 1 year ago

Can not inference

#4 opened about 1 year ago by

New activity in THUDM/chatglm2-6b over 1 year ago

有pro版本开源了吗？

#95 opened over 1 year ago by

fix when use_cache = False，inference 乱码

#85 opened over 1 year ago by

New activity in THUDM/chatglm2-6b almost 2 years ago

MacBook使用本地下载模型为什么会提示OSError: Can't load the configuration of 'your local path'.

#36 opened almost 2 years ago by

Update README.md

#41 opened almost 2 years ago by

longfish

#40 opened almost 2 years ago by

Request: DOI

#42 opened almost 2 years ago by

Ggml version please

#44 opened almost 2 years ago by

New activity in THUDM/chatglm-6b almost 2 years ago

Update README.md for typo

#87 opened almost 2 years ago by

New activity in THUDM/chatglm2-6b almost 2 years ago

It is so faaaaaast!

#30 opened almost 2 years ago by

Update README.md

#37 opened almost 2 years ago by

我做SFT微调时，发现tokenizer save的问题，需要改下

#13 opened almost 2 years ago by

RuntimeError: Internal: src/sentencepiece_processor.cc(1101) [model_proto->ParseFromArray(serialized.data(), serialized.size())]

#25 opened almost 2 years ago by

这个模型太强大了 , 感受到清华的威力,赞赞赞

#17 opened almost 2 years ago by

请教一下推理使用Multi-Query Attention 是需要在训练的时候就要使用Multi-Query Attention训练么

#21 opened almost 2 years ago by

0.0.216 版本 , 引入不了from langchain.document_loaders , 报错

#18 opened almost 2 years ago by

add default model_type

#10 opened almost 2 years ago by

可以处理更长的上下文，那么max_length应该设置更长？

#15 opened almost 2 years ago by