THUDM
/

chatglm-6b

Inference Endpoints

Model card Files Files and versions Community

Resources

View closed (33)

下面这几个glm微调的方法相同么？

#54 opened over 1 year ago by

When load_in_8bit=True, the chat becomes VERY VERY SLOW and returns nothing

#53 opened over 1 year ago by

'list' object has no attribute 'endswith'

#52 opened over 1 year ago by

训练之后，模型就只会回答服装的问题，好像是有问题

#51 opened over 1 year ago by

How to remove chinese words in output

#49 opened over 1 year ago by

add custom onnx export config

#46 opened over 1 year ago by

Update modeling_chatglm.py for inputs_embeds

#45 opened over 1 year ago by

🚩 Report : Ethical issue(s)

#44 opened over 1 year ago by

gptq量化相关代码

#43 opened over 1 year ago by

transformers 从4.26.1 升级至4.27.1 后报错 ModuleNotFoundError: No module named 'transformers_modules.THUDM/chatglm-6b'

#42 opened over 1 year ago by

Tokenizer

#41 opened over 1 year ago by

startlightquyet

About the unusual attention_mask of ChatGLM

#40 opened over 1 year ago by

python3.7 pytorch_model.bin, tf_model.h5, model.ckpt.index or flax_model.msgpack缺失

#38 opened over 1 year ago by

一个用 chatglm-6b 微调训练的例子

#34 opened over 1 year ago by

how convert chatglm-6b to save_model.pb?

#27 opened over 1 year ago by

有人用这个模型训练过吗？

#24 opened over 1 year ago by

ONNX Models Export from ChatGLM-6B

#19 opened over 1 year ago by

A pure C++ implementation, support CUDA, CPU, OpenCL etc.

#17 opened over 1 year ago by

What is the id of eos_token?

#15 opened over 1 year ago by

什么时候出一个类似于chatGPT的Retrieval插件？

#14 opened over 1 year ago by

Can I specify the number of threads used in CPU reasoning?

#13 opened almost 2 years ago by

how to evaluate it

#12 opened almost 2 years ago by

Post-inference normalization with user-provided locale hints

#6 opened almost 2 years ago by

Can it load on CPU mode?

#4 opened almost 2 years ago by

FenixInDarkSolo

very cool!

#2 opened almost 2 years ago by

How to finetune this model

#1 opened almost 2 years ago by