Hugging Face's logo

THUDM
/
chatglm2-6b

Transformers
PyTorch
Chinese
English
chatglm
glm
thudm
custom_code
Inference Endpoints
Model card Files Community
109
New discussion

微调后模型预测一直为空，我是使用readme中的参数微调的，但是使用的基座模型是量化4版本，不知道是不是这个原因

4
#50 opened over 1 year ago by couldn

add set_input_embedding to support resize token embedding
#49 opened over 1 year ago by Yes365

Update README.md
#48 opened over 1 year ago by Arjun2001

Update README.md
#47 opened over 1 year ago by Arjun2001

请问，chatGLM-6b自动更新后就是chatGLM2-6b吗？

1
#46 opened over 1 year ago by lysen963

Openllm调用GLM
#45 opened over 1 year ago by cat13

有没有quantization_kernels.c和quantization_kernels_parallel.c文件下载

3
#43 opened over 1 year ago by haaaaaaaa1

本地加载失败？

2
#39 opened over 1 year ago by enozhu

建议forward函数参数增加full_attention_mask
#35 opened over 1 year ago by zkwhandan

为啥hugging face的Hosted inference API不能直接用哇
#34 opened over 1 year ago by chrisliang

GGML version please!

2
#33 opened over 1 year ago by Hoioi

BatchEncoding error
#32 opened over 1 year ago by thirdHand

when use oobabooga/ext-generation-webui load this mode ，the chat message was blank and the terminal reponse error：IndexError: list index out of range

3
#29 opened over 1 year ago by elven2023

Utilizing chatglm2-6b for Downstream Classification Tasks
#28 opened over 1 year ago by CeroShrijver

unable to access 'https://huggingface.co/THUDM/chatglm2-6b/': Recv failure: Connection reset by peer

8
#22 opened over 1 year ago by RogerChen

ptuning微调报错'ChatGLMModel' object has no attribute 'prefix_encoder'

3
#19 opened over 1 year ago by moumouliu

model_type

1
#16 opened over 1 year ago by JaheimLee

请问有没有这版模型的微调DEMO

2
#12 opened over 1 year ago by robinzyx

Update modeling_chatglm.py
#11 opened over 1 year ago by tingxinli

中英文标点混杂

1
#8 opened over 1 year ago by JaheimLee

peft

1
#4 opened over 1 year ago by xzhdsb

Will the BASE model - ChatGLM2-6B (base) also be released?

3
#1 opened over 1 year ago by JosephusCheung