Resources

模型使用ptv2微调后其他能力下降该如何解决

#52 opened about 3 years ago by

couldn

🚩 Report

#51 opened about 3 years ago by

leyong

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

#50 opened about 3 years ago by

couldn

add set_input_embedding to support resize token embedding

#49 opened about 3 years ago by

Yes365

Update README.md

#48 opened about 3 years ago by

Arjun2001

Update README.md

#47 opened about 3 years ago by

Arjun2001

请问，chatGLM-6b自动更新后就是chatGLM2-6b吗？

#46 opened about 3 years ago by

lysen963

Openllm调用GLM

#45 opened about 3 years ago by

cat13

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

#43 opened about 3 years ago by

haaaaaaaa1

本地加载失败？

#39 opened about 3 years ago by

enozhu

建议forward函数参数增加full_attention_mask

#35 opened about 3 years ago by

zkwhandan

为啥hugging face的Hosted inference API不能直接用哇

#34 opened about 3 years ago by

chrisliang

GGML version please!

#33 opened about 3 years ago by

Hoioi

BatchEncoding error

#32 opened about 3 years 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

#29 opened about 3 years ago by

elven2023

Utilizing chatglm2-6b for Downstream Classification Tasks

❤️ 3

#28 opened about 3 years ago by

CeroShrijver

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

🔥 1

#22 opened about 3 years ago by

RogerChen

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

#19 opened about 3 years ago by

moumouliu

model_type

#16 opened about 3 years ago by

JaheimLee

请问有没有这版模型的微调DEMO

#12 opened about 3 years ago by

robinzyx

Update modeling_chatglm.py

#11 opened about 3 years ago by

tingxinli

中英文标点混杂

#8 opened about 3 years ago by

JaheimLee

peft

#4 opened about 3 years ago by

xzhdsb

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

👍 4

#1 opened about 3 years ago by

JosephusCheung