THUDM/chatglm-6b · Discussions

accelerate tokenizer

#98 opened 22 days ago by

lugim

chatglm2-6b微调过程中的attention_mask具体是如何实现的？哪一部分是双向，哪一部分是单向？

#97 opened 25 days ago by

someone652314

[AUTOMATED] Model Memory Requirements

#96 opened about 1 month ago by

model-sizer-bot

[AUTOMATED] Model Memory Requirements

#95 opened about 1 month ago by

model-sizer-bot

Update modeling_chatglm.py

#94 opened about 2 months ago by

Sofianesun

Update tokenization_chatglm.py

#93 opened 2 months ago by

fengkaige

🚩 Report: Ethical issue(s)

#92 opened 2 months ago by

syj1314

about self.scaled_masked_softmax in modeling_chatglm.py

#91 opened 2 months ago by

shl97

🚩 Report : Ethical issue(s)

#89 opened 3 months ago by

121121wqsas

Request: DOI

#88 opened 3 months ago by

shili1902

怎么做批量推理或生成？

#86 opened 3 months ago by

Shaobo1103

Could you support CPU device?

#85 opened 3 months ago by

changwangss

fix bug in tokenizer `decode` method

#84 opened 3 months ago by

njunlp

m2pro遇到RuntimeError: Unknown platform: darwin这个是什么问题

#83 opened 4 months ago by

jindada

Update README.md

#82 opened 4 months ago by

KaiwenS

多 batch 推理结果不对齐

4

#81 opened 4 months ago by

shungouxu

local deploy chatglm-6b issues

1

#80 opened 4 months ago by

guangfan

chatglm-6b在推理的时候可以修改温度吗？

#79 opened 4 months ago by

Prettyxfan

chatglm-6b如何支持stream流式输出啊

1

#78 opened 4 months ago by

Zomens

add gradient checkpointing for the final_layernorm module.

#77 opened 4 months ago by

zhaoqf123

基于chatglm-6b和mnn的离线安卓app

4

#76 opened 4 months ago by

zhaode

fix: truncate finished output in stream_generate

#74 opened 4 months ago by

goldenteethCN

KeyError: 'attention_mask'

#73 opened 4 months ago by

lanshan

v1.1，加载时报错 Unable to load weights from pytorch checkpoint file for '...'. If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True.

3

#72 opened 4 months ago by

hanswang73

索引超出范围

#71 opened 4 months ago by

ZXF123

Request: DOI

#70 opened 5 months ago by

dante314

Error of missing pipeline_tag

1

#69 opened 5 months ago by

radekbr86

求助：跑webDemo抛异常

#68 opened 5 months ago by

HuangSong

可以用transformers对chatglm-6b做微调吗？

#67 opened 5 months ago by

lunfan

[BUG/Help] ice_text.model词表长度与config里设置不一致

#65 opened 5 months ago by

Au3C2

Tokenizer 不支持batch encode

#64 opened 5 months ago by

next-social

利用chatglm6b进行embedding提取，输入input_ids提取出来的embedding全为0

1

#63 opened 5 months ago by

XiaoHangjia

怎么用chatglm做embedding

5

#62 opened 5 months ago by

betterme

chatglm-6B 如何在 Mac M2 上微调

19

#61 opened 5 months ago by

xiao111

支持batch形式的对话

1

#60 opened 5 months ago by

curlyfu

输入的最大字符串长度限制

1

#58 opened 5 months ago by

huvee

🚩 Report

#57 opened 5 months ago by

YokiLee

Update README.md

#55 opened 5 months ago by

zyuhang

下面这几个glm微调的方法相同么？

4

#54 opened 5 months ago by

kewei

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

2

#53 opened 5 months ago by

leoyangsw

'list' object has no attribute 'endswith'

#52 opened 5 months ago by

liuair

训练之后，模型就只会回答服装的问题，好像是有问题

#51 opened 5 months ago by

carlosbdw

How to remove chinese words in output

#49 opened 5 months ago by

SudipThomas

add custom onnx export config

3

#46 opened 6 months ago by

ltcs15

Update modeling_chatglm.py for inputs_embeds

2

#45 opened 6 months ago by

Xipotzzz

🚩 Report : Ethical issue(s)

#44 opened 6 months ago by

yltx

gptq量化相关代码

10

#43 opened 6 months ago by

BigMaoGoGoGo

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

2

#42 opened 6 months ago by

liuhantao

Tokenizer

#41 opened 6 months ago by

quyetzz

About the unusual attention_mask of ChatGLM

1

#40 opened 6 months ago by

hiyouga