Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to content

Issues: THUDM/GLM-4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

28 Open 400 Closed
28 Open 400 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

AttributeError: 'NoneType' object has no attribute 'shape'
#493 opened Aug 17, 2024 by jjzhu0579
1 of 2 tasks
@zRzRzRzRzRzRzR
1
微调脚本是否支持CodeGeex4?
#492 opened Aug 16, 2024 by songpb
1 of 2 tasks
@zRzRzRzRzRzRzR
1
glm4v 对于纯文本微调的支持
#489 opened Aug 15, 2024 by Jintao-Huang
1
GLM4训练过程中进行验证速度非常慢，比chatGLM3慢很多
#488 opened Aug 15, 2024 by guvsta
2 tasks done
@zRzRzRzRzRzRzR
2
l微调后推理输出乱码
#486 opened Aug 14, 2024 by cangyizhou
1 of 2 tasks
@zRzRzRzRzRzRzR
3
用 openai_api_server.py 多卡运行 glm-4-9b-chat 处理长文本的时候可能会胡乱输出
#476 opened Aug 13, 2024 by oubeichen
1 of 2 tasks
@zRzRzRzRzRzRzR
7
使用open_api_server部署api后，在spring ai中无法使用：POST /v1/chat/completions HTTP/1.1" 422 Unprocessable Entity
#473 opened Aug 13, 2024 by Lzzzii10
2 tasks
@zRzRzRzRzRzRzR
5
8卡lora微调训练，数据集AdvertiseGen，loss从3.2613开始到1000多个step之后一直在2.8 2.9左右震荡，请问这是正常的吗
#464 opened Aug 9, 2024 by yangrz7
@zRzRzRzRzRzRzR
9
glm-4v-9b微调eval阶段出错，attention_mask未考虑visual tokens
#463 opened Aug 9, 2024 by Hoonly
1 of 2 tasks
@zRzRzRzRzRzRzR
1
工具调用时，promp回答和工具无关时stream=true设置无效
#454 opened Aug 8, 2024 by justnobug
2 tasks
@zRzRzRzRzRzRzR
可以写一个支持mlx环境运行的模型代码吗
#453 opened Aug 8, 2024 by arthasyou
@zRzRzRzRzRzRzR
2
Rust Candle Framework Support
#451 opened Aug 8, 2024 by donjuanplatinum
@zRzRzRzRzRzRzR
本地glm4-9B模型使用function call 功能的问题
#448 opened Aug 7, 2024 by sunyicode0012
1 of 2 tasks
@zRzRzRzRzRzRzR
1
GLM-4 and Dify Response Reception Issue
#447 opened Aug 7, 2024 by ZYMCCX
2 tasks
@zRzRzRzRzRzRzR
1
You: bug GLM-4:The attention mask is not set and cannot be inferred from input because pad token is same as eos token.As a consequence, you may observe unexpected behavior. Please pass your input's attention_mask to obtain reliable results.
#443 opened Aug 5, 2024 by 2662007798
1 of 2 tasks
@zRzRzRzRzRzRzR
17
为啥system消息会传两次？
#442 opened Aug 5, 2024 by ciaoyizhen
@zRzRzRzRzRzRzR
TypeError: GenerationMixin._extract_past_from_model_output() got an unexpected keyword argument 'standardize_cache_format'
#439 opened Aug 4, 2024 by Mellow156
1 of 2 tasks
@zRzRzRzRzRzRzR
8
微调报错 ValueError: 151337 is not in list
#438 opened Aug 4, 2024 by TTXS123OK
1 of 2 tasks
@zRzRzRzRzRzRzR
8
请问如何加载ptuning微调后的模型，如下图所示，提示不支持prompt learning，但是相同的代码可以加载lora微调的模型，代码就是贵方给出的加载代码
#437 opened Aug 4, 2024 by LeeGitHub1
@zRzRzRzRzRzRzR
[glm-4v-9b]关于eval情况下的padding问题。
#433 opened Aug 1, 2024 by marko1616
@zRzRzRzRzRzRzR
2
ChatGLM4 batch推理时padding 细节
#424 opened Jul 31, 2024 by geekchen007
1 of 2 tasks
@zRzRzRzRzRzRzR
2
GLM4V在推理时候偶发出现重复循环输出相同文字
#390 opened Jul 24, 2024 by simoncai519
1 of 2 tasks
@zRzRzRzRzRzRzR
2
模型使用vllm推理报错
#381 opened Jul 23, 2024 by shatang123
1 of 2 tasks
@zRzRzRzRzRzRzR
1
chatglm3与glm4的tokenizer有什么不同吗？ chatglm3可以使用outlines，但是glm4会报错
#362 opened Jul 18, 2024 by Mewral
1 of 2 tasks
@zRzRzRzRzRzRzR
2
Ollama运行GLM-4-9b后乱码
#333 opened Jul 13, 2024 by lalahaohaizi
2 tasks
@zRzRzRzRzRzRzR
17
ProTip! Updated in the last three days: updated:>2024-08-15.