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

34 Open 538 Closed
34 Open 538 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

finetune_demo目录的inference方法，怎样才能变成流式输出
#661 opened Nov 26, 2024 by xuechaofei
1 of 2 tasks
@sixsixcoder
使用lora方案进行GLM-4-9B Chat 对话模型微调后，如何在xinference平台中加载？
#660 opened Nov 26, 2024 by xuechaofei
1 of 2 tasks
请问GLM4这边对于超出序列长度的数据是截断还是删除呢
#658 opened Nov 20, 2024 by XCF-Mike
@zRzRzRzRzRzRzR
1
第一轮评估完，训练就停止了
#657 opened Nov 20, 2024 by XHB-ZMM
2 tasks
@zhipuch
2
请问huggingface上提供的模型中的generate_config中的参数是怎么给出的呢？
#656 opened Nov 19, 2024 by samaritan1998
@zhipuch
使用GLM-4V-9B的时候，尽管设置了gen_kwargs = {"do_sample": False,"top_p":None,"temperature":None}，但每次结果还是不一样
#654 opened Nov 16, 2024 by nwym126
1 of 2 tasks
@zhipuch
1
关于网页端推理找不到麦克风
#647 opened Nov 10, 2024 by llh666521
1 of 2 tasks
@zRzRzRzRzRzRzR
输出数据遗漏
#642 opened Nov 6, 2024 by niniwai
@sixsixcoder
1
关于GLM4-9B模型训练过程中的OOMM问题
#641 opened Nov 5, 2024 by XCF-Mike
1 of 2 tasks
@zhipuch
15
推理框架可以加上微软的bitnet.cpp的方式吗
#640 opened Nov 5, 2024 by CoderYiFei
GLM-4-9B-int4模型的输出格式不听从prompt使唤，无论怎么调都不行，非常倔强，有解决方案吗
#636 opened Nov 1, 2024 by bolt163
1 of 2 tasks
@zRzRzRzRzRzRzR
1
GLM4同样出现了CUDA error: device-side assert
#635 opened Nov 1, 2024 by zzk2021
2 tasks
@zRzRzRzRzRzRzR
3
指令微调报错：A decoder-only architecture is being used, but right-padding was detected! For correct generation results, please set padding_side='left' when initializing the tokenizer.
#633 opened Nov 1, 2024 by 1938225289
1 of 2 tasks
@zRzRzRzRzRzRzR @sixsixcoder
4
使用vllm启动glm-4v-9b服务，调用/v1/chat/completions报错
#630 opened Nov 1, 2024 by OliverLiy
1 of 2 tasks
@sixsixcoder
6
工具调用没反应
#627 opened Oct 31, 2024 by sy960923
1 of 2 tasks
@zRzRzRzRzRzRzR
7
使用glm_server.py作为llm服务端，使用agent传输tools工具时，streaming模式并不会流式输出。
#618 opened Oct 30, 2024 by jurnea
1 of 2 tasks
@zRzRzRzRzRzRzR
GLM4-9b-chat 结合 PEFT 中的 Xlora 训练时, 无法从保存点继续恢复训练
#617 opened Oct 29, 2024 by SongHanKen
2 tasks done
@zhipuch
2
我想在jetson agx orin上的ollama跑glm-4v-9b或者是CogVLM2，需要从safetensors转gguf导入到ollama中，用llama.cpp转换，报错。
#616 opened Oct 29, 2024 by GengyuXu
2 tasks
GLM-4V-9B
#614 opened Oct 28, 2024 by Yxj-study
1 of 2 tasks
@zRzRzRzRzRzRzR
1
使用inference.py推理微调后的模型总报这个错：OSError: /tiamat-NAS/boyang/GLM4/gjm/1024/checkpoint-12000 does not appear to have a file named THUDM/glm-4-9b-chat--configuration_chatglm.py. Checkout 'https://huggingface.co//tiamat-NAS/boyang/GLM4/gjm/1024/checkpoint-12000/None' for available files.
#612 opened Oct 27, 2024 by LolerPanda
1 of 2 tasks
@zRzRzRzRzRzRzR
1
glm4-9b-chat和LoRA微调模型merge之后，使用vLLM推理，工具调用功能报错。
#607 opened Oct 24, 2024 by Jimmy-L99
2 tasks done
@zRzRzRzRzRzRzR
14
在使用FUDGE时出现报错：RuntimeError: Error(s) in loading state_dict for Model:
#604 opened Oct 22, 2024 by Enermy
用 openai_api_server.py 运行 glm-4-9b-chat 可能会重复输出
#599 opened Oct 17, 2024 by oubeichen
1 of 2 tasks
@sixsixcoder
7
To Submit a Security Disclosure
#592 opened Oct 16, 2024 by ZihanWangKi
2 tasks
@zRzRzRzRzRzRzR
3
关于许可协议的问题请教（部署模型并基于模型对外提供服务是否需要附带协议）
#584 opened Oct 12, 2024 by fangcun12138
ProTip! Adding no:label will show everything without a label.