Hugging Face's logo
zR's picture
168 4

zR

zRzRzRzRzRzRzR
roseking's profile picture dibmvt's profile picture viralvector's profile picture
·
https://github.com/zRzRzRzRzRzRzR

AI & ML interests

LLM & Agent

Organizations

Knowledge Engineering Group (KEG) & Data Mining at Tsinghua University's profile picture

zRzRzRzRzRzRzR's activity

New activity in THUDM/glm-4-9b-chat about 1 hour ago

KeyError: 'sop'

2
#52 opened 26 days ago by Culbertson
New activity in THUDM/cogvlm2-video-llama3-chat 1 day ago

When torch.nn.functional.scaled_dot_product_attention calls _scaled_dot_product_attention_math, the model reports an error

4
#3 opened 1 day ago by Quasimodo0808
New activity in THUDM/glm-4-9b 1 day ago

UnicodeDecodeError: 'utf-8' codec can't decode bytes in position 0-1: unexpected end of data

4
#10 opened 10 days ago by ixioxoixi
New activity in THUDM/glm-4-9b-chat-1m 1 day ago

model.generate cannot handle past_key_values correctly

3
#13 opened 2 days ago by Zhuangl
New activity in THUDM/glm-4-9b-chat 2 days ago

modeling_chatglm.py这个文件，新版4.42.4里面，是不是删除了stream_chat相关的函数，导致不能流式输出了呢

2
#66 opened 3 days ago by strange007

官方模型加载错误

11
#65 opened 4 days ago by xfs1990
New activity in THUDM/glm-4-9b-chat 3 days ago

TypeError: GenerationMixin._get_logits_warper() missing 1 required positional argument: 'device'

3
#64 opened 5 days ago by strange007
New activity in THUDM/codegeex4-all-9b 4 days ago

代码补全效果咨询

4
#13 opened 4 days ago by xtuxiongda
New activity in THUDM/glm-4-9b-chat 4 days ago

transformers4.42.3版本，使用opencompass评估报错

1
#63 opened 5 days ago by amaing1
New activity in THUDM/glm-4v-9b 6 days ago

模型推理脚本报错

4
#29 opened 8 days ago by Jay0324

context length?

1
#31 opened 8 days ago by catworld1212
New activity in THUDM/cogvlm2-llama3-chinese-chat-19B-int4 6 days ago

Unused kwargs: ['_load_in_4bit', '_load_in_8bit', 'quant_method']. These kwargs are not used in <class 'transformers.utils.quantization_config.BitsAndBytesConfig'>.

1
#2 opened 8 days ago by chuangzhidian
New activity in THUDM/glm-4v-9b 8 days ago

运行到apply_chat_template时报错KeyError

5
#22 opened about 1 month ago by FearandDreams

A100爆显存

3
#28 opened 14 days ago by baiall
New activity in THUDM/codegeex4-all-9b 9 days ago

较复杂sql任务发现比较差，对提示词不太敏感

5
#5 opened 10 days ago by chuangzhidian

请问指令微调的数据格式和glm4-9b-chat一致么？

2
#2 opened 12 days ago by yuezhiyu

Delete model-00001-of-00004.safetensors
#9 opened 9 days ago by Subbi8

Delete model-00002-of-00004.safetensors
#8 opened 9 days ago by Subbi8

Delete model-00001-of-00004.safetensors
#7 opened 9 days ago by Subbi8
New activity in THUDM/glm-4-9b-chat 9 days ago

del gradient_checkpointing_enable()

1
#60 opened 9 days ago by chandler88
New activity in THUDM/glm-4-9b-chat 10 days ago

ETA for Flash Attention 2.0 Support in ChatGLMForConditionalGeneration

1
#46 opened about 1 month ago by frank098

huggingface_hub.utils._errors.FileMetadataError: Distant resource does not have a Content-Length.

1
#49 opened 30 days ago by alxemade
New activity in THUDM/cogvlm-grounding-generalist-hf 10 days ago

Can this grounding model output bbox?

3
#3 opened 7 months ago by xxheyu
New activity in THUDM/glm-4-9b-chat 10 days ago

What's the chat prompt in plain string?

2
#59 opened 12 days ago by apepkuss79
New activity in THUDM/glm-4v-9b 10 days ago

glm-4v-9b自己call forward的时候cuda out of memory

13
#25 opened 27 days ago by FearandDreams
New activity in THUDM/glm-4-9b-chat 10 days ago

希望提供gguf版本

15
#17 opened about 1 month ago by windkkk
New activity in THUDM/glm-4-9b 11 days ago

推理代码报错 ValueError: too many values to unpack (expected 2)

1
#9 opened 11 days ago by qth-szu
New activity in THUDM/glm-4v-9b 13 days ago

Using `low_cpu_mem_usage=True` or a `device_map` requires Accelerate: `pip install accelerate`

2
#27 opened 14 days ago by mdeniz1
New activity in THUDM/glm-4-9b-chat 15 days ago

Harness Evaluation

2
#56 opened 19 days ago by VityaVitalich
New activity in THUDM/cogvlm2-llama3-chinese-chat-19B 16 days ago

运行实例报错

1
#5 opened 16 days ago by kklots
New activity in THUDM/glm-4-9b-chat-1m 17 days ago

Hitting exception when trying to run stock demo for THUDM/glm-4-9b-chat-1m

6
#12 opened 18 days ago by LukaBloomRox
New activity in THUDM/glm-4-9b-chat 24 days ago

How to use function call

5
#53 opened 25 days ago by JunePan
New activity in THUDM/glm-4-9b 25 days ago

AttributeError: module 'transformers_modules.GLM-4-9B.tokenization_chatglm' has no attribute 'ChatGLM4Tokenizer'

3
#8 opened 25 days ago by wangrenzhong
New activity in THUDM/glm-4-9b-chat 25 days ago

chat_template.jinja

5
#39 opened about 1 month ago by YuboWang
New activity in THUDM/glm-4-9b-chat 28 days ago

PanicException: index out of bounds: the len is 1 but the index is 1

1
#44 opened about 1 month ago by Moutsea
New activity in THUDM/glm-4v-9b 30 days ago

glm-4v-9b model by Gradio

3
#20 opened about 1 month ago by lele12306
New activity in THUDM/glm-4-9b 30 days ago

可以出个gguf的版本吗？想本地部署测试

1
#6 opened about 1 month ago by nardoo
New activity in THUDM/glm-4v-9b 30 days ago

在实际应用场景中，还可能会只做文本问答，不需要输入图片，这种场景是否可以满足？

6
#23 opened about 1 month ago by jackleef

我想问一下，我照着你提供脚本运行模型，为什么加载到百分之20就自己退了

2
#3 opened about 2 months ago by praymich
New activity in THUDM/glm-4-9b-chat about 1 month ago

add chat_template

13
#31 opened about 1 month ago by jinmingyi

safetensors_rust.SafetensorError: Error while deserializing header: MetadataIncompleteBuffer

1
#33 opened about 1 month ago by Twilightsh

除了用vLLM还有哪些方式可以本地部署？
#34 opened about 1 month ago by leo009
New activity in THUDM/glm-4-9b about 1 month ago

Fix tensor shape error
#7 opened about 1 month ago by hiyouga
New activity in THUDM/cogvlm2-llama3-chat-19B about 1 month ago

是否会支持提供chat函数支持默认的chat template

1
#8 opened about 2 months ago by william0014

About extracting embedding vectors of images and texts.

1
#10 opened about 1 month ago by iceleaf97tech
New activity in THUDM/glm-4-9b-chat about 1 month ago

KeyError: '<|endoftext|>'报错怎么解决？

3
#41 opened about 1 month ago by jackleef
New activity in THUDM/glm-4-9b-chat-1m about 1 month ago

Update tokenization_chatglm.py
#3 opened about 1 month ago by ksuriuri
New activity in THUDM/glm-4-9b-chat about 1 month ago

使用opendevin时，指定llm使用glm-4，让他执行代码给我说它是openai

1
#29 opened about 1 month ago by goofy-z

回答中英混合

5
#15 opened about 1 month ago by weiminw

GLM4理解生成问题

1
#43 opened about 1 month ago by dqqAAA

Update tokenization_chatglm.py
#7 opened about 1 month ago by ksuriuri
New activity in THUDM/glm-4v-9b about 1 month ago

有出量化模型INT4的计划吗

1
#21 opened about 1 month ago by Winkuis
New activity in THUDM/glm-4-9b-chat about 1 month ago

ollama 目前还不支持该模型吗

1
#45 opened about 1 month ago by osirissword

disable `torch.jit` when using Ascend NPUs

1
#20 opened about 1 month ago by statelesshz
New activity in THUDM/glm-4v-9b about 1 month ago

执行Model card中的代码出错

5
#14 opened about 1 month ago by zhaoyang0618
New activity in THUDM/glm-4-9b-chat about 1 month ago

requirements.txt

1
#40 opened about 1 month ago by lifelongwar

效果很差

1
#12 opened about 1 month ago by Junity

How do I resolve this bug? I tried to create a GLM-4 interface using Streamlit, and encountered this issue when running streamlit run.

1
#32 opened about 1 month ago by Elizaaaaaaa
New activity in THUDM/glm-4v-9b about 1 month ago

脚本貌似跑不起来，会报错

7
#5 opened about 1 month ago by haonanzhang

How many images can be inputted into the model?

2
#12 opened about 1 month ago by FrederickPi