THUDM
/

glm-4-9b-chat

Model card Files Files and versions Community

Resources

View closed (57)

Please upgrade to THUDM/glm-4-9b-chat-hf model.

#86 opened about 1 month ago by

用什么部署，可以像智普API那样传工具，VLLM和Llama.cpp，ollama的，有没有现成的Modelfile？

#85 opened about 1 month ago by

vllm 部署的 glm4 能使用 tool call 吗？

#84 opened about 1 month ago by

Converting to native Transformers

#81 opened 3 months ago by

Adding the Open Portuguese LLM Leaderboard Evaluation Results

#79 opened 3 months ago by

leaderboard-pt-pr-bot

Independent evaluation results

#78 opened 3 months ago by

Fix: AttributeError when `input_ids` is None during multimodal LLM training

#77 opened 3 months ago by

使用 vLLM 部署，无法使用 outlines 做 guided decoding

#75 opened 4 months ago by

Fix https://github.com/huggingface/peft/issues/1974#issue-2437471248

#74 opened 4 months ago by

ollama适配的glm4怎样触发function_call？

#71 opened 5 months ago by

Issue with Submitting Model to Open LLM Leaderboard

#68 opened 5 months ago by

paperplanedeemo

Rag Prompt

#67 opened 5 months ago by

请问如何复现模型介绍界面的经典任务的评估结果？

#62 opened 5 months ago by deleted

请问如何在llm-studio里使用

#61 opened 5 months ago by

del gradient_checkpointing_enable()

#60 opened 6 months ago by

What's the chat prompt in plain string?

#59 opened 6 months ago by

适配新版transformers | adapt transformers update (https://github.com/huggingface/transformers/pull/31116)

#58 opened 6 months ago by

Alternative quantizations.

#57 opened 6 months ago by

Harness Evaluation

#56 opened 6 months ago by

[AUTOMATED] Model Memory Requirements

#55 opened 6 months ago by

model-sizer-bot

Why GLM3 is better than GLM4 on LVEval benchmark?

#48 opened 6 months ago by

请问能否提供工具调用模板？

#42 opened 7 months ago by

模型许可证

#37 opened 7 months ago by

What does "open source" mean? Need info on source code, training data, fine-tuning data

#36 opened 7 months ago by

lobechat不能使用函数和图片功能

#35 opened 7 months ago by

FIX transformers compat

#28 opened 7 months ago by

[ISSUE] forward() requires input_ids even if inputs_embeds is provided alternatively

#23 opened 7 months ago by

FlashAttention only supports Ampere GPUs or newer.

#13 opened 7 months ago by

qunatizer部分的为什么去掉了？

#10 opened 7 months ago by