THUDM / THUDM/slime

About GLM-4.7-Flash

Open
#1,482 10 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
8.5k
Forks
1.3k
Avg merge
5h 36m
Merged PRs (30d)
22

Description

When I was using convert_hf_to_torch_dist.py to convert the format of GLM-4.7-Flash, I encountered an issue.
ValueError: Unregistered model type: glm4_moe_lite. Currently, only the following models are supported: dict_keys(['deepseek_v3', 'llama', 'qwen2', 'mimo', 'mixtral', 'qwen2_5_vl', 'qwen2_moe', 'qwen3', 'qwen3_moe', 'glm4_moe', 'glm4v', 'glm4v_moe', 'gemma3', 'internvl_chat', 'qwen3_vl', 'qwen3_vl_moe', 'glm4', 'qwen3_next'])
It seems that mbridge does not support glm4.7. How did you solve this problem?

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with convert_hf_to_torch_dist.py and the reported ValueError; compare glm4_moe_lite with the model types currently supported by mbridge. Done means confirming a working conversion path for GLM-4.7-Flash or documenting the missing support and its resolution.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.