metadata
base_model: unsloth/qwen2.5-coder-32b-instruct-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
- gguf
license: apache-2.0
language:
- en
datasets:
- xingyaoww/opendevin-code-act
Summary
The model userxxx/openhands-qwen-coder-32b is a fine-tuned version of qwen2.5-coder-32b, specifically tailored for the Swe Agent OpenHands. It delivers impressive performance, sometimes nearly rivaling that of Sonnet 3.5. However, certain limitations persist, particularly with function calling for IPython/Jupyter commands like INSERT and STR_REPLACE, which currently do not work. Aside from these issues, the model performs effectively in most other tasks.
Recommended Usage
To achieve optimal results, it is recommended to use this model via LM Studio.
Steps to Set Up LM Studio:
- Open LM Studio.
- Go to the Local Server tab.
- Click the "Start Server" button.
- Copy qwencoder32openhands-beta-q4-k-m.gguf inside the LmStudio Model Folder and than select it.
- Ensure the context window exceeds 4000 tokens
OpenHands Settings
For WSL, run the following commands to set up the networking mode to mirrored:
python -c "print('[wsl2]\nnetworkingMode=mirrored',file=open(r'%UserProfile%\.wslconfig','w'))"
wsl --shutdown
Setting inside Openhands
openai/lmstudio http://host.docker.internal:1234/v1