OpenHands LM is built on the foundation of Qwen Coder 2.5 Instruct 32B, leveraging its powerful base capabilities for coding tasks. The model achieves efficiency that approaches much larger models.

OpenHands LM is built on the foundation of Qwen Coder 2.5 Instruct 32B, leveraging its powerful base capabilities for coding tasks. The model achieves efficiency that approaches much larger models. (huggingface.co)
from yogthos@lemmy.ml to technology@lemmy.ml on 01 Apr 2025 18:02
https://lemmy.ml/post/27988592

#technology

threaded - newest

yogthos@lemmy.ml on 01 Apr 2025 20:07 collapse

@davel@lemmy.ml just ran across this model, and it seems to work a lot better than the other ones I’ve tried locally. Seems to be faster as well. One thing I noticed is that it helps to set temperature (which controls randomness) and Top P (which affects variety of output) values to 0 to keep it more focused.