Aiden0526
/

LogicReward-Qwen3-8B

Text Generation

instruction-tuning

Model card Files Files and versions

Improve model card: fix metadata, add pipeline tag and library name

#1

by nielsr HF Staff - opened Jan 30

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

Jan 30

Hi! This PR improves the model card for the LogicReward adapter:

Corrects the base_model from Llama to Qwen/Qwen3-8B.
Adds pipeline_tag: text-generation for better discoverability.
Updates library_name to peft since this is a LoRA adapter.
Adjusts tags to remove Llama-specific terms and include qwen.
Links the model to its official Hugging Face paper page.
Sets the license to apache-2.0 consistent with the base Qwen model.

Improve model card: fix metadata, add pipeline tag and library name3a57d052

Aiden0526 changed pull request status to merged Jan 31

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment