kevinshin
qwen2.5-1.5b-rft-rpo-lr-1e-5-alpha-4-beta-0.5-wc-cw-3k-neg-rethink-pos
Available on FriendliAI
Dedicated Endpoints
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
kevinshin
Model Tree
Base
kevinshin/qwen2.5-1.5b-it-think-rft-lr-1e-5-batch-16-epoch-1-wildchat-cw-3k
Fine-tuned
this model
Input Modalities
Text
Output Modalities
Text
Supported Functionality
Dedicated Endpoints