🦆DuckWeights

Mirrors only permissively licensed, ungated models. Weights are served content-addressed from R2.

BillyWang1/qwen3-4b-instruct-2507-retool-grpo

text-generationsafetensorsqwen3reinforcement-learninggrpotool-usecode-interpreter

License: apache-2.0
Size: not mirrored yet

Cataloged from BillyWang1/qwen3-4b-instruct-2507-retool-grpo

This model has no card.

BillyWang1/qwen3-4b-instruct-2507-retool-grpo · DuckWeights

Downloads in the last 30 days

0 / 30 days