SeanWang0027/qwen3-1.7b-sciworld-rose-s10t5-gpt54mini-3ep

Partial fine-tune vs Qwen/Qwen3-1.7B. Partial change: 69% of the weights changed (attention, mlp, norms), in 28 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 85/113, MLP 84/84, Attention 112/112, lm_head 0/1

On the Hub · Downloads on Model Pulse