VladShash/qwen3-8b-feedback-with-repair-distilled

Partial fine-tune vs formalmathatepfl/qwen3-8b-feedback-with-repair. Partial change: 85% of the weights changed (attention, mlp, norms), in 36 of 36 layers.

Tensors changed: Embeddings 0/1, Norms 111/145, MLP 108/108, Attention 144/144, lm_head 0/1

On the Hub · Downloads on Model Pulse