mehuldamani/hotpot-v2-brier-7b-no-split

Partial fine-tune vs Qwen/Qwen2.5-7B. Partial change: 84% of the weights changed (attention, mlp, norms), in 28 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 51/57, MLP 82/84, Attention 196/196, lm_head 0/1

On the Hub · Downloads on Model Pulse