chaoyinshe/EchoVLM_V2_lingshu_base_7b_instruct_preview

Partial fine-tune vs lingshu-medical-mllm/Lingshu-7B. Partial change: 87% of the weights changed (attention, mlp), in 32 of 32 layers.

Tensors changed: Embeddings 0/2, Norms 0/122, MLP 184/280, Attention 176/324, lm_head 0/1

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse