kkk5/CIM-LLaVA1.5-7B

Full fine-tune vs llava-hf/llava-1.5-7b-hf. Fine-tune: 98% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 3/4, Norms 118/165, MLP 188/192, Attention 311/320, other 4/4, lm_head 1/1

1 derivatives checked

• mradermacher/CIM-LLaVA1.5-7B-GGUF: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse