unsloth/llava-1.5-7b-hf

Same weights, converted vs llava-hf/llava-1.5-7b-hf. Same weights stored in another dtype (F16 → BF16).

Tensors changed: Embeddings 0/4, Norms 0/165, MLP 0/192, Attention 0/320, other 0/4, lm_head 0/1

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

On the Hub · Downloads on Model Pulse