mradermacher/CIM-LLaVA1.5-7B-GGUF

Same weights, converted (fewer layers) vs kkk5/CIM-LLaVA1.5-7B. mradermacher/CIM-LLaVA1.5-7B-GGUF matches part of kkk5/CIM-LLaVA1.5-7B (291 of its 686 tensors; the rest of kkk5/CIM-LLaVA1.5-7B has no counterpart). On the shared part: Same weights stored in another dtype (F32 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128, lm_head 0/1

On the Hub · Downloads on Model Pulse