mradermacher/LLaVA-Critic-R1-7B-Plus-Mimo-GGUF

Same weights, converted (fewer layers) vs lmms-lab/LLaVA-Critic-R1-7B-Plus-Mimo. mradermacher/LLaVA-Critic-R1-7B-Plus-Mimo-GGUF matches part of lmms-lab/LLaVA-Critic-R1-7B-Plus-Mimo (435 of its 825 tensors; the rest of lmms-lab/LLaVA-Critic-R1-7B-Plus-Mimo has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: MLP 0/108, Attention 0/252, Norms 0/73, lm_head 0/1, Embeddings 0/1

On the Hub · Downloads on Model Pulse