mradermacher/ThinkLite-Critic-7b-i1-GGUF

Quantization (fewer layers) vs lmms-lab/LLaVA-Critic-R1-7B-Plus-Qwen. mradermacher/ThinkLite-Critic-7b-i1-GGUF matches part of lmms-lab/LLaVA-Critic-R1-7B-Plus-Qwen (339 of its 729 tensors; the rest of lmms-lab/LLaVA-Critic-R1-7B-Plus-Qwen has no counterpart). On the shared part: mradermacher/ThinkLite-Critic-7b-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 141 tensors match exactly and 198 within quantization error.

Tensors changed: MLP 0/84, Attention 0/196, Norms 0/57, lm_head 0/1, Embeddings 0/1

On the Hub · Downloads on Model Pulse