mradermacher/Qwen2.5-VL-7B-MM-UPT-MMR1-GGUF

Same weights, converted (fewer layers) vs WaltonFuture/Qwen2.5-VL-7B-MM-UPT-MMR1. mradermacher/Qwen2.5-VL-7B-MM-UPT-MMR1-GGUF matches part of WaltonFuture/Qwen2.5-VL-7B-MM-UPT-MMR1 (339 of its 729 tensors; the rest of WaltonFuture/Qwen2.5-VL-7B-MM-UPT-MMR1 has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

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

On the Hub · Downloads on Model Pulse