mradermacher/Qwen2.5-VL-7B-RLVR-ReasoningOnly-ThinkLite-GGUF

Same weights, converted (fewer layers) vs vgandhi13/Qwen2.5-VL-7B-RLVR-ReasoningOnly-ThinkLite. mradermacher/Qwen2.5-VL-7B-RLVR-ReasoningOnly-ThinkLite-GGUF matches part of vgandhi13/Qwen2.5-VL-7B-RLVR-ReasoningOnly-ThinkLite (339 of its 729 tensors; the rest of vgandhi13/Qwen2.5-VL-7B-RLVR-ReasoningOnly-ThinkLite has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

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

On the Hub · Downloads on Model Pulse