DevQuasar/Alibaba-NLP.gme-Qwen2-VL-2B-Instruct-GGUF

Same weights, converted (fewer layers) vs Alibaba-NLP/gme-Qwen2-VL-2B-Instruct. DevQuasar/Alibaba-NLP.gme-Qwen2-VL-2B-Instruct-GGUF matches part of Alibaba-NLP/gme-Qwen2-VL-2B-Instruct (338 of its 729 tensors; the rest of Alibaba-NLP/gme-Qwen2-VL-2B-Instruct has no counterpart). On the shared part: Same weights stored in another dtype (F32 → F16/F32).

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

On the Hub · Downloads on Model Pulse