mradermacher/Caption3o-XL-2B-Qwen2VL-GGUF

Same weights, converted (fewer layers) vs prithivMLmods/Caption3o-XL-2B-Qwen2VL. mradermacher/Caption3o-XL-2B-Qwen2VL-GGUF matches part of prithivMLmods/Caption3o-XL-2B-Qwen2VL (338 of its 729 tensors; the rest of prithivMLmods/Caption3o-XL-2B-Qwen2VL has no counterpart). On the shared part: Same weights stored in another dtype (F16 → F16/F32).

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

On the Hub · Downloads on Model Pulse