mradermacher/Qwen2.5-VL-3B-Instruct-heretic-GGUF

Same weights, converted (fewer layers) vs coder3101/Qwen2.5-VL-3B-Instruct-heretic. mradermacher/Qwen2.5-VL-3B-Instruct-heretic-GGUF matches part of coder3101/Qwen2.5-VL-3B-Instruct-heretic (434 of its 824 tensors; the rest of coder3101/Qwen2.5-VL-3B-Instruct-heretic has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 0/252

On the Hub · Downloads on Model Pulse