mradermacher/FitCheck-Qwen2.5-VL-Archivist-Base-GGUF

Same weights, converted (fewer layers) vs barryallen16/FitCheck-Qwen3-VL-Archivist-Base. mradermacher/FitCheck-Qwen2.5-VL-Archivist-Base-GGUF matches part of barryallen16/FitCheck-Qwen3-VL-Archivist-Base (310 of its 625 tensors; the rest of barryallen16/FitCheck-Qwen3-VL-Archivist-Base has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/84, Attention 0/112

On the Hub · Downloads on Model Pulse