mradermacher/ottoman-ocr-qwen2.5-vl-7b-GGUF

Same weights, converted (fewer layers) vs kranidiotis/ottoman-ocr-qwen2.5-vl-7b. mradermacher/ottoman-ocr-qwen2.5-vl-7b-GGUF matches part of kranidiotis/ottoman-ocr-qwen2.5-vl-7b (339 of its 730 tensors; the rest of kranidiotis/ottoman-ocr-qwen2.5-vl-7b 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