mradermacher/typhoon2-qwen2vl-7b-vision-instruct-GGUF

Same weights, converted (fewer layers) vs typhoon-ai/typhoon2-qwen2vl-7b-vision-instruct. mradermacher/typhoon2-qwen2vl-7b-vision-instruct-GGUF matches part of typhoon-ai/typhoon2-qwen2vl-7b-vision-instruct (339 of its 730 tensors; the rest of typhoon-ai/typhoon2-qwen2vl-7b-vision-instruct has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

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

On the Hub · Downloads on Model Pulse