mradermacher/OpenVLThinker-7B-GGUF

Same weights, converted (fewer layers) vs ydeng9/OpenVLThinker-7B. mradermacher/OpenVLThinker-7B-GGUF matches part of ydeng9/OpenVLThinker-7B (339 of its 729 tensors; the rest of ydeng9/OpenVLThinker-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, Attention 0/196, MLP 0/84, Norms 0/57

On the Hub · Downloads on Model Pulse