karakuri-ai/karakuri-vl-32b-thinking-2507-exp
Full fine-tune vs karakuri-ai/karakuri-vl-32b-instruct-2507. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 2/2, Norms 194/194, MLP 388/388, Attention 576/576, lm_head 1/1
3 derivatives checked
- mradermacher/karakuri-vl-32b-thinking-2507-exp-i1-GGUF: Quantization (fewer layers)
- mradermacher/karakuri-vl-32b-thinking-2507-exp-GGUF: Quantization (fewer layers)
- mmnga/karakuri-vl-32b-thinking-2507-exp-gguf: Quantization (fewer layers)