kalomaze/hex-toolcall-base-v2
Full fine-tune vs EssentialAI/rnj-1-instruct. Fine-tune: 96% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 135/193, MLP 91/96, Attention 128/128
1 derivatives checked
- mradermacher/hex-toolcall-base-v2-GGUF: Same weights, converted