TheDrummer/Behemoth-R1-123B-v2
Full fine-tune vs mistralai/Mistral-Large-Instruct-2411. Fine-tune: 100% of the weights changed, across 88 of 88 layers.
Tensors changed: Embeddings 1/1, Norms 14/177, MLP 264/264, Attention 352/352, lm_head 0/1
4 derivatives checked
- bartowski/TheDrummer_Behemoth-R1-123B-v2-GGUF: Quantization
- mradermacher/Behemoth-R1-123B-v2-i1-GGUF: Quantization
- tacodevs/Behemoth-T1-123B: LoRA-style
- tacodevs/Behemoth-X-R1-123B: LoRA-style