ChaoticNeutrals/Templar_v1_8B
Full fine-tune vs ChaoticNeutrals/T-900-8B. Fine-tune: 91% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 0/1, Norms 16/65, MLP 93/96, Attention 124/128
3 derivatives checked
- mradermacher/Templar_v1_8B-GGUF: Same weights, converted
- mradermacher/Templar_v1_8B-i1-GGUF: Quantization
- featherless-ai-quants/ChaoticNeutrals-Templar_v1_8B-GGUF: Quantization