prithivMLmods/Calme-Ties-78B
LoRA-style vs MaziyarPanahi/calme-3.2-instruct-78b. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 36 of 86 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/173, MLP 16/258, Attention 27/602
2 derivatives checked
- mradermacher/Calme-Ties-78B-i1-GGUF: Quantization
- mradermacher/Calme-Ties-78B-GGUF: Quantization