TheDrummer/Endurance-100B-v1
LoRA-style vs TheDrummer/Lazarus-2407-100B. 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 72 of 72 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/145, MLP 216/216, Attention 288/288
2 derivatives checked
- bartowski/Endurance-100B-v1-GGUF: Quantization
- mradermacher/Endurance-100B-v1-i1-GGUF: Quantization