TheDrummer/Valkyrie-49B-v2
LoRA-style vs nvidia/Llama-3_3-Nemotron-Super-49B-v1_5. 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 80 of 80 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/130, MLP 240/240, Attention 196/196, lm_head 0/1
4 derivatives checked
- bartowski/TheDrummer_Valkyrie-49B-v2-GGUF: Same weights, converted
- mradermacher/Valkyrie-49B-v2-i1-GGUF: Quantization
- mradermacher/Valkyrie-49B-v2-GGUF: Quantization
- Green-eyedDevil/Monika-49B: LoRA-style