Ppoyaa/MythoNemo-L3.1-70B-v1.0

LoRA-style vs nvidia/Llama-3.1-Nemotron-70B-Instruct-HF. 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 0/161, MLP 236/240, Attention 304/320, lm_head 0/1

2 derivatives checked

On the Hub · Downloads on Model Pulse