e-n-v-y/Legion-V2.1-LLaMa-70B-Elarablated-v0.8-hf
LoRA-style vs Tarek07/Legion-V2.1-LLaMa-70B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of k_proj, o_proj, q_proj, v_proj changed, in 30 of 80 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/161, MLP 0/240, Attention 120/320