ArRENCEAI/pythia-2.8b-OBLITERATED
LoRA-style vs EleutherAI/pythia-2.8b. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of dense, dense_4h_to_h, dense_h_to_4h, query_key_value changed, in 30 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/130, Attention 60/128, MLP 60/128