dharun2049/kaveri-stgrpo-0.5b
LoRA-style vs Qwen/Qwen2-0.5B-Instruct. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of q_proj, v_proj changed, in 24 of 24 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 48/168
1 derivatives checked
- dharun2049/Brahmaputra-1: LoRA-style