tbooy/Qwen2.5-3B-Instruct-Sheldon-RLVR-math-v1
LoRA-style vs tbooy/Qwen2.5-3B-Instruct-Sheldon-RLAIF-grpo-v2. 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 36 of 36 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/73, MLP 108/108, Attention 144/252
1 derivatives checked
- tbooy/Qwen2.5-3B-Instruct-Sheldon-RLVR-math-v2-fullft: Full fine-tune