Thrillcrazyer/Qwen3_1.7B_LoopUS
Full fine-tune vs Qwen/Qwen3-1.7B-Base. Fine-tune: 100% of the weights changed, across 25 of 25 layers.
Tensors changed: Embeddings 1/1, Norms 101/101, MLP 75/75, Attention 100/100
Full fine-tune vs Qwen/Qwen3-1.7B-Base. Fine-tune: 100% of the weights changed, across 25 of 25 layers.
Tensors changed: Embeddings 1/1, Norms 101/101, MLP 75/75, Attention 100/100