PrimeIntellect/Qwen3-1.7B-Wordle-SFT
Full fine-tune vs PrimeIntellect/Qwen3-1.7B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 100/113, MLP 84/84, Attention 112/112, lm_head 1/1
Full fine-tune vs PrimeIntellect/Qwen3-1.7B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 100/113, MLP 84/84, Attention 112/112, lm_head 1/1