PrimeIntellect/Qwen3-0.6B-Reverse-Text-SFT-untied
Full fine-tune vs PrimeIntellect/Qwen3-0.6B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 98/113, MLP 84/84, Attention 112/112
Full fine-tune vs PrimeIntellect/Qwen3-0.6B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 98/113, MLP 84/84, Attention 112/112