liangzhidanta/Qwen3-8B-CC-SFT-v2

Full fine-tune vs liangzhidanta/Qwen3-8B-CC-SFT-v1. Fine-tune: 92% of the weights changed, across 36 of 36 layers.

Tensors changed: Norms 115/145, MLP 108/108, Attention 144/144, Embeddings 0/1, lm_head 1/1

1 derivatives checked

• liangzhidanta/Qwen3-8B-CC-SFT-v2-2e: Full fine-tune

On the Hub · Downloads on Model Pulse