codefuse-ai/F2LLM-v2-4B-Preview

Full fine-tune vs Qwen/Qwen3-4B. Fine-tune: 100% of the weights changed, across 36 of 36 layers.

Tensors changed: Embeddings 1/1, Norms 142/145, MLP 108/108, Attention 144/144

1 derivatives checked

• codefuse-ai/F2LLM-v2-4B: Full fine-tune

On the Hub · Downloads on Model Pulse