OpenDataArena/ODA-Fin-SFT-8B

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

Tensors changed: Embeddings 0/1, Norms 132/145, MLP 108/108, Attention 144/144, lm_head 1/1

2 derivatives checked

• mradermacher/ODA-Fin-SFT-8B-GGUF: Same weights, converted
• OpenDataArena/ODA-Fin-RL-8B: Partial fine-tune

On the Hub · Downloads on Model Pulse