wjbmattingly/nara-qwen-3.5-0.8b

Full fine-tune vs Qwen/Qwen3.5-0.8B. Fine-tune: 100% of the weights changed, across 24 of 24 layers.

Tensors changed: Attention 184/216, Norms 66/129, Embeddings 4/4, MLP 120/124

1 derivatives checked

• mradermacher/nara-qwen-3.5-0.8b-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse