Mohamed132411/Qwen3-4B-FitGPT-AR-EN-Instruct

Full fine-tune vs Qwen/Qwen3-4B-Instruct-2507. Fine-tune: 100% of the weights changed, across 36 of 36 layers.

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

1 derivatives checked

• mradermacher/Qwen3-4B-FitGPT-AR-EN-Instruct-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse