Bingguang/FunReason-MT

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 131/145, MLP 108/108, Attention 144/144

2 derivatives checked

• mradermacher/FunReason-MT-GGUF: Same weights, converted
• bunnycore/Qwen3-4B-Mini-Merge: Full fine-tune

On the Hub · Downloads on Model Pulse