nvidia/NFT-7B

Full fine-tune vs Qwen/Qwen2.5-Math-7B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 1/1, Norms 54/57, MLP 84/84, Attention 196/196, lm_head 1/1

3 derivatives checked

• gabriellarson/NFT-7B-GGUF: Quantization
• mradermacher/NFT-7B-i1-GGUF: Quantization
• mradermacher/NFT-7B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse