lwl-uestc/QFFT-S1-7B

Full fine-tune vs Qwen/Qwen2.5-7B-Instruct. Fine-tune: 93% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 54/57, MLP 84/84, Attention 196/196, lm_head 1/1

3 derivatives checked

• mradermacher/QFFT-S1-7B-i1-GGUF: Quantization
• mradermacher/QFFT-S1-7B-GGUF: Same weights, converted
• mradermacher/s1.1_7b_QFD-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse