WPS-Qingqiu/Qingqiu-MT-9B

Full fine-tune vs Qwen/Qwen3.5-9B. Fine-tune: 95% of the weights changed, across 32 of 32 layers.

Tensors changed: lm_head 1/1, Embeddings 1/4, MLP 96/208, Attention 205/332, Norms 85/215

2 derivatives checked

• mradermacher/Qingqiu-MT-9B-i1-GGUF: Quantization
• mradermacher/Qingqiu-MT-9B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse