RUC-AIBOX/STILL-2

Full fine-tune vs Qwen/Qwen2.5-32B-Instruct. Fine-tune: 98% of the weights changed, across 64 of 64 layers.

Tensors changed: Embeddings 0/1, Norms 125/129, MLP 192/192, Attention 448/448, lm_head 1/1

3 derivatives checked

• featherless-ai-quants/RUC-AIBOX-STILL-2-GGUF: Quantization
• mradermacher/STILL-2-i1-GGUF: Quantization
• mradermacher/STILL-2-GGUF: Quantization

On the Hub · Downloads on Model Pulse