UCSC-VLAA/STAR1-R1-Distill-14B

Full fine-tune vs deepseek-ai/DeepSeek-R1-Distill-Qwen-14B. Fine-tune: 95% of the weights changed, across 48 of 48 layers.

Tensors changed: Embeddings 0/1, Attention 336/336, MLP 144/144, Norms 94/97, lm_head 1/1

2 derivatives checked

• mradermacher/STAR1-R1-Distill-14B-i1-GGUF: Quantization
• mradermacher/STAR1-R1-Distill-14B-GGUF: Quantization

On the Hub · Downloads on Model Pulse