Gen-Verse/ReasonFlux-F1-14B
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 95/97, lm_head 1/1
5 derivatives checked
- mradermacher/ReasonFlux-F1-14B-i1-GGUF: Quantization
- mradermacher/ReasonFlux-F1-14B-GGUF: Quantization
- YOYO-AI/YOYO-O1-14B: Full fine-tune
- mergekit-community/mergekit-sce-sudfgqi: Full fine-tune
- YOYO-AI/Qwen2.5-14B-YOYO-stock: Full fine-tune