Gen-Verse/ReasonFlux-F1

Full fine-tune vs deepseek-ai/DeepSeek-R1-Distill-Qwen-32B. Fine-tune: 98% of the weights changed, across 64 of 64 layers.

Tensors changed: Embeddings 0/1, Attention 448/448, MLP 192/192, Norms 127/129, lm_head 1/1

4 derivatives checked

• mradermacher/ReasonFlux-F1-i1-GGUF: Quantization
• mradermacher/ReasonFlux-F1-GGUF: Quantization
• YOYO-AI/DS-R1-Distill-32B-SCE-V2: Full fine-tune
• YOYO-AI/DS-R1-Distill-32B-SCE: Full fine-tune

On the Hub · Downloads on Model Pulse