rinna/deepseek-r1-distill-qwen2.5-bakeneko-32b

Full fine-tune vs Qwen/Qwen2.5-32B. Fine-tune: 100% of the weights changed, across 64 of 64 layers.

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

4 derivatives checked

• mmnga/deepseek-r1-distill-qwen2.5-bakeneko-32b-gguf: Quantization
• featherless-ai-quants/rinna-deepseek-r1-distill-qwen2.5-bakeneko-32b-GGUF: Quantization
• rinna/deepseek-r1-distill-qwen2.5-bakeneko-32b-gguf: Quantization
• mradermacher/deepseek-r1-distill-qwen2.5-bakeneko-32b-GGUF: Quantization

On the Hub · Downloads on Model Pulse