grimjim/SauerHuatuoSkyworkDeepWatt-o1-Llama-3.1-8B

Full fine-tune vs deepseek-ai/DeepSeek-R1-Distill-Llama-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Attention 128/128, MLP 96/96, Norms 65/65, lm_head 1/1

2 derivatives checked

• mradermacher/SauerHuatuoSkyworkDeepWatt-o1-Llama-3.1-8B-i1-GGUF: Quantization
• mradermacher/SauerHuatuoSkyworkDeepWatt-o1-Llama-3.1-8B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse