voidful/Llama-3.1-TAIDE-R1-8B-Chat

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: Attention 128/128, MLP 96/96, Norms 65/65

1 derivatives checked

• MaziyarPanahi/Llama-3.1-TAIDE-R1-8B-Chat-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse