NexaAI/DeepSeek-R1-Distill-Llama-8B-NexaQuant

Full fine-tune vs deepseek-ai/DeepSeek-R1-Distill-Llama-8B. NexaAI/DeepSeek-R1-Distill-Llama-8B-NexaQuant is a GGUF (Q4_0/F16) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Attention 128/128, MLP 96/96, Norms 42/65, lm_head 1/1

On the Hub · Downloads on Model Pulse