RedHatAI/Sparse-Llama-3.1-8B-ultrachat_200k-2of4

Full fine-tune vs RedHatAI/Sparse-Llama-3.1-8B-2of4. Fine-tune: 93% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1

2 derivatives checked

• featherless-ai-quants/neuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-GGUF: Quantization
• DevQuasar-5/neuralmagic.Sparse-Llama-3.1-8B-ultrachat_200k-2of4-GGUF: Quantization

On the Hub · Downloads on Model Pulse