Dampfinchen/Llama-3-8B-Ultra-Instruct-SaltSprinkle

Full fine-tune vs Dampfinchen/Llama-3-8B-Ultra-Instruct. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

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

2 derivatives checked

• mradermacher/Llama-3-8B-Ultra-Instruct-SaltSprinkle-GGUF: Same weights, converted
• featherless-ai-quants/Dampfinchen-Llama-3-8B-Ultra-Instruct-SaltSprinkle-GGUF: Quantization

On the Hub · Downloads on Model Pulse