lik07/Hercules-Stheno-v1

Full fine-tune vs Locutusque/Llama-3-Hercules-5.0-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

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

2 derivatives checked

• mradermacher/Hercules-Stheno-v1-GGUF: Same weights, converted
• bartowski/Hercules-Stheno-v1-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse