saucam/aqua-smaug-0.2-8B

Full fine-tune vs abacusai/Llama-3-Smaug-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

1 derivatives checked

• mradermacher/aqua-smaug-0.2-8B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse