catallama/CataLlama-v0.1-Base

Full fine-tune vs meta-llama/Meta-Llama-3-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Norms 64/65, MLP 96/96, Attention 128/128

2 derivatives checked

• mradermacher/CataLlama-v0.1-Base-GGUF: Same weights, converted
• catallama/CataLlama-v0.2-Base: Full fine-tune

On the Hub · Downloads on Model Pulse