catallama/CataLlama-v0.2-Base
Full fine-tune vs catallama/CataLlama-v0.1-Base. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 65/65, MLP 96/96, Attention 128/128
2 derivatives checked
- mradermacher/CataLlama-v0.2-Base-GGUF: Same weights, converted
- catallama/CataLlama-v0.2-Instruct-SFT: Full fine-tune
1 other repos hold byte-for-byte identical weight files.