deepakkr/TinyLlama-1.1B-Instruct-v1.0
Full fine-tune vs TinyLlama/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T. Fine-tune: 100% of the weights changed, across 22 of 22 layers.
Tensors changed: Norms 45/45, MLP 66/66, Attention 88/88
1 derivatives checked
- mradermacher/TinyLlama-1.1B-Instruct-v1.0-GGUF: Same weights, converted