nicholasKluge/TeenyTinyLlama-460m-Chat

Full fine-tune vs nicholasKluge/TeenyTinyLlama-460m. Fine-tune: 100% of the weights changed, across 24 of 24 layers.

Tensors changed: Norms 49/49, MLP 72/72, Attention 96/96

2 derivatives checked

• afrideva/TeenyTinyLlama-460m-Chat-GGUF: Same weights, converted
• tensorblock/TeenyTinyLlama-460m-Chat-GGUF: Quantization

On the Hub · Downloads on Model Pulse