BEE-spoke-data/TinyLlama-3T-1.1bee

Full fine-tune vs TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T. Fine-tune: 100% of the weights changed, across 22 of 22 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 24/45, MLP 66/66, Attention 88/88

1 derivatives checked

• afrideva/TinyLlama-3T-1.1bee-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse