benni-ben/SmolBabble-360m

Full fine-tune vs HuggingFaceTB/SmolLM-360M. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128

1 derivatives checked

• mradermacher/SmolBabble-360m-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse