kawchar85/SmolLM2-1.7B-Instruct-TIFA-Random

Full fine-tune vs unsloth/SmolLM2-1.7B-Instruct. Fine-tune: 94% of the weights changed, across 24 of 24 layers.

Tensors changed: Embeddings 0/1, Norms 4/49, MLP 72/72, Attention 96/96

1 derivatives checked

• mradermacher/SmolLM2-1.7B-Instruct-TIFA-Random-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse