TiGa-RCE/SmolLM2-360M-OBLITERATED

Partial fine-tune vs HuggingFaceTB/SmolLM2-360M. Partial change: 29% of the weights changed (attention, embeddings, mlp), in 6 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 0/65, MLP 18/96, Attention 24/128

1 derivatives checked

• mradermacher/SmolLM2-360M-OBLITERATED-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse