mradermacher/SmolLM-135M-Instruct-layer-pruned-90M-raw-GGUF

Same weights, converted vs Trelis/SmolLM-135M-Instruct-layer-pruned-90M-raw. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/41, MLP 0/60, Attention 0/80

On the Hub · Downloads on Model Pulse