unclemusclez/SmolLM-135M-Instruct-DEVINator-v0.1

Same weights, converted vs HuggingFaceTB/SmolLM-135M-Instruct. Same weights stored in another dtype (BF16 → F16).

Tensors changed: Embeddings 0/1, Norms 0/61, MLP 0/90, Attention 0/120

3 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse