Fu01978/SmollerLM2-360M-Instruct-Pruned

Same weights, converted vs HuggingFaceTB/SmolLM2-360M-Instruct. Same weights stored in another dtype (BF16 → F16).

Tensors changed: Embeddings 0/1, Norms 0/65, Attention 0/128

2 derivatives checked

• mradermacher/SmollerLM2-360M-Instruct-Pruned-i1-GGUF: Quantization
• mradermacher/SmollerLM2-360M-Instruct-Pruned-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse