Fix: add GGUF cross-reference for 32K variant in How to Choose

Update model card: add smol-tools family table with 16k/32k cross-references

Upload tokenizer_config.json with huggingface_hub

Upload chat_template.jinja with huggingface_hub

Upload tokenizer_config.json with huggingface_hub

Upload config.json with huggingface_hub

Upload model.safetensors with huggingface_hub

Upload README.md with huggingface_hub

Delete chat_template.jinja with huggingface_hub

Upload tokenizer_config.json with huggingface_hub

Upload config.json with huggingface_hub

Upload model.safetensors with huggingface_hub

Delete tokenizer_config.json with huggingface_hub

Delete config.json with huggingface_hub

Delete model.safetensors with huggingface_hub

Delete preprocessor_config.json with huggingface_hub

Add when-to-use and when-not-to-use sections to model card

Add model card

Upload smol-tools-4b merged model (F1=0.955, 100% JSON validity)

initial commit