pytorch/SmolLM3-3B-INT8-INT4

Update README.md

Upload pytorch_model.bin with huggingface_hub

Upload config.json with huggingface_hub

Rename smollm3-3b-INT8-INT4.pte to model.pte

Delete pytorch_model.bin

Delete config.json

Rename smollm3-3b-8da4w.pte to smollm3-3b-INT8-INT4.pte

Update README.md

Update README.md (#1)

Update README.md

Updated metrics

Update README.md

Update README.md

Updated model card

Update README.md

Update README.md

Update README.md

More metrics update

More quality results

Updated with model quality (partial)

Add quant recipe

Upload tokenizer

Upload SmolLM3ForCausalLM

Update README.md

Fix links

Updated model card

Update README.md

Update README.md

Attach ExecuTorch model file and tokenizer to run on-device

initial commit