HuggingFaceTB
/

SmolLM2-1.7B-Instruct

Text Generation

Transformers.js

text-generation-inference

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

SmolLM2-1.7B-Instruct / onnx

Commit History

Fix q8 weights (use uint8 for q8; int8 produces poor results)

4f13109
verified

Xenova HF staff commited on Nov 26, 2024

Upload folder using huggingface_hub

0919b6c
verified

Xenova HF staff commited on Nov 26, 2024

Upload fixed q8 ONNX models (reduce_range=True, per_channel=True)

06633a3
verified

Xenova HF staff commited on Nov 26, 2024

Upload optimized ONNX weights (deduplicated) (#17)

b36fc77
verified

Xenova HF staff commited on Nov 26, 2024

Upload ONNX weights (#1)

84e8f3e
verified

eliebak HF staff

Xenova HF staff commited on Oct 31, 2024