SmolLM2-135M (ONNX, mirror)

Source: onnx-community/SmolLM2-135M-ONNX, an ONNX version of HuggingFaceTB/SmolLM2-135M by Hugging Face TB.

Conversion: none here. Every file is copied unchanged from onnx-community/SmolLM2-135M-ONNX at revision d0ae6834f1df45e0e95b5fdae95e536f9ca7cd3f, which was converted with the onnx-community conversion space. Only the files the app loads are included: the int8 build (onnx/model_int8.onnx) and the fp32 build (onnx/model.onnx with its external data onnx/model.onnx_data), plus config and tokenizer files. SHA-256 values were checked against the source repository.

This repository exists for in-browser demos with Transformers.js 4.3.2 (an educational app that compares base, SFT and SFT + DPO versions of SmolLM2-135M side by side). Language: English. The model can produce inaccurate or made-up text.

Licence: Apache 2.0, as HuggingFaceTB/SmolLM2-135M. All credit for the model goes to its authors.

File Bytes SHA-256
config.json 1,035 2c5f23fddabecdf9c47d0048f555899822ec87ec4a28169393840ac7e74192c4
generation_config.json 116 8e3a8ff6f89c519e9c88f8da84425fb9cc88f99d45f99ead478fff9b3692f48d
tokenizer.json 2,053,526 139d2f4b4919b90953bdd3c0c40c94c9b23074799a766508dc3bf5eb8ab73351
tokenizer_config.json 3,687 b5d746195c39b6aa173e7f70baf01eae62d26873a27d48ae0b62b4d99d4b9fbd
onnx/model_int8.onnx 135,658,354 50ba80511ce74634d232a043b6c37775cca756b826b49d0a4a8eff958c4bbcc9
onnx/model.onnx 199,002 de4f7dbed6420825147b1fd97d7ea000042ad667ce30316bedd87a3ed49c48b1
onnx/model.onnx_data 540,157,184 3ffe0420181424138de643144c94bd4c30126221cc636590f3ccb2fa352ae602

Citation (upstream)

@misc{allal2025smollm2smolgoesbig,
  title={SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model},
  author={Loubna Ben Allal and Anton Lozhkov and Elie Bakouch and Gabriel Martín Blázquez and Guilherme Penedo and Lewis Tunstall and Andrés Marafioti and Hynek Kydlíček and Agustín Piqueres Lajarín and Vaibhav Srivastav and Joshua Lochner and Caleb Fahlgren and Xuan-Son Nguyen and Clémentine Fourrier and Ben Burtenshaw and Hugo Larcher and Haojun Zhao and Cyril Zakka and Mathieu Morlon and Colin Raffel and Leandro von Werra and Thomas Wolf},
  year={2025},
  eprint={2502.02737},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2502.02737},
}
Downloads last month
314
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for andrzej/SmolLM2-135M-ONNX

Quantized
(79)
this model

Paper for andrzej/SmolLM2-135M-ONNX