onnx-community/SmolLM2-135M-Instruct-ONNX-MHA
By onnx-community · ↓ 457 · ♥ 0 · Updated 2025-03-10
What's in this repo
This page lists the files in onnx-community/SmolLM2-135M-Instruct-ONNX-MHA, including model.onnx, model_bnb4.onnx, model_fp16.onnx and more.
- 8 ONNX models (.onnx files)
- 17 files, including 8 .onnx, 6 .json, 1 .md, 1 .txt
- Repository size ~1.6 GB
- Last updated 2025-03-10
ONNX files
| File | Size | Download |
|---|---|---|
| onnx/model.onnx | 516 MB | Download |
| onnx/model_bnb4.onnx | 168 MB | Download |
| onnx/model_fp16.onnx | 258 MB | Download |
| onnx/model_int8.onnx | 131 MB | Download |
| onnx/model_q4.onnx | 174 MB | Download |
| onnx/model_q4f16.onnx | 113 MB | Download |
| onnx/model_quantized.onnx | 131 MB | Download |
| onnx/model_uint8.onnx | 131 MB | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct with ONNX weights to be compatible with Transformers.js.
Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using 🤗 Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).
Model info
Created: 2025-03-10
Updated: 2025-03-10
View on Hugging Face