Xenova/stablelm-2-1_6b
By Xenova · ↓ 3 · ♥ 2 · Updated 2024-10-08
What's in this repo
This page lists the files in Xenova/stablelm-2-1_6b, including decoder_model_merged.onnx, decoder_model_merged_quantized.onnx.
- 2 ONNX models (.onnx files)
- 14 files, including 7 .json, 2 .onnx, 1 .md, 1 .py, 1 .txt, 1 .onnx_data
- Last updated 2024-10-08
ONNX files
| File | Size | Download |
|---|---|---|
| onnx/decoder_model_merged.onnx | — | Download |
| onnx/decoder_model_merged_quantized.onnx | — | 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/stabilityai/stablelm-2-1_6b with ONNX weights to be compatible with Transformers.js.
Usage (Transformers.js)
If you haven't already, you can install the Transformers.js JavaScript library from NPM using:
npm i @xenova/transformers
Example: Text generation with Xenova/stablelm-2-1_6b.
import { pipeline } from '@xenova/transformers';
// Create text generation pipeline
const generator = await pipeline('text-generation', 'Xenova/stablelm-2-1_6b');
// Generate text
const output = await generator('The weather is always wonderful', { max_new_tokens: 20 });
console.log(output[0].generated_text);
// The weather is always wonderful when you are in the country. The sun is always shining, and you can always see the mountains
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: 2024-02-02
Updated: 2024-10-08
View on Hugging Face