Instructions to use novelaide/LLMLingua-2-Small-INT8-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use novelaide/LLMLingua-2-Small-INT8-ONNX with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('token-classification', 'novelaide/LLMLingua-2-Small-INT8-ONNX');
LLMLingua-2 Small INT8 ONNX
This repository contains the exact immutable local-model asset used by NovelAide.
Provenance
- Base model:
microsoft/llmlingua-2-bert-base-multilingual-cased-meetingbank - Asset source:
ldenoue/llmlingua-2-bert-base-multilingual-cased-meetingbank - Pinned source revision:
d7070a9b381ca5297dd7bd5cf7704dde81470518 - Runtime:
transformers-js - NovelAide asset ID:
llmlingua-2-small-int8 - NovelAide CDN prefix:
llmlingua-2-small-int8-onnx
The base model is
microsoft/llmlingua-2-bert-base-multilingual-cased-meetingbank.
NovelAide consumes the pinned Small ONNX export published at
ldenoue/llmlingua-2-bert-base-multilingual-cased-meetingbank
using the revision in the adjacent manifest.
Files
| File | Size | SHA-256 |
|---|---|---|
config.json |
0.00 MiB | ba5bf489ee684b00ef5e38c8b19762c2b4a6ce20a6389a7acf46cc57db19a154 |
special_tokens_map.json |
0.00 MiB | b6d346be366a7d1d48332dbc9fdf3bf8960b5d879522b7799ddba59e76237ee3 |
tokenizer.json |
2.78 MiB | bf1b59b7b11c95f194f51708d918eea378e09d05f84c0e1656dc5180e8117088 |
tokenizer_config.json |
0.00 MiB | 214f78f6c5d034a8b405632d301ee3710eb6f075b3f5faf8241a273a13908746 |
vocab.txt |
0.95 MiB | fe0fda7c425b48c516fc8f160d594c8022a0808447475c1a7c6d6479763f310c |
onnx/model_quantized.onnx |
170.29 MiB | 6745c7aff5cb5c2c3c96b8e72ab8a65ce42157058f9221f6c340f0c37e760f5d |
Usage
Use the GGUF files with a compatible llama.cpp runtime and the ONNX files with a compatible ONNX / Transformers.js runtime. NovelAide pins the exact files and checksums shown above; do not substitute similarly named quantizations.
License and attribution
The model asset follows the upstream apache-2.0 license.
Review the linked base model and asset source model cards for their complete
terms, limitations, and attribution requirements. NovelAide is not affiliated
with or endorsed by the upstream model authors.
- Downloads last month
- 16