LLMLingua-2 Large INT8 ONNX

This repository contains the exact immutable local-model asset used by NovelAide.

Provenance

The base model is microsoft/llmlingua-2-xlm-roberta-large-meetingbank. NovelAide consumes the pinned Large JavaScript ONNX export at atjsh/llmlingua-2-js-xlm-roberta-large-meetingbank with its immutable revision defined by the asset manifest.

Files

File Size SHA-256
config.json 0.00 MiB c2d70cabea93dc9409680b75f062c013ad58dd76b20f2d2bb71530bc6f0e163d
special_tokens_map.json 0.00 MiB 8c785abebea9ae3257b61681b4e6fd8365ceafde980c21970d001e834cf10835
tokenizer.json 16.29 MiB d5e1e0abdc17f93ca3c0c02a75d90c7c1f4ef556dd1a4e5c12d4ad4e8812e112
tokenizer_config.json 0.00 MiB dfb4021b23969fc942e96b2c4ac906d94712b4b96ef7081cb66a0ea211896d51
onnx/model_int8.onnx 535.82 MiB 0fddee8b1e0de33216b534370b884481f033f8d5225e73ac88f38bb8f829caff

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 mit 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
21
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for novelaide/LLMLingua-2-Large-INT8-ONNX

Quantized
(2)
this model