llmware/slim-topics-onnx
By llmware · ↓ 1 · ♥ 1 · Updated 2024-10-31
What's in this repo
This page lists the files in llmware/slim-topics-onnx, including model.onnx.
- 1 ONNX models (.onnx files)
- 10 files, including 5 .json, 1 .md, 1 .onnx, 1 .data, 1 .model
- Last updated 2024-10-31
ONNX files
| File | Size | Download |
|---|---|---|
| model.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
slim-topics-onnx
slim-topics-onnx is a specialized function calling model that generates a topic description for a text passage, typically no more than 2-3 words.
This is an ONNX int4 quantized version of slim-topics, providing a very fast, very small inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.
Model Description
- Developed by: llmware
- Model type: tinyllama
- Parameters: 1.1 billion
- Model Parent: llmware/slim-topics
- Language(s) (NLP): English
- License: Apache 2.0
- Uses: Topic categorization and summarization
- RAG Benchmark Accuracy Score: NA
- Quantization: int4
Model Card Contact
Model info
Created: 2024-06-15
Updated: 2024-10-31
View on Hugging Face