slim-ratings-npu-ov

slim-ratings-npu-ov is a specialized function calling model that generates a dictionary with a 'stars' rating characterizing the sentiment/positivity of a text passage between 1 (poor) and 5 (very positive).

This is an OpenVino int4 quantized version of slim-ratings, providing a very fast, very small inference implementation, optimized for AI PCs using Intel NPU.

Model Description

• Developed by: llmware
• Model type: tinyllama
• Parameters: 1.1 billion
• Model Parent: llmware/slim-ratings
• Language(s) (NLP): English
• License: Apache 2.0
• Uses: Sentiment 'stars' rating score of 1 (low) - 5 (high)
• RAG Benchmark Accuracy Score: NA
• Quantization: int4

Model Card Contact

llmware on github

llmware on hf

llmware website