[P] CAPPr: use OpenAI or HuggingFace models to easily do zero-shot text classification

• cappr

  4 63 9.4 Python

  Completion After Prompt Probability. Make your LLM make a choice

One interesting result is that on the Choice of Plausible Alternatives task, zero-shot text-curie-001 (a smaller GPT-3 model) is < 50% accurate when using sampling, but 80% accurate when using CAPPr. (Here's a link to the experiment notebook.) It would be cool to demonstrate that CAPPr squeezes more out of smaller or less-heavily trained LLMs, as CAPPr's performance may be based more on next-token prediction performance than instruction-based performance.

• InfluxDB

  www.influxdata.com featured

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

Suggest a related project