PairRM
Pairwise Reward Model (PairRM) takes an instruction and a pair of output candidates as the input, and output a score for each candidate to measure their relative quality.
text → text · made by LLM Blender
Sold by
Nobody in the catalogue publishes a price for this yet.
About
PairRM — a text model from LLM Blender.
It takes text and returns text. It was published in November 2023. The catalogue files it under chat. Its weights are published under MIT, so you may run it on your own machine, or buy it from whoever serves it cheapest.
Every current figure
- Maker
- LLM Blender
- Register
- model
- Takes
- text
- Returns
- text
- Published
- November 2023
- Parameters
- 436 million · read from its own weights
- Licence
- mit
Known as 1 name
llm-blender/PairRM