lechmazur / generalizationLinks
Thematic Generalization Benchmark: measures how effectively various LLMs can infer a narrow or specific "theme" (category/rule) from a small set of examples and anti-examples, then detect which item truly fits that theme among a collection of misleading candidates.
☆63Updated last month
Alternatives and similar repositories for generalization
Users that are interested in generalization are comparing it to the libraries listed below
Sorting:
- Multi-Agent Step Race Benchmark: Assessing LLM Collaboration and Deception Under Pressure. A multi-player “step-race” that challenges LLM…☆76Updated 2 months ago
- Glyphs, acting as collaboratively defined symbols linking related concepts, add a layer of multidimensional semantic richness to user-AI …☆53Updated 9 months ago
- Conduct in-depth research with AI-driven insights : DeepDive is a command-line tool that leverages web searches and AI models to generate…☆42Updated last year
- ☆116Updated 11 months ago
- A Python library to orchestrate LLMs in a neural network-inspired structure☆51Updated last year
- Adding a multi-text multi-speaker script (diffe) that is based on a script from asiff00 on issue 61 for Sesame: A Conversational Speech G…☆25Updated 7 months ago
- LLM Divergent Thinking Creativity Benchmark. LLMs generate 25 unique words that start with a given letter with no connections to each oth…☆33Updated 7 months ago
- Create text chunks which end at natural stopping points without using a tokenizer☆25Updated 8 months ago
- The hearth of The Pulsar App, fast, secure and shared inference with modern UI☆58Updated 11 months ago
- Serving LLMs in the HF-Transformers format via a PyFlask API☆71Updated last year
- klmbr - a prompt pre-processing technique to break through the barrier of entropy while generating text with LLMs☆84Updated last year
- ☆17Updated 11 months ago
- ☆24Updated 9 months ago
- ☆107Updated 2 weeks ago
- A proxy that hosts multiple single-model runners such as LLama.cpp and vLLM☆11Updated 5 months ago
- My version of an LLM Websearch Agent using a local SearXNG server because SearXNG is great.