monostate / weave-logprobs-reasoning-loopLinks
A notebook that compares a reasoning model x a non reasoning model that runs a loop using logprobs found uncertainty
☆25Updated 5 months ago
Alternatives and similar repositories for weave-logprobs-reasoning-loop
Users that are interested in weave-logprobs-reasoning-loop are comparing it to the libraries listed below
Sorting:
- syftr is an agent optimizer that helps you find the best agentic workflows for your budget.☆326Updated 2 weeks ago
- Build data processing and data analysis pipelines that leverage the power of LLMs 🧠☆247Updated 3 weeks ago
- Demo of knowledge graph creation and Graph RAG with BAML and Kuzu☆73Updated 4 months ago
- Pivotal Token Search☆145Updated last month
- This is a framework that implements various parallel reasoning strategies from the literature☆275Updated last month
- ~ streaming agents☆76Updated last week
- Sculpt: Structuring unstructured data with LLMs☆38Updated 4 months ago
- Chat strategies for LLMs☆129Updated 3 weeks ago
- Your AI research assistant☆79Updated 10 months ago
- Pixelagent — Multimodal stateful agents☆224Updated 8 months ago
- Fast Diversification for Search & Retrieval☆480Updated last week
- A Python toolkit for chain-of-thought prompting 🐍☆184Updated 2 months ago
- ☆28Updated last year
- ☆121Updated 6 months ago
- A library for building software agents using behavior trees and language models.☆90Updated last year
- LSD Model Context Protocol☆64Updated 10 months ago
- ☆37Updated 6 months ago
- Securely run AI-generated code in stateful sandboxes that run forever.☆227Updated 9 months ago
- A lightweight code assistant with tool-using capabilities built on HuggingFace's smolagents.☆41Updated 8 months ago
- Tools for LLM agents.☆61Updated last year
- ☆42Updated last year
- A framework for pitting LLMs against each other in an evolving library of games ⚔☆34Updated 9 months ago
- lossily compress representation vectors using product quantization☆59Updated 3 months ago
- A Model Context Protocol server that provides access to Kuzu databases☆39Updated 4 months ago
- Pragmatic framework to build LLM Copilots☆63Updated 11 months ago
- a Python library that uses Reinforcement Learning (RL) to train LLMs.☆42Updated 6 months ago
- Code for our paper PAPILLON: PrivAcy Preservation from Internet-based and Local Language MOdel ENsembles☆61Updated 9 months ago
- This repo is for the demonstration of TSCE principles.☆32Updated 3 weeks ago
- Explore GitHub repositories with natural language questions☆98Updated last year
- 🤖 Complete reproduction of 'AlphaGo Moment for Model Architecture Discovery' using MLX-LM instead of GPT-4. Autonomous neural architectu…☆27Updated 6 months ago