kerekovskik / autologic
autologic is a Python package that implements the SELF-DISCOVER framework proposed in the paper SELF-DISCOVER: Large Language Models Self-Compose Reasoning Structures.
☆57Updated last year
Alternatives and similar repositories for autologic:
Users that are interested in autologic are comparing it to the libraries listed below
- Official homepage for "Self-Harmonized Chain of Thought" (NAACL 2025)☆91Updated 2 months ago
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆138Updated last month
- Generate Synthetic Data Using OpenAI, MistralAI or AnthropicAI☆223Updated 11 months ago
- ☆112Updated last week
- Train your own SOTA deductive reasoning model☆83Updated last month
- This is our own implementation of 'Layer Selective Rank Reduction'☆234Updated 10 months ago
- ☆129Updated last week
- Let's create synthetic textbooks together :)☆74Updated last year
- Merge Transformers language models by use of gradient parameters.☆206Updated 8 months ago
- ☆73Updated last year
- A simple experiment on letting two local LLM have a conversation about anything!☆110Updated 9 months ago
- ☆66Updated 10 months ago
- Low-Rank adapter extraction for fine-tuned transformers models☆171Updated 11 months ago
- ☆117Updated 7 months ago
- Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vecto…☆232Updated last month
- Just a bunch of benchmark logs for different LLMs☆119Updated 8 months ago
- Client Code Examples, Use Cases and Benchmarks for Enterprise h2oGPTe RAG-Based GenAI Platform☆86Updated last month
- ReDel is a toolkit for researchers and developers to build, iterate on, and analyze recursive multi-agent systems. (EMNLP 2024 Demo)☆74Updated 3 weeks ago
- ☆38Updated last year
- A DSPy-based implementation of the tree of thoughts method (Yao et al., 2023) for generating persuasive arguments☆77Updated 6 months ago
- Easy to use, High Performant Knowledge Distillation for LLMs☆58Updated this week
- CaSIL is an advanced natural language processing system that implements a sophisticated four-layer semantic analysis architecture. It pro…☆64Updated 5 months ago
- A framework for orchestrating AI agents using a mermaid graph☆75Updated 10 months ago
- A guidance compatibility layer for llama-cpp-python☆34Updated last year
- Roy: A lightweight, model-agnostic framework for crafting advanced multi-agent systems using large language models.☆78Updated last year
- GPT-2 small trained on phi-like data☆66Updated last year
- A framework for evaluating function calls made by LLMs☆37Updated 8 months ago
- LLM reads a paper and produce a working prototype☆52Updated this week
- ☆45Updated last year
- ☆118Updated 8 months ago