kerekovskik / autologicLinks
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
Sorting:
- Generate Synthetic Data Using OpenAI, MistralAI or AnthropicAI☆221Updated last year
- ☆113Updated 5 months ago
- ☆121Updated last month
- Let's create synthetic textbooks together :)☆75Updated last year
- Low-Rank adapter extraction for fine-tuned transformers models☆171Updated last year
- ☆66Updated last year
- ☆19Updated last year
- ☆75Updated 2 weeks ago
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆139Updated 3 months ago
- ☆157Updated 10 months ago
- A framework for evaluating function calls made by LLMs☆37Updated 10 months ago
- Train your own SOTA deductive reasoning model☆92Updated 2 months ago
- Just a bunch of benchmark logs for different LLMs☆119Updated 10 months ago
- Using open source LLMs to build synthetic datasets for direct preference optimization☆63Updated last year
- This is our own implementation of 'Layer Selective Rank Reduction'☆238Updated last year
- ☆118Updated 9 months ago
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆81Updated last year
- ReDel is a toolkit for researchers and developers to build, iterate on, and analyze recursive multi-agent systems. (EMNLP 2024 Demo)☆78Updated 2 months ago
- ☆130Updated 9 months ago
- Mixing Language Models with Self-Verification and Meta-Verification☆104Updated 5 months ago
- Function Calling Benchmark & Testing☆87Updated 10 months ago
- A framework for orchestrating AI agents using a mermaid graph☆75Updated last year
- Official homepage for "Self-Harmonized Chain of Thought" (NAACL 2025)☆90Updated 4 months ago
- entropix style sampling + GUI☆26Updated 7 months ago
- GPT-2 small trained on phi-like data☆66Updated last year
- All the world is a play, we are but actors in it.☆50Updated this week
- Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vecto…☆238Updated 3 months ago
- Dataset Crafting w/ RAG/Wikipedia ground truth and Efficient Fine-Tuning Using MLX and Unsloth. Includes configurable dataset annotation …☆185Updated 10 months ago
- Source code for the collaborative reasoner research project at Meta FAIR.☆87Updated last month
- ☆57Updated last week