cognitivecomputations / extract-expert
Extract a single expert from a Mixture Of Experts model using slerp interpolation.
☆17Updated 3 months ago
Related projects: ⓘ
- ☆64Updated 3 months ago
- ☆71Updated last year
- ☆75Updated 3 weeks ago
- Official homepage for "Self-Harmonized Chain of Thought"☆45Updated this week
- ☆28Updated this week
- ☆20Updated 11 months ago
- ☆48Updated 11 months ago
- never forget anything again! combine AI and intelligent tooling for a local knowledge base to track catalogue, annotate, and plan for you…☆29Updated 4 months ago
- Just a bunch of benchmark logs for different LLMs☆112Updated last month
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks☆31Updated 3 months ago
- ☆50Updated 3 months ago
- ☆101Updated 6 months ago
- ☆68Updated 2 months ago
- Leveraging DSPy for AI-driven task understanding and solution generation, the Self-Discover Framework automates problem-solving through r…☆53Updated 2 months ago
- autologic is a Python package that implements the SELF-DISCOVER framework proposed in the paper SELF-DISCOVER: Large Language Models Self…☆53Updated 7 months ago
- Let's create synthetic textbooks together :)☆70Updated 7 months ago
- Data preparation code for CrystalCoder 7B LLM☆42Updated 4 months ago
- Low-Rank adapter extraction for fine-tuned transformers model☆154Updated 4 months ago
- ReDel is a toolkit for researchers and developers to build, iterate on, and analyze recursive multi-agent systems.☆48Updated 3 weeks ago
- High level library for batched embeddings generation, blazingly-fast web-based RAG and quantized indexes processing ⚡☆58Updated 2 weeks ago
- Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vecto…☆40Updated 6 months ago
- ☆144Updated 2 months ago
- ☆23Updated 8 months ago
- ☆15Updated 10 months ago
- run ollama & gguf easily with a single command☆46Updated 4 months ago
- Data preparation code for Amber 7B LLM☆76Updated 4 months ago
- A framework for evaluating function calls made by LLMs☆34Updated last month
- Evaluation and analysis code for LLM360☆75Updated 3 months ago
- a lightweight, open-source blueprint for building powerful and scalable LLM chat applications☆30Updated 3 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…☆34Updated 3 weeks ago