labmlai / inspectus
LLM Analytics
☆593Updated last month
Related projects: ⓘ
- Things you can do with the token embeddings of an LLM☆730Updated this week
- Bayesian Optimization as a Coverage Tool for Evaluating LLMs. Accurate evaluation (benchmarking) that's 10 times faster with just a few l…☆269Updated last month
- Visualize the intermediate output of Mistral 7B☆300Updated 7 months ago
- Build and query dynamic, temporally-aware Knowledge Graphs☆572Updated this week
- Stateful load balancer custom-tailored for llama.cpp☆518Updated this week
- DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤☆792Updated last month
- Chat with any codebase with 2 commands☆546Updated this week
- Optimizing inference proxy for LLMs☆406Updated this week
- clean & curate your data with LLMs.☆460Updated 2 months ago
- A framework for building, experimenting, deploying, and continuously iterating on your LLM application☆290Updated this week
- Neum AI is a best-in-class framework to manage the creation and synchronization of vector embeddings at large scale.☆821Updated 8 months ago
- High-performance retrieval engine for unstructured data☆778Updated this week
- Action library for AI Agent☆187Updated this week
- Code behind Arxiv Papers☆443Updated 5 months ago
- Felafax is building AI infra for non-NVIDIA GPUs☆282Updated this week
- The Open Source Memory Layer For Autonomous Agents☆1,390Updated last week
- Fine-tune LLM agents with online reinforcement learning☆971Updated 6 months ago
- ☆719Updated 5 months ago
- This project collects GPU benchmarks from various cloud providers and compares them to fixed per token costs. Use our tool for efficient …☆196Updated 2 weeks ago
- An application for running LLMs locally on your device, with your documents, facilitating detailed citations in generated responses.☆459Updated this week
- ☆366Updated last month
- Finetune llama2-70b and codellama on MacBook Air without quantization☆443Updated 5 months ago
- A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.☆790Updated last week
- llama3.np is a pure NumPy implementation for Llama 3 model.☆955Updated 3 months ago
- Curate better data for LLMs☆934Updated 6 months ago
- Build applications that make decisions (chatbots, agents, simulations, etc...). Monitor, trace, persist, and execute on your own infrastr…☆1,123Updated this week
- Agent accuracy measurements for LLMs☆201Updated 3 months ago
- Prompt engineering for developers☆665Updated 7 months ago
- An LLM-powered advanced RAG pipeline built from scratch☆785Updated 7 months ago
- AI-powered Jupyter Notebook — use local AI to generate and edit code cells, automatically fix errors, and chat with your data☆1,047Updated 3 weeks ago