labmlai / inspectusLinks
LLM Analytics
☆668Updated 8 months ago
Alternatives and similar repositories for inspectus
Users that are interested in inspectus are comparing it to the libraries listed below
Sorting:
- A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and full…☆615Updated 3 months ago
- Bayesian Optimization as a Coverage Tool for Evaluating LLMs. Accurate evaluation (benchmarking) that's 10 times faster with just a few l…☆285Updated 3 weeks ago
- MINT-1T: A one trillion token multimodal interleaved dataset.☆817Updated 10 months ago
- This project collects GPU benchmarks from various cloud providers and compares them to fixed per token costs. Use our tool for efficient …☆221Updated 6 months ago
- Visualize the intermediate output of Mistral 7B☆367Updated 5 months ago
- See Through Your Models☆394Updated 3 months ago
- clean & curate your data with LLMs.☆493Updated 11 months ago
- Animating R1's thoughts.☆382Updated 4 months ago
- ☆745Updated last year
- Dead Simple LLM Abliteration☆219Updated 4 months ago
- Felafax is building AI infra for non-NVIDIA GPUs☆562Updated 5 months ago
- RAG Logger is an open-source logging tool designed specifically for Retrieval-Augmented Generation (RAG) applications. It serves as a lig…☆221Updated 6 months ago
- Hypernetworks that adapt LLMs for specific benchmark tasks using only textual task description as the input☆649Updated 2 weeks ago
- Things you can do with the token embeddings of an LLM☆1,445Updated 2 months ago
- Build, Improve Performance, and Productionize your LLM Application with an Integrated Framework☆340Updated 6 months ago
- A library for making RepE control vectors☆610Updated 5 months ago
- a curated list of data for reasoning ai☆136Updated 10 months ago
- Ask GPT to run a command☆195Updated 3 months ago
- DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤☆1,028Updated 4 months ago
- Agent accuracy measurements for LLMs☆205Updated last year
- Code and data for "Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs"☆464Updated last year
- OpenAI's Structured Outputs with Logprobs☆172Updated 3 weeks ago
- Finetune llama2-70b and codellama on MacBook Air without quantization☆447Updated last year
- Code to train and evaluate Neural Attention Memory Models to obtain universally-applicable memory systems for transformers.☆311Updated 8 months ago
- Absolute minimalistic implementation of a GPT-like transformer using only numpy (<650 lines).☆252Updated last year
- Fine-tune LLM agents with online reinforcement learning☆1,197Updated last year
- Controlled Text Generation via Language Model Arithmetic☆221Updated 9 months ago
- ☆411Updated 10 months ago
- Official codebase for the paper "Beyond A* Better Planning with Transformers via Search Dynamics Bootstrapping".☆368Updated last year
- ai for jq☆242Updated 9 months ago