VectorInstitute / vector-inferenceLinks
Efficient LLM inference on Slurm clusters.
☆90Updated last week
Alternatives and similar repositories for vector-inference
Users that are interested in vector-inference are comparing it to the libraries listed below
Sorting:
- LLM finetuning in resource-constrained environments.☆55Updated last year
- Extract full next-token probabilities via language model APIs☆248Updated last year
- nanoGPT-like codebase for LLM training☆113Updated 2 months ago
- PyTorch library for Active Fine-Tuning☆96Updated 4 months ago
- Official repository for "Scaling Retrieval-Based Langauge Models with a Trillion-Token Datastore".☆223Updated last month
- A MAD laboratory to improve AI architecture designs 🧪☆135Updated last year
- ☆152Updated 4 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆186Updated last week
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆133Updated 3 years ago
- Simple and scalable tools for data-driven pretraining data selection.☆29Updated 7 months ago
- ☆76Updated 3 years ago
- ☆77Updated last year
- ☆167Updated 2 years ago
- Website for hosting the Open Foundation Models Cheat Sheet.☆269Updated 8 months ago
- Attribution-based Parameter Decomposition☆33Updated 7 months ago
- AI Logging for Interpretability and Explainability🔬☆138Updated last year
- Understand and test language model architectures on synthetic tasks.☆251Updated 2 weeks ago
- Language models scale reliably with over-training and on downstream tasks☆99Updated last year
- Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature☆177Updated 7 months ago
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆88Updated last year
- ☆52Updated 10 months ago
- Implementation of the BatchTopK activation function for training sparse autoencoders (SAEs)☆57Updated 6 months ago
- [NeurIPS 2023] Learning Transformer Programs☆162Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆63Updated last year
- A library for efficient patching and automatic circuit discovery.☆86Updated 3 weeks ago
- Code for Zero-Shot Tokenizer Transfer☆142Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆138Updated 11 months ago
- ☆83Updated 11 months ago
- A fast, effective data attribution method for neural networks in PyTorch☆227Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆235Updated last week