VectorInstitute / vector-inference
Efficient LLM inference on Slurm clusters using vLLM.
☆39Updated last week
Related projects ⓘ
Alternatives and complementary repositories for vector-inference
- LLM finetuning in resource-constrained environments.☆41Updated 4 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆25Updated 5 months ago
- NanoGPT-like codebase for LLM training☆75Updated this week
- ☆105Updated last month
- ☆107Updated this week
- ☆53Updated 3 weeks ago
- A library for efficient patching and automatic circuit discovery.☆31Updated last month
- ☆76Updated 9 months ago
- ☆29Updated 7 months ago
- Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature☆107Updated 3 months ago
- A MAD laboratory to improve AI architecture designs 🧪☆95Updated 6 months ago
- Language models scale reliably with over-training and on downstream tasks☆94Updated 7 months ago
- A library to create and manage configuration files, especially for machine learning projects.☆77Updated 2 years ago
- Sparse and discrete interpretability tool for neural networks☆55Updated 9 months ago
- ☆101Updated 3 months ago
- ☆71Updated 6 months ago
- Utilities for the HuggingFace transformers library☆61Updated last year
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆26Updated 5 months ago
- ☆44Updated this week
- ☆73Updated 4 months ago
- ☆50Updated 6 months ago
- A user toolkit for analyzing and interfacing with Large Language Models (LLMs)☆21Updated 2 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆119Updated last month
- ☆54Updated 2 years ago
- ☆18Updated last month
- AI Logging for Interpretability and Explainability🔬☆89Updated 5 months ago
- Simple and efficient pytorch-native transformer training and inference (batched)☆61Updated 7 months ago
- ☆149Updated 6 months ago
- ☆22Updated this week
- ☆99Updated 3 months ago