katzurik / Knowledge_Navigator
☆14Updated this week
Related projects ⓘ
Alternatives and complementary repositories for Knowledge_Navigator
- Training hybrid models for dummies.☆15Updated 3 weeks ago
- A Data Source for Reasoning Embodied Agents☆19Updated last year
- Efficient Dictionary Learning with Switch Sparse Autoencoders (SAEs)☆12Updated last month
- SCREWS: A Modular Framework for Reasoning with Revisions☆26Updated last year
- Learning to Retrieve by Trying - Source code for Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval☆24Updated 3 weeks ago
- A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.☆33Updated 8 months ago
- NeurIPS 2023 - Cappy: Outperforming and Boosting Large Multi-Task LMs with a Small Scorer☆37Updated 7 months ago
- A testbed for agents and environments that can automatically improve models through data generation.☆12Updated last week
- ☆13Updated last year
- DPO, but faster 🚀☆23Updated 3 weeks ago
- ☆59Updated last month
- ☆13Updated last year
- Visual RAG using less than 300 lines of code.☆23Updated 8 months ago
- PyTorch Implementation of the paper "MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training"☆23Updated last week
- ReBase: Training Task Experts through Retrieval Based Distillation☆27Updated 4 months ago
- ☆12Updated 7 months ago
- QLoRA for Masked Language Modeling☆20Updated last year
- ☆27Updated 5 months ago
- ☆41Updated last month
- ☆11Updated last month
- ☆14Updated 8 months ago
- LLM training in simple, raw C/CUDA☆12Updated last month
- Understanding the correlation between different LLM benchmarks☆29Updated 10 months ago
- ☆29Updated 11 months ago
- implementation of https://arxiv.org/pdf/2312.09299☆19Updated 4 months ago
- Lottery Ticket Adaptation☆36Updated last month
- The Benefits of a Concise Chain of Thought on Problem Solving in Large Language Models☆20Updated 9 months ago
- ☆27Updated 3 months ago
- ☆15Updated 11 months ago
- LLM reads a paper and produce a working prototype☆36Updated last week