imelnyk / ArxivPapers
Code behind Arxiv Papers
☆468Updated 7 months ago
Related projects ⓘ
Alternatives and complementary repositories for ArxivPapers
- LLM Analytics☆615Updated last month
- Finetune llama2-70b and codellama on MacBook Air without quantization☆447Updated 7 months ago
- A pure NumPy implementation of Mamba.☆216Updated 4 months ago
- Visualize the intermediate output of Mistral 7B☆313Updated 9 months ago
- Fine-tune LLM agents with online reinforcement learning☆995Updated 8 months ago
- Official codebase for the paper "Beyond A* Better Planning with Transformers via Search Dynamics Bootstrapping".☆322Updated 5 months ago
- Bayesian Optimization as a Coverage Tool for Evaluating LLMs. Accurate evaluation (benchmarking) that's 10 times faster with just a few l…☆271Updated this week
- System 2 Reasoning Link Collection☆693Updated 3 weeks ago
- An interactive HTML pretty-printer for machine learning research in IPython notebooks.☆337Updated 2 weeks ago
- MINT-1T: A one trillion token multimodal interleaved dataset.☆774Updated 3 months ago
- Open weights language model from Google DeepMind, based on Griffin.☆607Updated 4 months ago
- nanoGPT style version of Llama 3.1☆1,246Updated 3 months ago
- data-to-paper: Backward-traceable AI-driven scientific research☆489Updated 3 weeks ago
- Absolute minimalistic implementation of a GPT-like transformer using only numpy (<650 lines).☆250Updated last year
- llama3.np is a pure NumPy implementation for Llama 3 model.☆975Updated 5 months ago
- Fine-tune mistral-7B on 3090s, a100s, h100s☆702Updated last year
- From scratch implementation of a sparse mixture of experts language model inspired by Andrej Karpathy's makemore :)☆594Updated 3 weeks ago
- Deep learning for dummies. All the practical details and useful utilities that go into working with real models.☆715Updated last month
- This project collects GPU benchmarks from various cloud providers and compares them to fixed per token costs. Use our tool for efficient …☆210Updated last month
- Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI☆1,336Updated 7 months ago
- Agents Capable of Self-Editing Their Prompts / Python Code☆745Updated 8 months ago
- A library for making RepE control vectors☆481Updated last month
- A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.☆1,095Updated last week
- Ask GPT to run a command☆193Updated 2 months ago
- NanoGPT (124M) quality in 7.8 8xH100-minutes☆1,033Updated this week
- LLM Chain querying a scientific Zotero library, with citations☆411Updated last year
- ☆448Updated 7 months ago
- High-performance retrieval engine for unstructured data☆982Updated last week
- Talk to any ArXiv paper using ChatGPT☆508Updated 10 months ago
- DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤☆845Updated 3 months ago