google-deepmind / onetwoLinks
☆251Updated last week
Alternatives and similar repositories for onetwo
Users that are interested in onetwo are comparing it to the libraries listed below
Sorting:
- Website for hosting the Open Foundation Models Cheat Sheet.☆269Updated 6 months ago
- ☆212Updated this week
- ☆143Updated 2 months ago
- Draw more samples☆196Updated last year
- ☆124Updated last year
- ☆159Updated 11 months ago
- Training-Ready RL Environments + Evals☆177Updated this week
- Multi-backend recommender systems with Keras 3☆147Updated 3 weeks ago
- ☆68Updated last year
- ☆210Updated 4 months ago
- Minimal example scripts of the Hugging Face Trainer, focused on staying under 150 lines☆196Updated last year
- Fast bare-bones BPE for modern tokenizer training☆170Updated 5 months ago
- Banishing LLM Hallucinations Requires Rethinking Generalization☆275Updated last year
- ☆65Updated 4 months ago
- Library for text-to-text regression, applicable to any input string representation and allows pretraining and fine-tuning over multiple r…☆290Updated this week
- ☆170Updated last year
- Manage scalable open LLM inference endpoints in Slurm clusters☆277Updated last year
- Let's build better datasets, together!☆265Updated 11 months ago
- ☆233Updated 4 months ago
- An introduction to LLM Sampling☆79Updated 11 months ago
- Inference-time scaling for LLMs-as-a-judge.☆310Updated 2 weeks ago
- The history files when recording human interaction while solving ARC tasks☆118Updated last week
- Modular, scalable library to train ML models☆170Updated this week
- Public repository containing METR's DVC pipeline for eval data analysis☆129Updated 7 months ago
- Toolkit for attaching, training, saving and loading of new heads for transformer models☆291Updated 8 months ago
- code for training & evaluating Contextual Document Embedding models☆200Updated 6 months ago
- A puzzle to learn about prompting☆135Updated 2 years ago
- Doing simple retrieval from LLM models at various context lengths to measure accuracy☆106Updated 2 months ago
- A framework for standardizing evaluations of large foundation models, beyond single-score reporting and rankings.☆171Updated last week
- git extension for {collaborative, communal, continual} model development☆216Updated last year