CarperAI / cheese
Used for adaptive human in the loop evaluation of language and embedding models.
☆304Updated last year
Related projects ⓘ
Alternatives and complementary repositories for cheese
- Experiments with generating opensource language model assistants☆97Updated last year
- Exploring finetuning public checkpoints on filter 8K sequences on Pile☆115Updated last year
- Reproduce results and replicate training fo T0 (Multitask Prompted Training Enables Zero-Shot Task Generalization)☆457Updated 2 years ago
- Scaling Data-Constrained Language Models☆321Updated last month
- Python library which enables complex compositions of language models such as scratchpads, chain of thought, tool use, selection-inference…☆196Updated 5 months ago
- Pipeline for pulling and processing online language model pretraining data from the web☆174Updated last year
- DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.☆164Updated 6 months ago
- This project is an attempt to create a common metric to test LLM's for progress in eliminating hallucinations which is the most serious c…☆221Updated last year
- ☆158Updated last year
- Open Instruction Generalist is an assistant trained on massive synthetic instructions to perform many millions of tasks☆206Updated 10 months ago
- ☆175Updated last year
- A Multilingual Dataset for Parsing Realistic Task-Oriented Dialogs☆113Updated last year
- Ask Me Anything language model prompting☆539Updated last year
- Multipack distributed sampler for fast padding-free training of LLMs☆178Updated 3 months ago
- TART: A plug-and-play Transformer module for task-agnostic reasoning☆190Updated last year
- ☆221Updated last year
- Code repository for the c-BTM paper☆105Updated last year
- Code and data for "Measuring and Narrowing the Compositionality Gap in Language Models"☆299Updated 10 months ago
- ☆239Updated 4 months ago
- Easily convert common crawl to a dataset of caption and document. Image/text Audio/text Video/text, ...☆310Updated 11 months ago
- ☆91Updated last week
- ☆91Updated last year
- The GeoV model is a large langauge model designed by Georges Harik and uses Rotary Positional Embeddings with Relative distances (RoPER).…☆122Updated last year
- Reimplementation of the task generation part from the Alpaca paper☆119Updated last year
- For experiments involving instruct gpt. Currently used for documenting open research questions.☆71Updated 2 years ago
- ☆128Updated 2 years ago
- Datasets collection and preprocessings framework for NLP extreme multitask learning☆149Updated 4 months ago
- Reflexion: an autonomous agent with dynamic memory and self-reflection☆380Updated 11 months ago
- Erasing concepts from neural representations with provable guarantees☆209Updated last week
- Manage scalable open LLM inference endpoints in Slurm clusters☆236Updated 4 months ago