google-research / cascades
Python library which enables complex compositions of language models such as scratchpads, chain of thought, tool use, selection-inference, and more.
☆195Updated 4 months ago
Related projects ⓘ
Alternatives and complementary repositories for cascades
- ☆239Updated 4 months ago
- Used for adaptive human in the loop evaluation of language and embedding models.☆303Updated last year
- Train very large language models in Jax.☆195Updated last year
- Repository for the code of the "PPL-MCTS: Constrained Textual Generation Through Discriminator-Guided Decoding" paper, NAACL'22☆64Updated 2 years ago
- git extension for {collaborative, communal, continual} model development☆205Updated 5 months ago
- ☆158Updated last year
- A library to create and manage configuration files, especially for machine learning projects.☆77Updated 2 years ago
- Erasing concepts from neural representations with provable guarantees☆208Updated 3 weeks ago
- Extract full next-token probabilities via language model APIs☆228Updated 8 months ago
- ☆91Updated 7 months ago
- [NeurIPS 2023] Learning Transformer Programs☆157Updated 5 months ago
- Inference code for LLaMA models in JAX☆112Updated 5 months ago
- Mechanistic Interpretability for Transformer Models☆49Updated 2 years ago
- A repository for transformer critique learning and generation☆85Updated 11 months ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆186Updated this week
- ☆64Updated 2 years ago
- A MAD laboratory to improve AI architecture designs 🧪☆95Updated 6 months ago
- Datasets collection and preprocessings framework for NLP extreme multitask learning☆147Updated 3 months ago
- Code repository for the c-BTM paper☆105Updated last year
- some common Huggingface transformers in maximal update parametrization (µP)☆76Updated 2 years ago
- TART: A plug-and-play Transformer module for task-agnostic reasoning☆190Updated last year
- A dataset of alignment research and code to reproduce it☆68Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆95Updated 2 years ago
- See the issue board for the current status of active and prospective projects!☆65Updated 2 years ago
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆168Updated last year
- ☆122Updated last week
- ☆198Updated last year
- Probabilistic LLM evaluations. [CogSci2023; ACL2023]☆73Updated 3 months ago
- Experiments for efforts to train a new and improved t5☆76Updated 6 months ago