google-research / cascades
Python library which enables complex compositions of language models such as scratchpads, chain of thought, tool use, selection-inference, and more.
☆202Updated last month
Alternatives and similar repositories for cascades:
Users that are interested in cascades are comparing it to the libraries listed below
- Used for adaptive human in the loop evaluation of language and embedding models.☆306Updated last year
- Train very large language models in Jax.☆202Updated last year
- A repository for transformer critique learning and generation☆88Updated last year
- [NeurIPS 2023] Learning Transformer Programs☆157Updated 9 months ago
- ☆160Updated last year
- ☆253Updated 7 months ago
- git extension for {collaborative, communal, continual} model development☆207Updated 3 months ago
- A library to create and manage configuration files, especially for machine learning projects.☆76Updated 2 years ago
- TART: A plug-and-play Transformer module for task-agnostic reasoning☆195Updated last year
- Erasing concepts from neural representations with provable guarantees☆222Updated 3 weeks ago
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆175Updated last year
- Extract full next-token probabilities via language model APIs☆229Updated 11 months ago
- ☆93Updated 2 months ago
- Neural Networks and the Chomsky Hierarchy☆199Updated 10 months ago
- some common Huggingface transformers in maximal update parametrization (µP)☆78Updated 2 years ago
- Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023☆130Updated 9 months ago
- Inference code for LLaMA models in JAX☆114Updated 9 months ago
- ☆164Updated last year
- See the issue board for the current status of active and prospective projects!☆65Updated 3 years ago
- ☆201Updated last year
- Seminar on Large Language Models (COMP790-101 at UNC Chapel Hill, Fall 2022)☆310Updated 2 years ago
- ☆72Updated 9 months ago
- A domain-specific probabilistic programming language for modeling and inference with language models☆114Updated last year
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆195Updated last week
- ☆73Updated last year
- ☆65Updated 2 years ago
- For experiments involving instruct gpt. Currently used for documenting open research questions.☆71Updated 2 years ago
- Mechanistic Interpretability for Transformer Models☆49Updated 2 years ago
- DialOp: Decision-oriented dialogue environments for collaborative language agents☆106Updated 3 months ago
- Simple next-token-prediction for RLHF☆222Updated last year