google-research / cascadesLinks
Python library which enables complex compositions of language models such as scratchpads, chain of thought, tool use, selection-inference, and more.
☆207Updated 4 months ago
Alternatives and similar repositories for cascades
Users that are interested in cascades are comparing it to the libraries listed below
Sorting:
- Used for adaptive human in the loop evaluation of language and embedding models.☆308Updated 2 years ago
- Train very large language models in Jax.☆204Updated last year
- TART: A plug-and-play Transformer module for task-agnostic reasoning☆196Updated last year
- A repository for transformer critique learning and generation☆89Updated last year
- git extension for {collaborative, communal, continual} model development☆212Updated 6 months ago
- ☆273Updated 11 months ago
- [NeurIPS 2023] Learning Transformer Programs☆161Updated last year
- ☆159Updated 2 years ago
- Neural Networks and the Chomsky Hierarchy☆205Updated last year
- Probabilistic LLM evaluations. [CogSci2023; ACL2023]☆72Updated 10 months ago
- For experiments involving instruct gpt. Currently used for documenting open research questions.☆70Updated 2 years ago
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆181Updated last year
- ☆67Updated 2 years ago
- A library to create and manage configuration files, especially for machine learning projects.☆78Updated 3 years ago
- Inference code for LLaMA models in JAX☆117Updated last year
- Code repository for the c-BTM paper☆106Updated last year
- ☆94Updated 5 months ago
- ☆166Updated last year
- some common Huggingface transformers in maximal update parametrization (µP)☆80Updated 3 years ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆125Updated 2 years ago
- A domain-specific probabilistic programming language for modeling and inference with language models☆130Updated last month
- ☆72Updated last year
- Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways - in Jax (Equinox framework)☆187Updated 2 years ago
- Extract full next-token probabilities via language model APIs☆248Updated last year
- An interactive exploration of Transformer programming.☆264Updated last year
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆204Updated this week
- Understand and test language model architectures on synthetic tasks.☆195Updated 2 months ago
- Drive a browser with Cohere☆71Updated 2 years ago
- Scaling Data-Constrained Language Models☆334Updated 8 months ago
- A framework for few-shot evaluation of autoregressive language models.☆102Updated 2 years ago