Metadata-Version: 2.1
Name: search-and-learn
Version: 0.1.0
Summary: A tool for search-based methods on llms
Home-page: https://github.com/reliable-agents/search-and-learn
Author: The Hugging Face team (past and future)
Author-email: lewis@huggingface.co
License: Apache
Keywords: nlp deep learning mcts
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Education
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.10.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: accelerate
Requires-Dist: pebble
Requires-Dist: latex2sympy2==1.9.1
Requires-Dist: word2number
Requires-Dist: transformers>=4.47.0
Requires-Dist: fastapi
Provides-Extra: quality
Requires-Dist: ruff; extra == "quality"
Requires-Dist: isort; extra == "quality"
Provides-Extra: tests
Requires-Dist: pytest; extra == "tests"
Provides-Extra: dev
Requires-Dist: vllm==0.6.3; extra == "dev"
Requires-Dist: ruff; extra == "dev"
Requires-Dist: isort; extra == "dev"
Requires-Dist: pytest; extra == "dev"

# Search and Learn

> One thing that should be learned from [the bitter lesson](https://www.cs.utexas.edu/~eunsol/courses/data/bitter_lesson.pdf) is the great power of general purpose methods, of methods that continue to scale with increased computation even as the available computation becomes very great. The two methods that seem to scale arbitrarily in this way are _**search**_ and _**learning**_.

# Installation

```shell
conda create -n sal python=3.10 && conda activate sal
```
```shell
pip install -e '.[dev]'
```


## Replicating Scaling Test Time Compute results:
The [recipes readme](recipes/README.md) includes launch commands and config files in order to replicate our results.


## Citation
If you use this codebase or the blogpost it would be great if you could cite us:
```
@misc{beeching2024scalingtesttimecompute,
      title={Scaling test-time compute with open models},
      author={Edward Beeching and Lewis Tunstall and Sasha Rush},
      url={https://huggingface.co/spaces/HuggingFaceH4/blogpost-scaling-test-time-compute},
}
```
Please also cite this work:
```
@misc{snell2024scalingllmtesttimecompute,
      title={Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters}, 
      author={Charlie Snell and Jaehoon Lee and Kelvin Xu and Aviral Kumar},
      year={2024},
      eprint={2408.03314},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2408.03314}, 
}
```

