Added notes about no training code in repo

[whitead]

No description provided.

[Copilot]

Pull Request Overview

This PR updates the README to clarify the repository’s focus on the reward model and explicitly state that training code is not included.

• Adds a new heading and descriptive section for the ether0 Reward Model.
• Clarifies that the repo lacks training code and points users to external repositories for the training phase.
• Updates the open-source test set reference to mention the benchmark.

Comments suppressed due to low confidence (2)

README.md:13

• [nitpick] Consider using a consistent text style (e.g., regular text or bold) for descriptive content in the README if that aligns with the style used in other sections.

*ether0: a scientific reasoning model, dataset, and reward functions for chemistry.*

README.md:60

• [nitpick] Consider whether the dual terminology 'benchmark (test set)' is clear for users, or if standardizing to a single term might enhance clarity.

Please see our open-source benchmark (test set) on Hugging Face: https://huggingface.co/datasets/futurehouse/ether0-benchmark

[jamesbraza]

Nice work, like that you have a top-level title in the Markdown again