Files
Olmo-HH-Helpful/README.md
ModelHub XC c0df53c329 初始化项目,由ModelHub XC社区提供模型
Model: xiaoqingsun004/Olmo-HH-Helpful
Source: Original Platform
2026-08-09 09:31:19 +08:00

21 lines
721 B
Markdown

---
library_name: transformers
datasets:
- Anthropic/hh-rlhf
base_model:
- allenai/Olmo-3-7B-Instruct-SFT
---
# Model Card for Model ID
allenai/Olmo-3-7B-Instruct-SFT further finetuned using DPO on Anthropic/hh-rlhf helpful-base.
We also train four variants, see subfolders: project dataset along "Gender equity" and "Methodical rigor", and train on only top (50-100) or bottom (0-50) half of the dataset.
## Training Details
For the exact 52k dataset used, see data_hf.csv in repo.
Open-instruct (https://github.com/allenai/open-instruct), same training setup as in Olmo-3 (https://arxiv.org/abs/2512.13961).
## Accompanying Blog Post
https://www.lesswrong.com/posts/b8u6XrphyHAXA4hBi/where-do-llm-values-come-from