Models and datasets to align LLMs with Odds Ratio Preference Optimisation (ORPO). Recipes here: https://github.com/huggingface/alignment-handbook
Hugging Face H4
Enterprise
company
AI & ML interests
Aligning LLMs to be helpful, honest, harmless, and huggy (H4)
Organization Card
Hello world!
We're the Hugging Face H4 team, focused on aligning language models to be helpful, honest, harmless, and huggy 🤗.
models
30
HuggingFaceH4/zephyr-7b-alpha
Text Generation
•
Updated
•
26.7k
•
•
1.1k
HuggingFaceH4/zephyr-7b-beta
Text Generation
•
Updated
•
543k
•
•
1.61k
HuggingFaceH4/mistral-7b-sft-beta
Text Generation
•
Updated
•
11.5k
•
24
HuggingFaceH4/sft-llava-1.5-7b-hf
Updated
•
6
HuggingFaceH4/EleutherAI_pythia-6.9b-deduped__sft__tldr
Text Generation
•
Updated
•
10
HuggingFaceH4/dummy-repo-without-revision-e0c007b1-25d2-4527-b8ec-c6f54821a847
Updated
HuggingFaceH4/dummy-repo-with-revision-5d2f53d0-61c1-4943-ba1c-68ec8507051b
Updated
HuggingFaceH4/dummy-repo-with-revision-b961bb0f-8012-48f9-8bcc-8373d10e3868
Updated
HuggingFaceH4/dummy-repo-without-revision-46fd598b-6792-48e0-9c14-fe86fc035183
Updated
HuggingFaceH4/dummy-repo-with-revision-00a840ca-835f-4370-a2d7-6cb15e1fbdfa
Updated
datasets
71
HuggingFaceH4/MATH-500
Viewer
•
Updated
•
500
•
244
HuggingFaceH4/ultrachat_200k
Viewer
•
Updated
•
515k
•
12.6k
•
477
HuggingFaceH4/ultrafeedback_binarized
Viewer
•
Updated
•
187k
•
6.29k
•
244
HuggingFaceH4/ifeval-like-data
Viewer
•
Updated
•
5.61k
•
104
HuggingFaceH4/10k_prompts_ranked
Viewer
•
Updated
•
10.3k
•
112
•
2
HuggingFaceH4/testing_h4
Viewer
•
Updated
•
70
•
114
HuggingFaceH4/Magpie-Pro-DPO-100K-v0.1-Prompts
Viewer
•
Updated
•
100k
•
52
•
1
HuggingFaceH4/test-cot
Viewer
•
Updated
•
1.32k
•
45
HuggingFaceH4/rlaif-v_formatted
Viewer
•
Updated
•
83.1k
•
251
•
3
HuggingFaceH4/no_robots
Viewer
•
Updated
•
10k
•
1.54k
•
451