Downloads · 30 days
10
2% of all-time downloads
hamishivi/tulu-v2.5-7b-uf-mean-7b-uf-rm-value
tulu-v2.5-7b-uf-mean-7b-uf-rm-value is a token classification model from hamishivi. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as apache-2.0.
<center <img src="https://huggingface.co/datasets/allenai/blog-images/resolve/main/tulu-2.5/tulu25banner.png" alt="Tulu 2.5 banner image" width="800px"/ </center
Downloads · 30 days
10
2% of all-time downloads
All-time downloads
510
Public
Parameters
6.6B
13.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors13.2 GB · 100%
From the Hugging Face model README
Tulu is a series of language models that are trained to act as helpful assistants. Tulu V2.5 is a series of models trained using DPO and PPO starting from the Tulu 2 suite. This is a value model produced during the PPO training of this model. It was initialised from the Tulu v2.5 7B UltraFeedback RM. We release the value model as it may provide a good starting point for additional research or improved decoding with our released PPO models.
At time of writing, you may have to install transformers from source to get the LlamaForTokenClassification class.
For more details, read the paper: Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback.
ultrafeedback_mean_aspects split.The model is trained to use the following format (note the newlines):
<|user|>
Your message here!
<|assistant|>
For best results, format all inputs in this manner. Make sure to include a newline after <|assistant|>, this can affect generation quality quite a bit.
We have included a chat template in the tokenizer implementing this template.
The model was initially fine-tuned on a filtered and preprocessed of the Tulu V2 mix dataset, which contains a diverse range of human created instructions and synthetic dialogues generated primarily by other LLMs. We then further trained the model with a Jax PPO trainer built on EasyLM on the dataset mentioned above. This model is meant as a research artefact.
The following hyperparameters were used during overall PPO training:
If you find Tulu 2.5 is useful in your work, please cite it with:
@misc{ivison2024unpacking,
title={{Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback}},
author={{Hamish Ivison and Yizhong Wang and Jiacheng Liu and Ellen Wu and Valentina Pyatkin and Nathan Lambert and Yejin Choi and Noah A. Smith and Hannaneh Hajishirzi}}
year={2024},
eprint={2406.09279},
archivePrefix={arXiv},
primaryClass={cs.CL}
}