allenai/open-instruct-llama2-sharegpt-dpo-7b

Model Card for Open Instruct ShareGPT DPO Llama2 7B

This model belongs to the Tulu series of models, which is a series of language models that are trained to act as helpful assistants. Open Instruct ShareGPT Llama2 7B is initially fine-tuned version of Llama 2 that was trained on the ShareGPT dataset. The model was then further trained on the UltraFeedback dataset using Direct Preference Optimization (DPO).

For more details, read the paper: Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2 .

Model description

• Model type: A model belonging to a suite of instruction and RLHF tuned chat models on a mix of publicly available, synthetic and human-created datasets.
• Language(s) (NLP): Primarily English
• License: AI2 ImpACT Low-risk license.
• Finetuned from model: meta-llama/Llama-2-7b-hf

Model Sources

• Repository: https://github.com/allenai/https://github.com/allenai/open-instruct
• Model Family: Other models and the dataset are found in the Tulu V2 collection.

Input Format

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.

Intended uses & limitations

The model was 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.

Bias, Risks, and Limitations

The Tulu models have not been aligned to generate safe completions within the RLHF phase or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so). It is also unknown what the size and composition of the corpus was used to train the base Llama 2 models, however it is likely to have included a mix of Web data and technical sources like books and code. See the Falcon 180B model card for an example of this.

Training hyperparameters

The following hyperparameters were used during DPO training:

• learning_rate: 5e-07
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3.0

Citation

If you find this model is useful in your work, please cite it with:

@misc{ivison2023camels,
      title={Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2}, 
      author={Hamish Ivison and Yizhong Wang and Valentina Pyatkin and Nathan Lambert and Matthew Peters and Pradeep Dasigi and Joel Jang and David Wadden and Noah A. Smith and Iz Beltagy and Hannaneh Hajishirzi},
      year={2023},
      eprint={2311.10702},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

Model card adapted from Zephyr Beta