| | --- |
| | inference: false |
| | --- |
| | |
| | # Robin Model Card |
| |
|
| | ## Model Details |
| |
|
| | Robin is a series of models finetuned from LLaMA on several high-quality data. |
| |
|
| | - **Developed by:** [LMFlow](https://github.com/OptimalScale/LMFlow/) |
| | - **Model type:** An auto-regressive language model based on the transformer architecture. |
| | - **License:** Non-commercial license |
| | - **Finetuned from model:** [LLaMA](https://arxiv.org/abs/2302.13971). |
| |
|
| | ### Model Sources |
| |
|
| | - **Repository:** https://github.com/OptimalScale/LMFlow/ |
| | - **Blog:** https://medium.com/@hkust.ml/robin-v2-launches-achieves-unparalleled-performance-on-openllm-4f6886e822c1 |
| | - **Paper:** https://arxiv.org/abs/2306.12420 |
| | - **Demo:** https://lmflow.com/ |
| |
|
| | ## Uses |
| |
|
| | Robin is primarily utilized for conducting research on extensive language models and chatbots, catering to users specializing in natural language processing, machine learning, and artificial intelligence research. |
| |
|
| | ## How to Get Started with the Model |
| |
|
| | We provide four kinds of demos including: |
| |
|
| | - Online Service: If you don't want to run any code and just want to try our models, we deploy our instruction-tuned LLaMA you to have a try. |
| | - Colab Chatbot (shell): An interactive shell-based chatbot for you to easily deploy a chatbot on colab. |
| | - Colab Chatbot (web): An interactive web-based chatbot for you to easily deploy your own chatbot on colab. |
| | - Local Deploy: We also provide a way for you to deploy your model/chatbot locally, which means you can deploy much larger model than previous three methods if you have enough resource. |
| |
|
| | Please refer to https://github.com/OptimalScale/LMFlow#demos |
| |
|
| | ## Training Details |
| |
|
| |
|
| | Expanding upon the initial idea of self-instruct techniques, we incorporated several different data sources and build a new dataset called [LMFlow Dataset](http://lmflow.org:5000/lmflow_data.tar.gz). |
| | The new training split is created by merging the following datasets: |
| | - ShareGPT: randomly sample 50K English data and 10K Chinese data from ShareGPT. |
| | - GPT-4-LLM: 52K English data from GPT-4-LLM. |
| | - BELLE: randomly sample 80K Chinese data from BELLE. |
| |
|
| | See more details in the "Instruction Tuning" section in our [paper](https://arxiv.org/pdf/2306.12420.pdf). |
| |
|
| | ## Evaluation |
| |
|
| | Robin is evaluated with [LMFlow Benchmark](https://blog.gopenai.com/lmflow-benchmark-an-automatic-evaluation-framework-for-open-source-llms-ef5c6f142418). |
| | See more details in this [paper](https://arxiv.org/pdf/2306.12420.pdf). |
| |
|
| | ## Citation |
| | If you find this repository useful, please consider giving ⭐ and citing our [paper](https://arxiv.org/abs/2306.12420): |
| |
|
| | ``` |
| | @misc{lmflow, |
| | author = {Shizhe Diao and Rui Pan and Hanze Dong and KaShun Shum and Jipeng Zhang and Wei Xiong and Tong Zhang}, |
| | title = {LMFlow: An Extensible Toolkit for Finetuning and Inference of Large Foundation Models}, |
| | year = {2023}, |
| | publisher = {GitHub}, |
| | journal = {GitHub repository}, |
| | howpublished = {\url{https://optimalscale.github.io/LMFlow/}}, |
| | } |
| | ``` |
