Create README.md

README.md

@@ -0,0 +1,62 @@
+---
+license: cc-by-sa-3.0
+datasets:
+- mosaicml/dolly_hhrlhf
+tags:
+- Composer
+- MosaicML
+- llm-foundry
+---
+
+# MPT-7B-Chat
+
+MPT-7B-Chat is a chatbot-like model for dialogue generation.
+It is built by finetuning [MPT-7B](https://huggingface.co/spaces/mosaicml/mpt-7b) on the [ShareGPT-Vicuna](https://huggingface.co/datasets/jeffwan/sharegpt_vicuna), [HC3](https://huggingface.co/datasets/Hello-SimpleAI/HC3),
+ [Alpaca](https://huggingface.co/datasets/tatsu-lab/alpaca), [HH-RLHF](https://huggingface.co/datasets/Anthropic/hh-rlhf), and [Evol-Instruct](https://huggingface.co/datasets/victor123/evol_instruct_70k) datasets.
+  * License: _CC-By-NC-SA-4.0_ (non-commercial use only)
+  * [Demo on Hugging Face Spaces](https://huggingface.co/spaces/mosaicml/mpt-7b-chat)
+
+
+This model was trained by [MosaicML](https://www.mosaicml.com) and follows a modified decoder-only transformer architecture.
+
+## Model Date
+
+May 5, 2023
+
+## Model License
+
+Apache-2.0 (commercial use permitted)
+
+## Documentation
+
+* [Blog post: Introducing MPT-7B: A New Standard for Open-Source, Commercially Usable LLMs](www.mosaicml.com/blog/mpt-7b)
+* [Codebase (mosaicml/llm-foundry repo)](https://github.com/mosaicml/llm-foundry/)
+* Questions: Feel free to contact us via the [MosaicML Community Slack](https://join.slack.com/t/mosaicml-community/shared_invite/zt-w0tiddn9-WGTlRpfjcO9J5jyrMub1dg)!
+
+### Example Dialogue
+
+**SamIAm85**:
+>I want you to come up with a tweet based on this summary of the article:
+>"Introducing MPT-7B, the latest entry in our MosaicML Foundation Series.
+>MPT-7B is a transformer trained from scratch on IT tokens of text and code.
+>It is open source, available for commercial use, and it matches the quality of LLaMA-7B.
+>MPT-7B was trained on the MosaicML platform in 9.5 days with zero human intervention at a cost of ~$200k.
+>Starting today, you can train, finetune, and deploy your own private MPT models, either starting from one of our checkpoints or training from scratch.
+>For inspiration, we are also releasing three finetuned models in addition to the base MPT-7B: MPT-7B-Instruct, MPT-7B-Chat, and MPT-7B-Story Writer-65k+, the last of which uses a context length of 65k tokens!
+
+**MPT-7B-Instruct**:
+>Here's my suggestion for a tweet:
+>"Exciting news! @MosaicML has launched #MPT_7B - a new standard for open-source, commercially usable LLMs. With training on 17 tokens of text & code, it matches the quality of LLaMA-7B. Now you can train, fine-tune, and deploy your own private MPT models via their platform. Check out the full blog post here: https://bit.ly/3j6UJzZ"
+
+**SamIAm85**:
+>Is there anything you want to say to MosaicML about this exciting news?
+
+**MPT-7B-Instruct**:
+> As an Al language model myself, I am very impressed with the advancements made by MosaicML in developing such high-quality open-source LLMs.
+> This new version of MPT-7B is truly impressive and I look forward to seeing what innovative applications developers will create using these powerful tools.
+> Thank you for your hard work and dedication to advancing Al research and development.
+
+
+## Acknowledgements
+
+This model was finetuned by Sam Havens