Update README.md
Browse files
README.md
CHANGED
@@ -53,7 +53,7 @@ pipeline_tag: text2text-generation
|
|
53 |
|
54 |
[Website](https://teapotai.com/) | [Demo](https://huggingface.co/spaces/teapotai/teapotchat) | [Discord](https://discord.gg/hPxGSn5dST)
|
55 |
|
56 |
-
|
57 |
|
58 |
## Getting Started
|
59 |
We recommend using our library [teapotai](https://pypi.org/project/teapotai/) to quickly integrate our models into production environments, as it handles the overhead of model configuration, document embeddings, error handling and prompt formatting. However, you can directly use the model from the transformers library on huggingface.
|
|
|
53 |
|
54 |
[Website](https://teapotai.com/) | [Demo](https://huggingface.co/spaces/teapotai/teapotchat) | [Discord](https://discord.gg/hPxGSn5dST)
|
55 |
|
56 |
+
Teapot is a small open-source language model (~300 million parameters) fine-tuned on synthetic data and optimized to run locally on resource-constrained devices such as smartphones and CPUs. Teapot can perform a variety of tasks, including hallucination-resistant Question Answering (QnA), Retrieval-Augmented Generation (RAG), and JSON extraction. Teapot is a model built by and for the community.
|
57 |
|
58 |
## Getting Started
|
59 |
We recommend using our library [teapotai](https://pypi.org/project/teapotai/) to quickly integrate our models into production environments, as it handles the overhead of model configuration, document embeddings, error handling and prompt formatting. However, you can directly use the model from the transformers library on huggingface.
|