Add Transformers.js library tag and sample code

README.md

@@ -11,51 +11,68 @@ language:
 library_name: transformers
 tags:
 - text2text-generation
+- transformers.js
 widget:
 - text: >-
-    Teapot is an open-source small language model (~800 million parameters) fine-tuned on synthetic data and optimized to run locally on resource-constrained devices such as smartphones and CPUs.
-    Teapot is trained to only answer using context from documents, reducing hallucinations.
-    Teapot can perform a variety of tasks, including hallucination-resistant Question Answering (QnA), Retrieval-Augmented Generation (RAG), and JSON extraction.
-    TeapotLLM is a fine tune of flan-t5-large that was trained on synthetic data generated by Deepseek v3
-    TeapotLLM can be hosted on low-power devices with as little as 2GB of CPU RAM such as a Raspberry Pi.
-    Teapot is a model built by and for the community.
+    Teapot is an open-source small language model (~800 million parameters)
+    fine-tuned on synthetic data and optimized to run locally on
+    resource-constrained devices such as smartphones and CPUs. Teapot is trained
+    to only answer using context from documents, reducing hallucinations. Teapot
+    can perform a variety of tasks, including hallucination-resistant Question
+    Answering (QnA), Retrieval-Augmented Generation (RAG), and JSON extraction.
+    TeapotLLM is a fine tune of flan-t5-large that was trained on synthetic data
+    generated by Deepseek v3 TeapotLLM can be hosted on low-power devices with
+    as little as 2GB of CPU RAM such as a Raspberry Pi. Teapot is a model built
+    by and for the community.
 
 
     What devices can teapot run on?
   example_title: Question Answering
 - text: >-
-    Teapot is an open-source small language model (~800 million parameters) fine-tuned on synthetic data and optimized to run locally on resource-constrained devices such as smartphones and CPUs.
-    Teapot is trained to only answer using context from documents, reducing hallucinations.
-    Teapot can perform a variety of tasks, including hallucination-resistant Question Answering (QnA), Retrieval-Augmented Generation (RAG), and JSON extraction.
-    TeapotLLM is a fine tune of flan-t5-large that was trained on synthetic data generated by Deepseek v3
-    TeapotLLM can be hosted on low-power devices with as little as 2GB of CPU RAM such as a Raspberry Pi.
-    Teapot is a model built by and for the community.
+    Teapot is an open-source small language model (~800 million parameters)
+    fine-tuned on synthetic data and optimized to run locally on
+    resource-constrained devices such as smartphones and CPUs. Teapot is trained
+    to only answer using context from documents, reducing hallucinations. Teapot
+    can perform a variety of tasks, including hallucination-resistant Question
+    Answering (QnA), Retrieval-Augmented Generation (RAG), and JSON extraction.
+    TeapotLLM is a fine tune of flan-t5-large that was trained on synthetic data
+    generated by Deepseek v3 TeapotLLM can be hosted on low-power devices with
+    as little as 2GB of CPU RAM such as a Raspberry Pi. Teapot is a model built
+    by and for the community.
 
 
     Tell me about teapotllm 
   example_title: Summarization Answering
 - text: >-
-    Teapot is an open-source small language model (~800 million parameters) fine-tuned on synthetic data and optimized to run locally on resource-constrained devices such as smartphones and CPUs.
-    Teapot is trained to only answer using context from documents, reducing hallucinations.
-    Teapot can perform a variety of tasks, including hallucination-resistant Question Answering (QnA), Retrieval-Augmented Generation (RAG), and JSON extraction.
-    TeapotLLM is a fine tune of flan-t5-large that was trained on synthetic data generated by Deepseek v3
-    TeapotLLM can be hosted on low-power devices with as little as 2GB of CPU RAM such as a Raspberry Pi.
-    Teapot is a model built by and for the community.
+    Teapot is an open-source small language model (~800 million parameters)
+    fine-tuned on synthetic data and optimized to run locally on
+    resource-constrained devices such as smartphones and CPUs. Teapot is trained
+    to only answer using context from documents, reducing hallucinations. Teapot
+    can perform a variety of tasks, including hallucination-resistant Question
+    Answering (QnA), Retrieval-Augmented Generation (RAG), and JSON extraction.
+    TeapotLLM is a fine tune of flan-t5-large that was trained on synthetic data
+    generated by Deepseek v3 TeapotLLM can be hosted on low-power devices with
+    as little as 2GB of CPU RAM such as a Raspberry Pi. Teapot is a model built
+    by and for the community.
 
 
     Extract the number of parameters
   example_title: Information Extraction
 - text: >-
-    Teapot is an open-source small language model (~800 million parameters) fine-tuned on synthetic data and optimized to run locally on resource-constrained devices such as smartphones and CPUs.
-    Teapot is trained to only answer using context from documents, reducing hallucinations.
-    Teapot can perform a variety of tasks, including hallucination-resistant Question Answering (QnA), Retrieval-Augmented Generation (RAG), and JSON extraction.
-    TeapotLLM is a fine tune of flan-t5-large that was trained on synthetic data generated by Deepseek v3
-    TeapotLLM can be hosted on low-power devices with as little as 2GB of CPU RAM such as a Raspberry Pi.
-    Teapot is a model built by and for the community.
+    Teapot is an open-source small language model (~800 million parameters)
+    fine-tuned on synthetic data and optimized to run locally on
+    resource-constrained devices such as smartphones and CPUs. Teapot is trained
+    to only answer using context from documents, reducing hallucinations. Teapot
+    can perform a variety of tasks, including hallucination-resistant Question
+    Answering (QnA), Retrieval-Augmented Generation (RAG), and JSON extraction.
+    TeapotLLM is a fine tune of flan-t5-large that was trained on synthetic data
+    generated by Deepseek v3 TeapotLLM can be hosted on low-power devices with
+    as little as 2GB of CPU RAM such as a Raspberry Pi. Teapot is a model built
+    by and for the community.
 
 
     How many parameters is Deepseek? 
-  example_title: Hallucination Resistance 
+  example_title: Hallucination Resistance
 base_model:
 - google/flan-t5-large
 pipeline_tag: text2text-generation
@@ -264,6 +281,25 @@ answer = teapot_ai(context+"\n"+question)
 print(answer[0].get('generated_text')) # => The Eiffel Tower stands at a height of 330 meters.
 ```
 
+### Transformers.js Support
+
+You can even run the model in-browser (or any other JavaScript environment) with [Transformers.js](https://huggingface.co/docs/transformers.js) as follows:
+
+```js
+// npm i @huggingface/transformers
+import { pipeline } from "@huggingface/transformers";
+
+const teapot_ai = await pipeline("text2text-generation", "teapotai/teapotllm");
+
+const context = `
+The Eiffel Tower is a wrought iron lattice tower in Paris, France. It was designed by Gustave Eiffel and completed in 1889.
+It stands at a height of 330 meters and is one of the most recognizable structures in the world.
+`;
+const question = "What is the height of the Eiffel Tower?";
+const answer = await teapot_ai(context + "\n" + question);
+console.log(answer[0].generated_text); // => " The Eiffel Tower stands at a height of 330 meters."
+```
+
 ---