Added spaces code

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,13 @@
+---
+title: Law LM
+emoji: 💬
+colorFrom: yellow
+colorTo: purple
+sdk: gradio
+app_file: app.py
+pinned: false
+license: llama3
+---
+
+# About
+Law Language Model is an RAG (**Retrieval Augmented Generation**) based LLM (**Large Language Model**) application that is used to solve one of the complex problem that is understanding **LAW** of India. As of now there is no availability for a common man in India to learn or know about Law. So this project's aim to provide a clarification of India Law with the implementation of RAG based LLM.

.ipynb_checkpoints/app-checkpoint.py

@@ -0,0 +1,58 @@
+import gradio as gr
+from huggingface_hub import InferenceClient
+import spaces
+
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+
+@spaces.GPU
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
+    messages = [{"role": "system", "content": system_message}]
+
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
+
+    messages.append({"role": "user", "content": message})
+
+    response = ""
+
+    for message in client.chat_completion(
+        messages,
+        max_tokens=max_tokens,
+        stream=True,
+        temperature=temperature,
+        top_p=top_p,
+    ):
+        token = message.choices[0].delta.content
+
+        response += token
+        yield response
+
+demo = gr.ChatInterface(
+    respond,
+    additional_inputs=[
+        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+        gr.Slider(
+            minimum=0.1,
+            maximum=1.0,
+            value=0.95,
+            step=0.05,
+            label="Top-p (nucleus sampling)",
+        ),
+    ],
+)
+
+
+if __name__ == "__main__":
+    demo.launch()

.ipynb_checkpoints/requirements-checkpoint.txt

@@ -0,0 +1,2 @@
+huggingface_hub==0.22.2
+spaces

README.md

@@ -9,4 +9,5 @@ pinned: false
 license: llama3
 ---
 
-An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).
+# About
+Law Language Model is an RAG (**Retrieval Augmented Generation**) based LLM (**Large Language Model**) application that is used to solve one of the complex problem that is understanding **LAW** of India. As of now there is no availability for a common man in India to learn or know about Law. So this project's aim to provide a clarification of India Law with the implementation of RAG based LLM.

app.py

@@ -1,12 +1,10 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+import spaces
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
-
+@spaces.GPU
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -39,9 +37,6 @@ def respond(
         response += token
         yield response
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[

requirements.txt

@@ -1 +1,2 @@
-huggingface_hub==0.22.2
+huggingface_hub==0.22.2
+spaces