Spaces:
Runtime error
Runtime error
VenkateshRoshan
commited on
Commit
·
1d92a29
1
Parent(s):
9f203ff
app and dockerfile for hf added
Browse files- README.md +1 -18
- app_hf.py +1 -1
- dockerfile_hf +3 -3
README.md
CHANGED
@@ -12,23 +12,6 @@ pinned: false
|
|
12 |
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
13 |
|
14 |
# Real Time Customer Support Chatbot
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
# Hugging Face Model Deployment with Docker
|
19 |
-
|
20 |
-
This repository contains a Dockerized setup for deploying a Hugging Face model. The `dockerfile_hf` file defines the environment to build and run the application.
|
21 |
-
|
22 |
-
## Table of Contents
|
23 |
-
- [Project Overview](#project-overview)
|
24 |
-
- [Setup](#setup)
|
25 |
-
- [Docker Usage](#docker-usage)
|
26 |
-
- [Running the Container](#running-the-container)
|
27 |
-
- [Model Inference](#model-inference)
|
28 |
-
- [License](#license)
|
29 |
-
|
30 |
-
## Project Overview
|
31 |
-
|
32 |
---
|
33 |
### Developing a real-time customer support chatbot using a fine-tuned LLM to provide accurate responses. Building CI/CD pipelines for scalable deployment on AWS SageMaker and integrating MLflow for tracking model versions, experiment logging, and continuous improvements.
|
34 |
-
---
|
|
|
12 |
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
13 |
|
14 |
# Real Time Customer Support Chatbot
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
---
|
16 |
### Developing a real-time customer support chatbot using a fine-tuned LLM to provide accurate responses. Building CI/CD pipelines for scalable deployment on AWS SageMaker and integrating MLflow for tracking model versions, experiment logging, and continuous improvements.
|
17 |
+
---
|
app_hf.py
CHANGED
@@ -192,7 +192,7 @@ if __name__ == "__main__":
|
|
192 |
demo = create_chat_interface()
|
193 |
print("Starting Gradio server...")
|
194 |
demo.launch(
|
195 |
-
share=
|
196 |
server_name="0.0.0.0",
|
197 |
server_port=7860, # Changed to 7860 for Gradio
|
198 |
debug=True,
|
|
|
192 |
demo = create_chat_interface()
|
193 |
print("Starting Gradio server...")
|
194 |
demo.launch(
|
195 |
+
share=False,
|
196 |
server_name="0.0.0.0",
|
197 |
server_port=7860, # Changed to 7860 for Gradio
|
198 |
debug=True,
|
dockerfile_hf
CHANGED
@@ -2,10 +2,10 @@ FROM python3.10-slim
|
|
2 |
|
3 |
WORKDIR /app
|
4 |
|
5 |
-
COPY app_hf.py
|
6 |
-
COPY src/
|
7 |
-
|
8 |
COPY requirements.txt .
|
|
|
9 |
RUN pip install --no-cache-dir --upgrade pip
|
10 |
RUN pip install --no-cache-dir torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 --index-url https://download.pytorch.org/whl/cu121
|
11 |
RUN pip install --no-cache-dir -r requirements.txt
|
|
|
2 |
|
3 |
WORKDIR /app
|
4 |
|
5 |
+
COPY app_hf.py .
|
6 |
+
COPY src/ .
|
|
|
7 |
COPY requirements.txt .
|
8 |
+
|
9 |
RUN pip install --no-cache-dir --upgrade pip
|
10 |
RUN pip install --no-cache-dir torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 --index-url https://download.pytorch.org/whl/cu121
|
11 |
RUN pip install --no-cache-dir -r requirements.txt
|