Upload 3 files

Dockerfile

@@ -1,60 +1,17 @@
-FROM ghcr.io/huggingface/chat-ui:latest AS base
+FROM python:3.9-slim
 
-FROM ghcr.io/huggingface/text-generation-inference:latest AS final
+# Set working directory
+WORKDIR /app
 
-ARG MODEL_NAME
-ENV MODEL_NAME=${MODEL_NAME}
+# Copy the application files
+COPY app.py /app
+COPY requirements.txt /app
 
-ENV TZ=Europe/Paris \
-    PORT=3000
+# Install required Python libraries
+RUN pip install --no-cache-dir -r requirements.txt
 
-# mongo installation
-RUN curl -fsSL https://www.mongodb.org/static/pgp/server-7.0.asc | \
-    gpg -o /usr/share/keyrings/mongodb-server-7.0.gpg \
-   --dearmor
+# Expose the default Gradio port
+EXPOSE 7860
 
-RUN echo "deb [ arch=amd64,arm64 signed-by=/usr/share/keyrings/mongodb-server-7.0.gpg ] https://repo.mongodb.org/apt/ubuntu jammy/mongodb-org/7.0 multiverse" | tee /etc/apt/sources.list.d/mongodb-org-7.0.list
-
-RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
-    mongodb-org && \
-    rm -rf /var/lib/apt/lists/*
-
-# node installation
-RUN curl -fsSL https://deb.nodesource.com/setup_20.x | /bin/bash -
-
-RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
-    nodejs && \
-    rm -rf /var/lib/apt/lists/*
-
-# image setup
-RUN useradd -m -u 1000 user
-
-RUN mkdir /app
-RUN chown -R 1000:1000 /app
-RUN mkdir /data
-RUN chown -R 1000:1000 /data
-
-# Switch to the "user" user
-USER user
-
-ENV HOME=/home/user \
-    PATH=/home/user/.local/bin:$PATH
-
-RUN npm config set prefix /home/user/.local
-RUN npm install -g dotenv-cli
-
-
-# copy chat-ui from base image
-COPY --from=base --chown=1000 /app/node_modules /app/node_modules
-COPY --from=base --chown=1000 /app/package.json /app/package.json
-COPY --from=base --chown=1000 /app/build /app/build
-
-COPY --from=base --chown=1000 /app/.env /app/.env
-COPY --chown=1000 .env.local /app/.env.local
-
-COPY --chown=1000 entrypoint.sh /app/entrypoint.sh
-
-RUN chmod +x /app/entrypoint.sh
-
-# entrypoint
-ENTRYPOINT [ "/app/entrypoint.sh" ]
+# Run the application
+CMD ["python", "app.py"]

app.py

@@ -0,0 +1,77 @@
+import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from vllm import LLMEngine, SamplingParams
+
+# Load the model and tokenizer from Hugging Face
+model_name = "Qwen/Qwen2-7B"  
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+engine = LLMEngine(model=model_name)
+
+def generate_response(prompt, max_tokens, temperature, top_p):
+    # Tokenize the prompt
+    inputs = tokenizer(prompt, return_tensors="pt")
+    
+    # Define sampling parameters
+    sampling_params = SamplingParams(
+        max_tokens=max_tokens,
+        temperature=temperature,
+        top_p=top_p,
+    )
+    
+    # Generate text using vLLM
+    output = engine.generate(inputs["input_ids"], sampling_params)
+    
+    # Decode the generated tokens to text
+    generated_text = tokenizer.decode(output[0]["token_ids"], skip_special_tokens=True)
+    return generated_text
+
+# Gradio UI
+with gr.Blocks() as demo:
+    gr.Markdown("# 🚀 Hugging Face Integration with vLLM")
+    gr.Markdown("Generate text using the vLLM integration with Hugging Face models.")
+
+    with gr.Row():
+        with gr.Column():
+            prompt_input = gr.Textbox(
+                label="Prompt",
+                placeholder="Enter your prompt here...",
+                lines=3,
+            )
+            max_tokens = gr.Slider(
+                label="Max Tokens",
+                minimum=10,
+                maximum=500,
+                value=100,
+                step=10,
+            )
+            temperature = gr.Slider(
+                label="Temperature",
+                minimum=0.1,
+                maximum=1.0,
+                value=0.7,
+                step=0.1,
+            )
+            top_p = gr.Slider(
+                label="Top P",
+                minimum=0.1,
+                maximum=1.0,
+                value=0.9,
+                step=0.1,
+            )
+            submit_button = gr.Button("Generate")
+        
+        with gr.Column():
+            output_text = gr.Textbox(
+                label="Generated Text",
+                lines=10,
+                interactive=False,
+            )
+    
+    submit_button.click(
+        generate_response,
+        inputs=[prompt_input, max_tokens, temperature, top_p],
+        outputs=output_text,
+    )
+
+# Launch the app
+demo.launch()

requirements.txt

@@ -0,0 +1,3 @@
+gradio==3.33.1
+vllm
+transformers