Random trial

Dockerfile

@@ -0,0 +1,31 @@
+# Use Python 3.10 as base image
+FROM python:3.10-slim
+
+# Set working directory
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    git \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy requirements first to leverage Docker cache
+COPY requirements.txt .
+
+# Install Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the rest of the application
+COPY . .
+
+# Expose the port Gradio will run on
+EXPOSE 7860
+
+# Set environment variables
+ENV PYTHONUNBUFFERED=1
+ENV GRADIO_SERVER_NAME=0.0.0.0
+ENV GRADIO_SERVER_PORT=7860
+
+# Run the application
+CMD ["python", "app.py"]

app.py

@@ -0,0 +1,78 @@
+import gradio as gr
+from huggingface_hub import InferenceClient
+from transformers import TextStreamer
+from peft import AutoPeftModelForCausalLM
+from transformers import AutoTokenizer
+
+
+"""
+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
+"""
+
+model_name_or_path = "samlama111/lora_model"
+
+# client = InferenceClient(model_name_or_path)
+model = AutoPeftModelForCausalLM.from_pretrained(
+    model_name_or_path, # YOUR MODEL YOU USED FOR TRAINING
+    load_in_4bit = True,
+    device_map = "auto",
+)
+tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
+
+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 = ""
+    
+    inputs = tokenizer.apply_chat_template(messages, tokenize = True, add_generation_prompt = True, return_tensors = "pt")
+
+    text_streamer = TextStreamer(tokenizer)
+    # TODO: Doesn't stream ATM
+    for message in model.generate(input_ids = inputs, streamer = text_streamer, max_new_tokens = 1024, use_cache = True):
+        # Decode the tensor to a string
+        decoded_message = tokenizer.decode(message, skip_special_tokens=True)
+        
+        # Manually getting the response
+        response = decoded_message.split("assistant")[-1].strip()  # Extract only the assistant's response
+        print(response)
+
+        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=[
+        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()

requirements.txt

@@ -0,0 +1,5 @@
+huggingface_hub==0.26.2
+gradio
+https://github.com/bitsandbytes-foundation/bitsandbytes/releases/download/continuous-release_multi-backend-refactor/bitsandbytes-0.44.1.dev0-py3-none-manylinux_2_24_x86_64.whl
+transformers
+peft