Upload folder using huggingface_hub

README.md

@@ -1,12 +1,63 @@
----
-title: Amkyaw Coder
-emoji: 🦀
-colorFrom: blue
-colorTo: yellow
-sdk: gradio
-sdk_version: 6.12.0
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# amkyawdev/amkyaw-dev-v1
+
+## Model Overview
+
+- **Model Name**: amkyaw-coder-1.5b-instruct
+- **Type**: Code Generation / Instruction Following
+- **Size**: 1.5B parameters
+- **Format**: GGUF (quantized)
+
+## Quick Start
+
+```bash
+# Run the model
+ollama run amkyawdev/amkyaw-dev-v1
+
+# Or run with specific tag
+ollama run amkyawdev/amkyaw-dev-v1:latest
+```
+
+## Features
+
+- Code generation
+- Instruction following
+- Burmese language support
+- English language support
+
+## System Requirements
+
+- Ollama installed
+- At least 2GB RAM available
+- No GPU required (runs on CPU)
+
+## Configuration
+
+| Parameter | Value |
+|-----------|-------|
+| Temperature | 0.8 |
+| Top P | 0.9 |
+| Top K | 40 |
+| Context Length | 4096 |
+
+## Usage Examples
+
+```python
+import ollama
+
+response = ollama.generate(
+    model='amkyawdev/amkyaw-dev-v1',
+    prompt='Write a Python function to calculate factorial'
+)
+print(response['response'])
+```
+
+## License
+
+See [Hugging Face](https://huggingface.co/amkyawdev/amkyaw-dev-v1) for license information.
+
+## Troubleshooting
+
+If you encounter issues:
+1. Make sure Ollama is running: `ollama serve`
+2. Check model is installed: `ollama list`
+3. Try restarting Ollama: `pkill ollama && ollama serve`

app.py

@@ -0,0 +1,42 @@
+import gradio as gr
+import ollama
+import os
+
+def generate(prompt, temperature=0.8, max_tokens=512):
+    try:
+        response = ollama.generate(
+            model='amkyawdev/amkyaw-dev-v1',
+            prompt=prompt,
+            options={
+                'temperature': temperature,
+                'num_predict': max_tokens
+            }
+        )
+        return response['response']
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+# Check if Ollama is accessible
+try:
+    ollama.list()
+    status = "✅ Ollama is running"
+except:
+    status = "❌ Ollama is not running"
+
+with gr.Blocks(title="amkyaw-coder") as demo:
+    gr.Markdown(f"# amkyaw-coder-1.5b-instruct\n{status}")
+    
+    with gr.Row():
+        with gr.Column():
+            prompt = gr.Textbox(label="Prompt", lines=4, placeholder="Enter your prompt here...")
+            temperature = gr.Slider(0.1, 2.0, value=0.8, step=0.1, label="Temperature")
+            max_tokens = gr.Slider(64, 2048, value=512, step=64, label="Max Tokens")
+            submit = gr.Button("Generate", variant="primary")
+        
+        with gr.Column():
+            output = gr.Textbox(label="Output", lines=15)
+    
+    submit.click(generate, inputs=[prompt, temperature, max_tokens], outputs=output)
+
+if __name__ == "__main__":
+    demo.launch(server_name="0.0.0.0", server_port=7860)

requirements.txt

@@ -0,0 +1,2 @@
+gradio>=4.0.0
+ollama>=0.1.0