Upload folder using huggingface_hub

.claude/settings.local.json

@@ -0,0 +1,7 @@
+{
+  "permissions": {
+    "allow": [
+      "Skill(writing-skills:hugging-face-space-deployer)"
+    ]
+  }
+}

README.md

@@ -1,12 +1,34 @@
 ---
-title: Qwen2.5 Coder 7b
-emoji: 🏆
-colorFrom: indigo
-colorTo: yellow
+title: Qwen2.5 Coder 7B
+emoji: 💻
+colorFrom: blue
+colorTo: purple
 sdk: gradio
-sdk_version: 6.2.0
+sdk_version: 5.9.1
 app_file: app.py
 pinned: false
+license: apache-2.0
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Qwen2.5 Coder 7B Chat
+
+A coding assistant powered by [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) via the Hugging Face Inference API.
+
+## Features
+
+- Streaming responses for real-time code generation
+- Configurable system prompt, temperature, and other parameters
+- Optimized for coding tasks including:
+  - Code generation and completion
+  - Code explanation and documentation
+  - Debugging and optimization
+  - Multi-language support
+
+## Usage
+
+Simply type your coding question or request in the chat interface. You can adjust the parameters:
+
+- **System message**: Customize the assistant's behavior
+- **Max tokens**: Control response length (up to 4096)
+- **Temperature**: Adjust creativity (lower = more focused, higher = more creative)
+- **Top-p**: Control diversity of responses

app.py

@@ -0,0 +1,55 @@
+import gradio as gr
+from huggingface_hub import InferenceClient
+
+MODEL_ID = "Qwen/Qwen2.5-Coder-7B-Instruct"
+client = InferenceClient(MODEL_ID)
+
+
+def respond(message, history, system_message, max_tokens, temperature, top_p):
+    messages = [{"role": "system", "content": system_message}]
+
+    for user_msg, assistant_msg in history:
+        if user_msg:
+            messages.append({"role": "user", "content": user_msg})
+        if assistant_msg:
+            messages.append({"role": "assistant", "content": assistant_msg})
+
+    messages.append({"role": "user", "content": message})
+
+    response = ""
+    for token in client.chat_completion(
+        messages,
+        max_tokens=max_tokens,
+        stream=True,
+        temperature=temperature,
+        top_p=top_p,
+    ):
+        delta = token.choices[0].delta.content or ""
+        response += delta
+        yield response
+
+
+demo = gr.ChatInterface(
+    respond,
+    title="Qwen2.5 Coder 7B",
+    description="A coding assistant powered by Qwen2.5-Coder-7B-Instruct via Hugging Face Inference API",
+    additional_inputs=[
+        gr.Textbox(
+            value="You are Qwen, a helpful coding assistant. You excel at writing clean, efficient code and explaining programming concepts clearly.",
+            label="System message",
+            lines=2,
+        ),
+        gr.Slider(minimum=1, maximum=4096, value=1024, step=1, label="Max tokens"),
+        gr.Slider(minimum=0.1, maximum=2.0, 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"),
+    ],
+    examples=[
+        ["Hello! What programming languages are you best at?"],
+        ["Write a Python function to check if a string is a palindrome"],
+        ["Explain the difference between async/await and promises in JavaScript"],
+        ["Help me optimize this SQL query: SELECT * FROM users WHERE name LIKE '%john%'"],
+    ],
+)
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,2 @@
+gradio>=5.0.0
+huggingface_hub>=0.26.0