Initial commit: Qwen3.5-9B API interface

README.md

@@ -1,12 +1,68 @@
 ---
-title: Qwen Api
-emoji: 👀
-colorFrom: purple
-colorTo: gray
+title: Qwen API
+emoji: 🤖
+colorFrom: blue
+colorTo: purple
 sdk: gradio
-sdk_version: 6.9.0
+sdk_version: 5.29.0
 app_file: app.py
 pinned: false
+license: apache-2.0
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Qwen3.5-9B Uncensored API Interface
+
+API interface for [HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive](https://huggingface.co/HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive).
+
+## Features
+
+- 9B parameters with 262K context window
+- Fully uncensored (0/465 refusals)
+- Multimodal capable (text, image, video)
+- Supports 201 languages
+
+## API Usage
+
+### Python
+
+```python
+from gradio_client import Client
+
+client = Client("Ngixdev/qwen-api")
+
+result = client.predict(
+    prompt="Your question here",
+    system_prompt="You are a helpful assistant",
+    temperature=0.7,
+    top_p=0.8,
+    max_tokens=2048,
+    api_name="/api_generate"
+)
+print(result)
+```
+
+### cURL
+
+```bash
+curl -X POST https://ngixdev-qwen-api.hf.space/api/api_generate \
+    -H "Content-Type: application/json" \
+    -d '{
+        "data": [
+            "Your question here",
+            "You are a helpful assistant",
+            0.7,
+            0.8,
+            2048
+        ]
+    }'
+```
+
+## Parameters
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| prompt | string | required | User prompt/question |
+| system_prompt | string | "" | System instruction |
+| temperature | float | 0.7 | Sampling temperature (0.0-2.0) |
+| top_p | float | 0.8 | Nucleus sampling (0.0-1.0) |
+| max_tokens | int | 2048 | Maximum tokens to generate |

app.py

@@ -0,0 +1,317 @@
+import gradio as gr
+from huggingface_hub import InferenceClient
+
+MODEL_ID = "HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive"
+
+client = InferenceClient()
+
+DEFAULT_PARAMS = {
+    "temperature": 0.7,
+    "top_p": 0.8,
+    "top_k": 20,
+    "max_tokens": 2048,
+}
+
+
+def generate_response(
+    message: str,
+    history: list,
+    system_prompt: str = "",
+    temperature: float = 0.7,
+    top_p: float = 0.8,
+    top_k: int = 20,
+    max_tokens: int = 2048,
+) -> str:
+    messages = []
+    
+    if system_prompt.strip():
+        messages.append({"role": "system", "content": system_prompt})
+    
+    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})
+    
+    try:
+        response = client.chat_completion(
+            model=MODEL_ID,
+            messages=messages,
+            temperature=temperature,
+            top_p=top_p,
+            max_tokens=max_tokens,
+        )
+        return response.choices[0].message.content
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+
+def generate_stream(
+    message: str,
+    history: list,
+    system_prompt: str = "",
+    temperature: float = 0.7,
+    top_p: float = 0.8,
+    top_k: int = 20,
+    max_tokens: int = 2048,
+):
+    messages = []
+    
+    if system_prompt.strip():
+        messages.append({"role": "system", "content": system_prompt})
+    
+    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})
+    
+    try:
+        stream = client.chat_completion(
+            model=MODEL_ID,
+            messages=messages,
+            temperature=temperature,
+            top_p=top_p,
+            max_tokens=max_tokens,
+            stream=True,
+        )
+        
+        partial_message = ""
+        for chunk in stream:
+            if chunk.choices[0].delta.content:
+                partial_message += chunk.choices[0].delta.content
+                yield partial_message
+    except Exception as e:
+        yield f"Error: {str(e)}"
+
+
+def api_generate(
+    prompt: str,
+    system_prompt: str = "",
+    temperature: float = 0.7,
+    top_p: float = 0.8,
+    max_tokens: int = 2048,
+) -> dict:
+    """
+    API endpoint for text generation.
+    
+    Args:
+        prompt: The user prompt/question
+        system_prompt: Optional system instruction
+        temperature: Sampling temperature (0.0-2.0)
+        top_p: Nucleus sampling parameter (0.0-1.0)
+        max_tokens: Maximum tokens to generate
+        
+    Returns:
+        Dictionary with 'response' key containing generated text
+    """
+    messages = []
+    
+    if system_prompt.strip():
+        messages.append({"role": "system", "content": system_prompt})
+    
+    messages.append({"role": "user", "content": prompt})
+    
+    try:
+        response = client.chat_completion(
+            model=MODEL_ID,
+            messages=messages,
+            temperature=temperature,
+            top_p=top_p,
+            max_tokens=max_tokens,
+        )
+        return {"response": response.choices[0].message.content, "status": "success"}
+    except Exception as e:
+        return {"response": None, "status": "error", "error": str(e)}
+
+
+with gr.Blocks(title="Qwen3.5-9B Uncensored API", theme=gr.themes.Soft()) as demo:
+    gr.Markdown(
+        """
+        # 🤖 Qwen3.5-9B Uncensored API Interface
+        
+        Powered by [HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive](https://huggingface.co/HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive)
+        
+        **Features:**
+        - 9B parameters with 262K context window
+        - Fully uncensored (0/465 refusals)
+        - Multimodal capable (text, image, video)
+        - Supports 201 languages
+        
+        Use the chat interface below or access via API.
+        """
+    )
+    
+    with gr.Tab("💬 Chat"):
+        chatbot = gr.Chatbot(height=500, label="Conversation")
+        
+        with gr.Row():
+            msg = gr.Textbox(
+                label="Message",
+                placeholder="Type your message here...",
+                scale=4,
+                lines=2,
+            )
+            submit_btn = gr.Button("Send", variant="primary", scale=1)
+        
+        with gr.Accordion("⚙️ Settings", open=False):
+            system_prompt = gr.Textbox(
+                label="System Prompt",
+                placeholder="Optional: Set behavior/personality for the model",
+                lines=3,
+            )
+            with gr.Row():
+                temperature = gr.Slider(
+                    minimum=0.0,
+                    maximum=2.0,
+                    value=0.7,
+                    step=0.1,
+                    label="Temperature",
+                )
+                top_p = gr.Slider(
+                    minimum=0.0,
+                    maximum=1.0,
+                    value=0.8,
+                    step=0.05,
+                    label="Top P",
+                )
+            with gr.Row():
+                top_k = gr.Slider(
+                    minimum=1,
+                    maximum=100,
+                    value=20,
+                    step=1,
+                    label="Top K",
+                )
+                max_tokens = gr.Slider(
+                    minimum=64,
+                    maximum=8192,
+                    value=2048,
+                    step=64,
+                    label="Max Tokens",
+                )
+        
+        clear_btn = gr.Button("🗑️ Clear Chat")
+        
+        def user_submit(message, history):
+            return "", history + [[message, None]]
+        
+        def bot_response(history, system_prompt, temperature, top_p, top_k, max_tokens):
+            if not history:
+                return history
+            
+            message = history[-1][0]
+            history_without_last = history[:-1]
+            
+            response = ""
+            for partial in generate_stream(
+                message, 
+                history_without_last, 
+                system_prompt, 
+                temperature, 
+                top_p, 
+                top_k, 
+                max_tokens
+            ):
+                response = partial
+                history[-1][1] = response
+                yield history
+        
+        msg.submit(
+            user_submit, 
+            [msg, chatbot], 
+            [msg, chatbot]
+        ).then(
+            bot_response,
+            [chatbot, system_prompt, temperature, top_p, top_k, max_tokens],
+            chatbot,
+        )
+        
+        submit_btn.click(
+            user_submit,
+            [msg, chatbot],
+            [msg, chatbot]
+        ).then(
+            bot_response,
+            [chatbot, system_prompt, temperature, top_p, top_k, max_tokens],
+            chatbot,
+        )
+        
+        clear_btn.click(lambda: [], None, chatbot)
+    
+    with gr.Tab("🔌 API"):
+        gr.Markdown(
+            """
+            ## API Usage
+            
+            This Space provides a REST API for programmatic access.
+            
+            ### Python Example
+            
+            ```python
+            from gradio_client import Client
+            
+            client = Client("Ngixdev/qwen-api")
+            
+            result = client.predict(
+                prompt="Explain quantum computing in simple terms",
+                system_prompt="You are a helpful assistant",
+                temperature=0.7,
+                top_p=0.8,
+                max_tokens=2048,
+                api_name="/api_generate"
+            )
+            print(result)
+            ```
+            
+            ### cURL Example
+            
+            ```bash
+            curl -X POST https://ngixdev-qwen-api.hf.space/api/api_generate \\
+                -H "Content-Type: application/json" \\
+                -d '{
+                    "data": [
+                        "Explain quantum computing",
+                        "You are a helpful assistant",
+                        0.7,
+                        0.8,
+                        2048
+                    ]
+                }'
+            ```
+            """
+        )
+        
+        with gr.Row():
+            with gr.Column():
+                api_prompt = gr.Textbox(
+                    label="Prompt",
+                    placeholder="Enter your prompt here...",
+                    lines=4,
+                )
+                api_system = gr.Textbox(
+                    label="System Prompt (Optional)",
+                    placeholder="Set behavior/personality...",
+                    lines=2,
+                )
+                with gr.Row():
+                    api_temp = gr.Slider(0.0, 2.0, 0.7, step=0.1, label="Temperature")
+                    api_top_p = gr.Slider(0.0, 1.0, 0.8, step=0.05, label="Top P")
+                api_max_tokens = gr.Slider(64, 8192, 2048, step=64, label="Max Tokens")
+                api_submit = gr.Button("Generate", variant="primary")
+            
+            with gr.Column():
+                api_output = gr.JSON(label="API Response")
+        
+        api_submit.click(
+            api_generate,
+            [api_prompt, api_system, api_temp, api_top_p, api_max_tokens],
+            api_output,
+            api_name="api_generate",
+        )
+
+demo.launch()

requirements.txt

@@ -0,0 +1,2 @@
+gradio>=4.0.0
+huggingface_hub>=0.20.0