text-generation

app.py

@@ -1,64 +1,50 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-"""
-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
-"""
-client = InferenceClient("rieon/DeepCoder-14B-Preview-Suger")
+# ←–– set this to the exact name of your HF repo
+HF_MODEL_ID = "rieon/DeepCoder-14B-Preview-Suger"
 
+# explicitly tell the client you want text-generation
+client = InferenceClient(repo_id=HF_MODEL_ID, task="text-generation")
 
 def respond(
-    message,
+    message: str,
     history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
+    system_message: str,
+    max_tokens: int,
+    temperature: float,
+    top_p: float,
 ):
-    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 = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+    # assemble a single prompt from system message + history
+    prompt = system_message.strip() + "\n"
+    for user, bot in history:
+        prompt += f"User: {user}\nAssistant: {bot}\n"
+    prompt += f"User: {message}\nAssistant:"
+
+    # stream back tokens
+    generated = ""
+    for chunk in client.text_generation(
+        inputs=prompt,
+        max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
+        stream=True,
     ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
+        # the API returns a small JSON with .generated_text
+        generated += chunk.generated_text
+        yield generated
 
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
 demo = gr.ChatInterface(
-    respond,
+    fn=respond,
+    system_prompt="You are a helpful coding assistant.",
     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)",
-        ),
+        gr.Textbox(value="You are a helpful coding assistant.", label="System message"),
+        gr.Slider(1, 2048, value=512, step=1, label="Max new tokens"),
+        gr.Slider(0.1, 4.0, value=0.7, step=0.1, label="Temperature"),
+        gr.Slider(0.1, 1.0, value=0.95, step=0.05, label="Top-p"),
     ],
+    title="DeepCoder-14B (LoRA Fine-Tuned)",
 )
 
-
 if __name__ == "__main__":
     demo.launch()