Upload 2 files

app.py

@@ -1,64 +1,72 @@
+import time
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
 
-"""
-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("HuggingFaceH4/zephyr-7b-beta")
+# Load model
+tokenizer = AutoTokenizer.from_pretrained("microsoft/phi-2")
+model = AutoModelForCausalLM.from_pretrained("microsoft/phi-2")
 
+# Inference function
+def chat_completion(messages, model_name="mock-gpt-model", max_tokens=512, temperature=0.1, stream=False):
+    if not messages:
+        return {
+            "error": "No messages provided."
+        }
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+    # Rebuild prompt
+    prompt = ""
+    for msg in messages:
+        role = msg.get("role", "")
+        content = msg.get("content", "")
+        if role == "user":
+            prompt += f"User: {content}\n"
+        elif role == "assistant":
+            prompt += f"Assistant: {content}\n"
+    prompt += "Assistant:"
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    # Generate output
+    inputs = tokenizer(prompt, return_tensors="pt")
+    with torch.no_grad():
+        outputs = model.generate(
+            **inputs,
+            max_new_tokens=max_tokens,
+            temperature=temperature,
+            do_sample=True,
+            pad_token_id=tokenizer.eos_token_id
+        )
+    generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
 
-    messages.append({"role": "user", "content": message})
+    # Extract assistant reply
+    assistant_reply = generated_text[len(prompt):].strip()
 
-    response = ""
+    return {
+        "id": "1337",
+        "object": "chat.completion",
+        "created": time.time(),
+        "model": model_name,
+        "choices": [{
+            "message": {
+                "role": "assistant",
+                "content": assistant_reply
+            }
+        }]
+    }
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        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)",
-        ),
+# Gradio API endpoint setup
+demo = gr.Interface(
+    fn=chat_completion,
+    inputs=[
+        gr.JSON(label="messages"),             # List[{"role":..., "content":...}]
+        gr.Textbox(label="model", value="mock-gpt-model"),
+        gr.Slider(minimum=1, maximum=1024, value=512, label="max_tokens"),
+        gr.Slider(minimum=0.0, maximum=1.0, value=0.1, label="temperature"),
+        gr.Checkbox(label="stream", value=False)
     ],
+    outputs=gr.JSON(label="response"),
+    title="OpenAI-compatible Chat API (Gradio + Transformers)",
+    allow_flagging="never"
 )
 
-
 if __name__ == "__main__":
     demo.launch()

requirements.txt

@@ -1 +1,7 @@
-huggingface_hub==0.25.2
+fastapi
+uvicorn
+transformers
+torch
+pydantic
+starlette
+gradio