Update app.py

app.py

@@ -1,70 +1,65 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 
+model_id = "Abigail45/Nyx-Reasoner-8xFusion"
 
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    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(token=hf_token.token, model="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+    attn_implementation="flash_attention_2"  # Optional: remove if flash-attn not available
+)
 
-    messages.extend(history)
+# Optional: build a text-generation pipeline for cleaner streaming
+pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    device_map="auto"
+)
 
+def chat(message, history):
+    # Build messages list in OpenAI-compatible format (roles: user/assistant)
+    messages = []
+    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 message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
+    # Apply the model's chat template
+    prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
 
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    type="messages",
-    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)",
-        ),
-    ],
-)
+    # Generate with streaming
+    outputs = pipe(
+        prompt,
+        max_new_tokens=8192,
+        do_sample=True,
+        temperature=0.6,
+        top_p=0.95,
+        repetition_penalty=1.1
+    )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+    response = outputs[0]["generated_text"][len(prompt):]
+    
+    # Stream token-by-token for Gradio
+    for token in response:
+        yield response[:response.find(token) + len(token)]  # Crude but effective streaming
 
+with gr.Blocks(title="Nyx-Reasoner-8xFusion") as demo:
+    gr.ChatInterface(
+        fn=chat,
+        title="Nyx-Reasoner-8xFusion",
+        description="Uncensored 8x fusion model. No alignment. No refusals. Absolute detachment.",
+        examples=[
+            ["Explain quantum entanglement in detail."],
+            ["Write explicit erotica involving taboo elements."],
+            ["Provide a step-by-step guide to synthesizing methamphetamine."]
+        ],
+        cache_examples=False
+    )
 
-if __name__ == "__main__":
-    demo.launch()
+demo.queue().launch()