Update app.py

app.py

@@ -1,69 +1,39 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-
-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}]
-
-    messages.extend(history)
-
-    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
-
-        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,
-    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)",
-        ),
-    ],
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+REPO = "prathamkode/particle-1.0"
+tok = AutoTokenizer.from_pretrained(REPO)
+model = AutoModelForCausalLM.from_pretrained(
+    REPO,
+    torch_dtype=torch.float32,
+    device_map="cpu",
 )
+model.eval()
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
 
+def chat(message, history):
+    messages = [{"role": m["role"], "content": m["content"]} for m in history]
+    messages.append({"role": "user", "content": message})
+    prompt = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+    ids = tok(prompt, return_tensors="pt")
+    ids.pop("token_type_ids", None)
+    out = model.generate(
+        **ids,
+        max_new_tokens=64,
+        do_sample=True,
+        temperature=0.7,
+        top_k=50,
+        pad_token_id=tok.pad_token_id,
+        eos_token_id=tok.eos_token_id,
+    )
+    text = tok.decode(out[0], skip_special_tokens=False)
+    if "<|assistant|>" in text:
+        text = text.split("<|assistant|>")[-1]
+    return text.replace("<|endoftext|>", "").replace("<|padding|>", "").strip()
+
+
+demo = gr.ChatInterface(chat, type="messages", title="particle-1.0")
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(ssr_mode=False)