Updating to api url

app.py

@@ -5,125 +5,69 @@ from typing import Iterator
 import gradio as gr
 import spaces
 import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+from openai import OpenAI, APIError
+
+client = OpenAI(
+	base_url="https://hjopms3xd7gembdu.us-east-1.aws.endpoints.huggingface.cloud/v1/", 
+	api_key="hf_XXXXX" 
+)
 
 MAX_MAX_NEW_TOKENS = 2048
-DEFAULT_MAX_NEW_TOKENS = 1024
+DEFAULT_MAX_NEW_TOKENS = 512
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 DESCRIPTION = """
 Llama3-TenyxChat-70B is part of the TenyxChat series, models trained to function as useful assistants. 
 The model is obtained via direct preference tuning using Tenyx's fine-tuning technology. Model details available at our model page. 
-
-**The model is currently loaded in 8-bit**.
 """
 
 
 LICENSE = """
 This demo is governed by the license available [here.](https://huggingface.co/spaces/tenyx/Llama3-TenyxChat-70B/blob/main/LICENSE.txt)"""
 
-
-if not torch.cuda.is_available():
-    DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
-
-
-if torch.cuda.is_available():
-    model_id = "tenyx/Llama3-TenyxChat-70B"
-    # model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype=torch.bfloat16)
-    model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", load_in_4bit=True)
-    tokenizer = AutoTokenizer.from_pretrained(model_id)
-    tokenizer.use_default_system_prompt = False
-
-
 @spaces.GPU
 def generate(
     message: str,
     chat_history: list[tuple[str, str]],
-    system_prompt: str,
-    max_new_tokens: int = 1024,
-    temperature: float = 0.6,
-    top_p: float = 0.9,
-    top_k: int = 50,
-    repetition_penalty: float = 1.2,
 ) -> Iterator[str]:
     conversation = [{"role": "system", "content": "You are a helpful assistant developed by Tenyx, a conversational voice AI company."}]
-    if system_prompt:
-        conversation.append({"role": "system", "content": system_prompt})
+
     for user, assistant in chat_history:
         conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
     conversation.append({"role": "user", "content": message})
-    
-    # if not message.strip():
-    #     return "It looks like your message is empty. How can I assist you today?"
-
-    input_ids = tokenizer.apply_chat_template(conversation, add_generation_prompt = True, return_tensors="pt")
-    if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
-        input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:]
-        gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
-    input_ids = input_ids.to(model.device)
-
-    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
-    generate_kwargs = dict(
-        {"input_ids": input_ids},
-        streamer=streamer,
-        max_new_tokens=max_new_tokens,
-        # eos_token_id=[128001, 128009],
-        do_sample=True,
-        top_p=top_p,
-        top_k=top_k,
-        temperature=temperature,
-        num_beams=1,
-        repetition_penalty=repetition_penalty,
-    )
-    t = Thread(target=model.generate, kwargs=generate_kwargs)
-    t.start()
-
-    outputs = []
-    for text in streamer:
-        outputs.append(text)
-        yield "".join(outputs)
-
-
-chat_interface = gr.ChatInterface(
+
+    try:
+        response = client.chat.completions.create(
+                            model="tgi",
+                            messages=conversation,
+                            stop=["<|end_of_text|>", "<|eot_id|>"],
+                            stream=True,
+                            max_tokens=1024,
+                        )
+        outputs = []
+        for chunk in response:
+            outputs.append(chunk.choices[0].delta.content)
+            yield "".join(outputs)
+
+    except APIError as e:
+        # Handle API errors or network errors here
+        print(f"Error: {e}")
+        yield "An error occurred. Please try again later."
+
+
+
+demo = gr.ChatInterface(
     fn=generate,
-    additional_inputs=[
-        gr.Textbox(label="System prompt", lines=6),
-        gr.Slider(
-            label="Max new tokens",
-            minimum=1,
-            maximum=MAX_MAX_NEW_TOKENS,
-            step=1,
-            value=DEFAULT_MAX_NEW_TOKENS,
-        ),
-        gr.Slider(
-            label="Temperature",
-            minimum=0.1,
-            maximum=4.0,
-            step=0.1,
-            value=0.1,
-        ),
-        gr.Slider(
-            label="Top-p (nucleus sampling)",
-            minimum=0.05,
-            maximum=1.0,
-            step=0.05,
-            value=0.9,
-        ),
-        gr.Slider(
-            label="Top-k",
-            minimum=1,
-            maximum=1000,
-            step=1,
-            value=50,
-        ),
-        gr.Slider(
-            label="Repetition penalty",
-            minimum=1.0,
-            maximum=2.0,
-            step=0.05,
-            value=1.2,
-        ),
-    ],
+    # additional_inputs=[
+    #     gr.Textbox(label="System prompt", lines=6),
+    #     gr.Slider(
+    #         label="Max new tokens",
+    #         minimum=1,
+    #         maximum=MAX_MAX_NEW_TOKENS,
+    #         step=1,
+    #         value=DEFAULT_MAX_NEW_TOKENS,
+    #     ),
+    # ],
     stop_btn=None,
     examples=[
         ["Hello there! How are you doing?"],
@@ -134,13 +78,14 @@ chat_interface = gr.ChatInterface(
     ],
 )
 
-with gr.Blocks(css="style.css") as demo:
-    gr.Markdown(DESCRIPTION)
-    gr.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button")
-    chat_interface.render()
-    gr.Markdown(LICENSE)
+# with gr.Blocks() as demo:
+#     # gr.Markdown(DESCRIPTION)
+#     # gr.Markdown(LICENSE)
+#     # gr.DuplicateButton(value="Duplicate Space for private use", elem_id="duplicate-button")
+#     chat_interface.render()
+    
 
 if __name__ == "__main__":
-    demo.queue(max_size=4).launch()
+    demo.queue(max_size=4).launch(share=True)
 
 

requirements.txt

@@ -6,4 +6,5 @@ spaces==0.26.2
 scipy
 sentencepiece
 torch==2.3.0
-transformers==4.40.1
+transformers==4.40.1
+openai==1.25.0