Update app.py

app.py

@@ -1,62 +1,64 @@
 import gradio as gr
-
-from transformers import AutoModelForCausalLM, AutoTokenizer, StopStringCriteria, StoppingCriteriaList
-import torch
-
-import torch._dynamo
-torch._dynamo.config.suppress_errors = True
-
-import os
-os.system("nvidia-smi")
-print("TORCH_CUDA", torch.cuda.is_available())
-
-
-print("loading model")
-# Load the tokenizer and model
-# repo_name = "nvidia/Hymba-1.5B-Instruct"
-repo_name = "HuggingFaceTB/SmolLM2-1.7B-Instruct"
-
-tokenizer = AutoTokenizer.from_pretrained(repo_name, trust_remote_code=True)
-model = AutoModelForCausalLM.from_pretrained(repo_name, trust_remote_code=True)
-
-model = model.cuda().to(torch.bfloat16)
-
-print("model is loaded")
-
-
-# Chat with Hymba
-# prompt = input()
-prompt = "Who are you?"
-
-messages = [
-    {"role": "system", "content": "You are a helpful assistant."}
-]
-messages.append({"role": "user", "content": prompt})
-
-# Apply chat template
-tokenized_chat = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to('cuda')
-stopping_criteria = StoppingCriteriaList([StopStringCriteria(tokenizer=tokenizer, stop_strings="</s>")])
-
-print("generating prompt")
-
-
-outputs = model.generate(
-    tokenized_chat, 
-    max_new_tokens=256,
-    do_sample=False,
-    temperature=0.7,
-    use_cache=True,
-    stopping_criteria=stopping_criteria
+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("HuggingFaceTB/SmolLM2-1.7B-Instruct")
+# client = InferenceClient("nvidia/Hymba-1.5B-Instruct")
+
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
+    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,
+        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)",
+        ),
+    ],
 )
-input_length = tokenized_chat.shape[1]
-response = tokenizer.decode(outputs[0][input_length:], skip_special_tokens=True)
-
-
 
-def greet(name):
-    print(f"User: prompt")
-    print(f"Model response: {response}")
-    # return "Hello " + name + "!!"
 
-demo = gr.Interface(fn=greet, inputs="text", outputs="text")
-demo.launch()
+if __name__ == "__main__":
+    demo.launch()