Update app.py

app.py

@@ -1,11 +1,19 @@
 import gradio as gr
-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("HuggingFaceH4/zephyr-7b-beta")
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_path = "Wonder-Griffin/ShorseyBeerLeague"
+
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(
+    model_path,
+    device_map="auto",
+    torch_dtype='auto'
+).eval()
 
+input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
+output_ids = model.generate(input_ids.to('cuda'))
+respond = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
 
 def respond(
     message,
@@ -25,7 +33,7 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
+    respond = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
 
     for message in client.chat_completion(
         messages,
@@ -36,8 +44,8 @@ def respond(
     ):
         token = message.choices[0].delta.content
 
-        response += token
-        yield response
+        respond += token
+        yield respond
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface