Update app.py

app.py

@@ -3,47 +3,47 @@ from transformers import pipeline
 import librosa
 
 ########################LLama model###############################
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-model_name_or_path = "TheBloke/llama2_7b_chat_uncensored-GPTQ"
-# To use a different branch, change revision
-# For example: revision="main"
-model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
-                                             device_map="auto",
-                                             trust_remote_code=True,
-                                             revision="main",
-                                             #quantization_config=QuantizationConfig(disable_exllama=True)
-                                             )
-
-tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
-Llama_pipe = pipeline(
-    "text-generation",
-    model=model,
-    tokenizer=tokenizer,
-    max_new_tokens=40,
-    do_sample=True,
-    temperature=0.7,
-    top_p=0.95,
-    top_k=40,
-    repetition_penalty=1.1
-)
-history="""User: Hello, Rally?
-Rally: I'm happy to see you again. What you want to talk to day?
-User: Let's talk about food
-Rally: Sure.
-User: I'm hungry right now. Do you know any Vietnamese food?"""
-
-prompt_template = f"""<|im_start|>system
-Write one sentence to continue the conversation<|im_end|>
-{history}
-Rally:"""
-print(Llama_pipe(prompt_template)[0]['generated_text'])
-
-def RallyRespone(chat_history, message):
-    chat_history += "User: " + message + "\n"
-    t_chat = Llama_pipe(prompt_template)[0]['generated_text']
-    res = t_chat[t_chat.rfind("Rally: "):]
-    return res
+# from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# model_name_or_path = "TheBloke/llama2_7b_chat_uncensored-GPTQ"
+# # To use a different branch, change revision
+# # For example: revision="main"
+# model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
+#                                              device_map="auto",
+#                                              trust_remote_code=True,
+#                                              revision="main",
+#                                              #quantization_config=QuantizationConfig(disable_exllama=True)
+#                                              )
+
+# tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
+# Llama_pipe = pipeline(
+#     "text-generation",
+#     model=model,
+#     tokenizer=tokenizer,
+#     max_new_tokens=40,
+#     do_sample=True,
+#     temperature=0.7,
+#     top_p=0.95,
+#     top_k=40,
+#     repetition_penalty=1.1
+# )
+# history="""User: Hello, Rally?
+# Rally: I'm happy to see you again. What you want to talk to day?
+# User: Let's talk about food
+# Rally: Sure.
+# User: I'm hungry right now. Do you know any Vietnamese food?"""
+
+# prompt_template = f"""<|im_start|>system
+# Write one sentence to continue the conversation<|im_end|>
+# {history}
+# Rally:"""
+# print(Llama_pipe(prompt_template)[0]['generated_text'])
+
+# def RallyRespone(chat_history, message):
+#     chat_history += "User: " + message + "\n"
+#     t_chat = Llama_pipe(prompt_template)[0]['generated_text']
+#     res = t_chat[t_chat.rfind("Rally: "):]
+#     return res
 
 ########################ASR model###############################