Update app.py

app.py

@@ -2,15 +2,8 @@ import gradio as gr
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM, AutoConfig
 
-tokenizer = AutoTokenizer.from_pretrained("TheBloke/SOLAR-10.7B-Instruct-v1.0-uncensored-GPTQ")
-config = AutoConfig.from_pretrained("TheBloke/SOLAR-10.7B-Instruct-v1.0-uncensored-GPTQ", trust_remote_code=True)
-# # config.quantization_config["use_exllama"] = True
-# config.quantization_config["disable_exllama"] = True
-# config.quantization_config["exllama_config"] = {"version":2}
-# # model = AutoModelForCausalLM.from_config(config, trust_remote_code=True)
-config = AutoConfig.from_pretrained("TheBloke/SOLAR-10.7B-Instruct-v1.0-uncensored-GPTQ")
-config.quantization_config["disable_exllama"] = True
-model = AutoModelForCausalLM.from_config(config)
+tokenizer = AutoTokenizer.from_pretrained("kimnt93/chat-llama2-1b-1.0")
+model = AutoModelForCausalLM.from_pretrained("kimnt93/chat-llama2-1b-1.0")
 
 def generate_response(prompt):
     conversation = [{'role': 'user', 'content': prompt}]