Update app.py

app.py

@@ -1,27 +1,27 @@
 import streamlit as st
 
 
-# import torch
-# from transformers import pipeline
-# from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
+import torch
+from transformers import pipeline
+from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 
 
-# quantization_config = BitsAndBytesConfig(load_in_4bit=True)
+quantization_config = BitsAndBytesConfig(load_in_4bit=True)
 
 
-# model_name = "masakhane/zephyr-7b-gemma-sft-african-alpaca"
+model_name = "masakhane/zephyr-7b-gemma-sft-african-alpaca"
 
-# tokenizer = AutoTokenizer.from_pretrained(model_name)
-# model = AutoModelForCausalLM.from_pretrained(model_name, quantization_config=quantization_config)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, quantization_config=quantization_config)
 
 
-# pipe = pipeline("text-generation", model=model,tokenizer=tokenizer, torch_dtype=torch.bfloat16, device_map="auto")
+pipe = pipeline("text-generation", model=model,tokenizer=tokenizer, torch_dtype=torch.bfloat16, device_map="auto")
 
 
-import torch
-from transformers import pipeline
+# import torch
+# from transformers import pipeline
 
-pipe = pipeline("text-generation", model="masakhane/zephyr-7b-gemma-sft-african-alpaca", torch_dtype=torch.bfloat16, device_map="auto")
+# pipe = pipeline("text-generation", model="masakhane/zephyr-7b-gemma-sft-african-alpaca", torch_dtype=torch.bfloat16, device_map="auto")
 
 # We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
 # messages = [