Update app.py

app.py

@@ -6,18 +6,35 @@ 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
+
+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 = [
+#     {
+#         "role": "system",
+#         "content": "You are a friendly chatbot who answewrs question in given language",
+#     },
+#     {"role": "user", "content": "what is the 3 biggest countrys in Africa?"},
+# ]
+# prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+# outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+# print(outputs[0]["generated_text"])
+
 
 if 'messages' not in st.session_state:
     st.session_state.messages = [