Update README.md

README.md

@@ -19,28 +19,25 @@ datasets:
 
 ```python
 
-from transformers import AutoModelForCausalLM, AutoTokenizer
+import requests
 
-model_path = "seyabde/mistral_7b_yo_instruct"
+API_URL = "https://i8nykns7vw253vx3.us-east-1.aws.endpoints.huggingface.cloud"
+headers = {
+	"Authorization": "Bearer hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
+	"Content-Type": "application/json"
+}
 
-tokenizer = AutoTokenizer.from_pretrained(model_path)
-model = AutoModelForCausalLM.from_pretrained(
-    model_path,
-    device_map="auto",
-    torch_dtype='auto'
-).eval()
+def query(payload):
+	response = requests.post(API_URL, headers=headers, json=payload)
+	return response.json()
 
-# Prompt content: "Pẹlẹ o. Bawo ni o se wa?" ("Hello. How are you?")
-messages = [
-    {"role": "user", "content": "Pẹlẹ o. Bawo ni o se wa?"}
-]
+# Prompt content: "Pẹlẹ o. Bawo ni o se wa?" ("Hello. How are you?")	
+output = query({
+	"inputs": "Pẹlẹ o. Bawo ni o se wa?",
+})
 
-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'))
-response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
-
-# Model response:
-print(response)
+# Model response: "O dabo. O jẹ ọjọ ti o dara." ("I am safe. It was a good day.")
+print(output)
 ```