first api

app.py

@@ -1,23 +1,19 @@
-pip install transformers
-
-from transformers import AutoModelForCausalLM, AutoTokenizer, set_seed
-import torch
+import requests
 import streamlit as st 
 
-#Setting.
-torch.set_default_tensor_type(torch.cuda.FloatTensor)
-
-
-#Loading model. 
-
-model = AutoModelForCausalLM.from_pretrained("bigscience/bloom", use_cache=True)
-tokenizer = AutoTokenizer.from_pretrained("bigscience/bloom")
+API_URL = "https://api-inference.huggingface.co/models/bigscience/bloom"
+headers = {"Authorization": f"Bearer {API_TOKEN}"}
 
+def query(payload):
+	response = requests.post(API_URL, headers=headers, json=payload)
+	return response.json()
+	
+output = query({
+	"inputs": "Can you please let us know more details about your ",
+})
 
 
 #For app.
 prompt = st.text_input("Input")
-input_ids = tokenizer(prompt, return_tensors="pt").to(0)
-sample = model.generate(**input_ids, max_length=100, top_k=0, temperature=0.7)
 output = st.write(tokenizer.decode(sample[0]))