removed last token

app.py

@@ -25,6 +25,31 @@ def calculate_func(input:User_input):
     res= calculate(input.operation, input.x, input.y)
     return res
 
+import requests
+# def query(API_URL, headers, payload):
+#         response = requests.post(API_URL, headers=headers, json=payload)
+#         print(response)
+#         return response
+@app.post("/HFAPI")
+def HF_API():
+#     API_TOKEN=""
+#     API_URL = "https://api-inference.huggingface.co/models/openai-community/gpt2"
+#     headers = {"Authorization": f"Bearer {API_TOKEN}"}
+    
+#     data = query(API_URL,headers, {
+# 	"inputs": "Can you please let us know more details about your ",
+# })
+    API_URL = "https://api-inference.huggingface.co/models/openai-community/gpt2"
+    headers = {"Authorization": "Bearer ......................q"}
+    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 India? ",
+    })
+    return output[0]["generated_text"]
+        
+
 @app.post("/sentimentAnalysis")
 def sentimentAnalysis_func(input:User_input):
     res= sentimentAnalysis(input.sentence)
@@ -34,6 +59,27 @@ def sentimentAnalysis_func(input:User_input):
 def getReply_func(input:User_input):
     res= customerConverstaion(input.sentence)
     return res
+@app.post("/hf_spaces")
+def HF_interact():
+    from huggingface_hub import HfApi
+    # Initialize API client
+    api = HfApi()
+
+    # Replace these with your values
+    repo_id = 'DSU-FDP/Sample-API'
+    token = ''
+
+    # Authenticate
+   
+    api.pause_space(repo_id=repo_id)
+
+
+    # List all Spaces (not pausing, just showing how to interact)
+    spaces = api.list_spaces()
+    print(spaces)
+
+    # Example action: delete a space (be cautious with this!)
+    # api.delete_repo(repo_id, token=token)
 
 
 

customerSupport.py

@@ -12,8 +12,11 @@ def input_data_preprocessing(example):
 
 
 def customerConverstaion(prompt):
+    # Check GPU availability
+    print("Available GPU devices:", torch.cuda.device_count())
+    print("Name of the first available GPU:", torch.cuda.get_device_name(0))
     config = PeftConfig.from_pretrained("DSU-FDP/customer-support")
-    base_model = AutoModelForCausalLM.from_pretrained("TheBloke/zephyr-7B-beta-GPTQ")
+    base_model = AutoModelForCausalLM.from_pretrained("TheBloke/zephyr-7B-beta-GPTQ", device_map='cuda')
     model = PeftModel.from_pretrained(base_model, "DSU-FDP/customer-support")
     from transformers import AutoTokenizer,GPTQConfig
     tokenizer=AutoTokenizer.from_pretrained(base_model, trust_remote_code=True)