test

app.py

@@ -2,46 +2,15 @@ import gradio as gr
 import requests
 import json
 import logging
-import os
+from optimum.neuron import utils
+
 
 # Set up logging
 logging.basicConfig(level=logging.INFO)
 
-def get_model_info(model_id="Qwen/Qwen2-7B-Instruct", hf_token=os.getenv('HF_TOKEN')):
-    url = f"https://huggingface.co/api/integrations/aws/v1/lookup/{model_id}"
-    
-    headers = {}
-    if hf_token:
-        headers["Authorization"] = f"Bearer {hf_token}"
-    try:
-        response = requests.get(url, headers=headers)
-    except requests.exceptions.RequestException as e:
-        print(f"Error fetching data for task text-generation: {e}")
-        return None
-    data = response.json()
-    return json.dumps(data, indent=4)
-    
-    # url = f"https://huggingface.co/api/integrations/aws/v1/lookup/{model_id}"
-    # headers = {
-    #     "Authorization": f"Bearer {hf_token}",
-    # }
-
-    # logging.info(f"Requesting model info for model ID: {model_id}")
-    # logging.info(f"URL: {url}")
-
-    # response = requests.get(url, headers=headers)
-    
-    # logging.info(f"Response Status: {response.status_code}")
-    # logging.info(f"Response Headers: {response.headers}")
-    # logging.info(f"Response Text: {response.text}")
-
-    # if response.status_code != 200:
-    #     logging.error(f"Error: {response.status_code} - {response.text}")
-    #     return f"Error: {response.status_code}\\nResponse: {response.text}"
-    
-    # data = response.json()
-    # logging.info("Successfully retrieved model info.")
-    # return json.dumps(data, indent=4)
+def get_model_info(model_id="Qwen/Qwen2-7B-Instruct"):
+    config_list = utils.get_hub_cached_entries(model_id=model_id, mode="inference")
+    return config_list
 
 iface = gr.Interface(
     fn=lambda model_id: get_model_info(model_id, hf_token=os.getenv('HF_TOKEN')),

requirements.txt

@@ -1 +1,2 @@
-requests==2.32.3
+requests==2.32.3
+optimum-neuron==0.1.0