Attempted to add hf hub login for gated repo; cleaned up house

app_inference.py

@@ -3,6 +3,8 @@ import streamlit as st
 import transformers, torch
 import json, os
 
+from huggingface_hub import HfApi
+
 # CONSTANTS
 MAX_NEW_TOKENS = 256
 SYSTEM_MESSAGE = "You are a hepful, knowledgeable assistant"
@@ -15,6 +17,9 @@ text_input = st.text_input("Query", value="Why is the sky Blue")
 submit = st.button("Submit")
 
 # MODEL AREA
+# Use the token to authenticate
+token = os.environ.get("HF_TOKEN_READ")
+api = HfApi(token=token)
 model_id = "meta-llama/Meta-Llama-3.1-8B-Instruct"
 
 @st.cache_resource

examples/tests/hf_login.py

@@ -0,0 +1,23 @@
+# from huggingface_hub import login
+# login()
+
+import transformers, torch
+
+import os
+from huggingface_hub import HfApi
+
+# Get the token from the environment variable
+token = os.environ.get("HF_TOKEN_READ")
+
+print(token)
+
+# Use the token to authenticate
+api = HfApi(token=token)
+model_id = "meta-llama/Meta-Llama-3.1-8B-Instruct"
+
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model_id,
+    model_kwargs={"torch_dtype": torch.bfloat16},
+    device_map="auto",
+)

requirements.txt

@@ -9,4 +9,5 @@ langchain-google-genai==2.0.0
 langchain-community==0.3.0
 python-dotenv==1.0.1
 tiktoken==0.7.0
-torch
+torch
+huggingface-hub==0.25.1