update settings

app.py

@@ -110,9 +110,9 @@ elif sidebar_option == 'HF Local':
         #model_name="HuggingFaceH4/zephyr-7b-beta",
         # model_name="meta-llama/Meta-Llama-3-8B",
         #model_name="numind/NuExtract-1.5",
-        model_name="meta-llama/Llama-3.1-8B",
+        model_name="meta-llama/Llama-3.2-3B",
         
-        tokenizer_name="meta-llama/Llama-3.1-8B",
+        tokenizer_name="meta-llama/Llama-3.2-3B",
         device_map="auto",
         # tokenizer_kwargs={"max_length": 2048},
         # uncomment this if using CUDA to reduce memory usage

requirements.txt

@@ -12,6 +12,6 @@ openpyxl
 llama-index-llms-huggingface
 llama-index-llms-huggingface-api
 transformers[torch]
-huggingface_hub[inference]
+huggingface_hub
 llama_index.embeddings.huggingface
 llama-index-readers-file