removed the model binary, will now use model from hugginface models repo

app.py

@@ -1,6 +1,7 @@
 import torch
 from transformers import AutoTokenizer
 import gradio as gr
+from huggingface_hub import hf_hub_download
 from model import LlamaForCausalLM # Import your custom model class
 
 # Load tokenizer and model
@@ -17,7 +18,8 @@ model = LlamaForCausalLM(
     num_heads=9
 )
 device = "cpu"
-checkpoint_path = "model_bin.pt"
+model_id = "chbsaikiran/smollm2_135M_model"
+checkpoint_path = hf_hub_download(repo_id=model_id, filename="model_bin.pt")
 
 checkpoint = torch.load(checkpoint_path, map_location=device)
 model.load_state_dict(checkpoint['model_state_dict'])

model_bin.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3a77b73f06315595be13616cb77bf4483955cd9e5c9f40176332feebf7d149e5
-size 704502186

requirements.txt

@@ -1,3 +1,4 @@
-gradio
 torch
-transformers
+gradio
+transformers 
+huggingface_hub