Update space

Gemma_Model.py

@@ -8,14 +8,14 @@ class GemmaLLM:
     
     def __init__(self):
         model_id = "google/gemma-3-1b-it"
-        # quantization_config = BitsAndBytesConfig(load_in_8bit=True)
+        quantization_config = BitsAndBytesConfig(load_in_8bit=True)
         
         self.model = Gemma3ForCausalLM.from_pretrained(
             model_id,
             device_map="cpu",
-            # quantization_config=quantization_config,
-            # low_cpu_mem_usage=True,
-            # torch_dtype=torch.float16,
+            quantization_config=quantization_config,
+            low_cpu_mem_usage=True,
+            torch_dtype=torch.float16,
         ).eval()
 
         self.tokenizer = AutoTokenizer.from_pretrained(model_id)

requirements.txt

@@ -4,4 +4,5 @@ newsapi_python==0.2.7
 newspaper3k==0.2.8
 torch==2.6.0
 transformers==4.50.0
-lxml_html_clean==0.4.1
+lxml_html_clean==0.4.1
+accelerate==1.5.2