Update config.json

config.json

@@ -11,6 +11,18 @@
   "mm_tokens_per_image": 256,
   "model_type": "gemma3",
   "pad_token_id": 0,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "float16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
   "text_config": {
     "attention_bias": false,
     "attention_dropout": 0.0,
@@ -60,4 +72,4 @@
     "torch_dtype": "float16",
     "vision_use_head": false
   }
-}
+}