Update config.json

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "Qwen/Qwen2.5-3B",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
@@ -15,14 +16,29 @@
   "num_attention_heads": 16,
   "num_hidden_layers": 36,
   "num_key_value_heads": 2,
+  "quantization_config": {
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "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": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
   "rms_norm_eps": 1e-06,
   "rope_theta": 1000000.0,
-  "sliding_window": 32768,
+  "sliding_window": null,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.40.1",
-  "use_cache": true,
+  "transformers_version": "4.44.2",
+  "use_cache": false,
   "use_mrope": false,
   "use_sliding_window": false,
-  "vocab_size": 151936
-}
+  "vocab_size": 151665
+}