update config.json

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "PoppyWang/ContaLLM-Beauty-8B-Instruct",
+  "_name_or_path": "ContaAI/ContaLLM-Beauty-8B-Instruct-4bit",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -24,6 +24,18 @@
   "num_key_value_heads": 8,
   "pad_token_id": 128004,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "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"
+  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": {
     "factor": 8.0,