Update config.json

config.json

@@ -18,16 +18,18 @@
   "num_key_value_heads": 32,
   "pretraining_tp": 1,
   "quantization_config": {
-    "backend": "llm-awq",
-    "bits": 4,
-    "do_fuse": false,
-    "fuse_max_seq_len": null,
-    "group_size": 128,
-    "modules_to_fuse": null,
-    "modules_to_not_convert": null,
-    "quant_method": "awq",
-    "version": "gemm",
-    "zero_point": true
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
+    "bnb_4bit_compute_dtype": "float32",
+    "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": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
   },
   "rms_norm_eps": 1e-06,
   "rope_scaling": {