Upload config

config.json

@@ -23,6 +23,19 @@
   "num_hidden_layers": 126,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "backend": "autoawq",
+    "bits": 4,
+    "do_fuse": false,
+    "exllama_config": null,
+    "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
+  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": {
     "factor": 8.0,