Update config.json

config.json

@@ -1,7 +1,8 @@
 {
   "architectures": [
-    "LlamaForCausalLM"
+    "JiRackTernaryModel"
   ],
+  "model_type": "jirack_ternary",
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
@@ -14,23 +15,28 @@
   "intermediate_size": 53248,
   "max_position_embeddings": 131072,
   "mlp_bias": false,
-  "model_type": "llama",
   "num_attention_heads": 128,
   "num_hidden_layers": 126,
-  "num_key_value_heads": 8,
+  "num_key_value_heads": 16,
   "pad_token_id": null,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "quant_method": "bitnet",
+    "bits": 2,
+    "packing": "2bit_uint8",
+    "group_size": 128
+  },
   "rms_norm_eps": 1e-05,
-  "rope_parameters": {
+  "rope_scaling": {
     "factor": 8.0,
     "high_freq_factor": 4.0,
     "low_freq_factor": 1.0,
     "original_max_position_embeddings": 8192,
-    "rope_theta": 500000.0,
     "rope_type": "llama3"
   },
+  "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "transformers_version": "5.0.0",
   "use_cache": true,
   "vocab_size": 128256
-}
+}