Create config.json

config.json

@@ -1,27 +1,28 @@
 {
-  "_name_or_path": "/checkpoint/dpf/models/cm-1.3B-hf",
-  "activation_dropout": 0.0,
-  "activation_function": "gelu",
   "architectures": [
-    "XGLMForCausalLM"
+    "LlamaForCausalLM"
   ],
-  "attention_dropout": 0.1,
-  "attention_heads": 32,
-  "bos_token_id": 0,
-  "d_model": 2048,
-  "decoder_start_token_id": 2,
-  "dropout": 0.1,
-  "eos_token_id": 2,
-  "ffn_dim": 8192,
-  "init_std": 0.02,
-  "layerdrop": 0.0,
-  "max_position_embeddings": 2048,
-  "model_type": "xglm",
-  "num_layers": 24,
-  "pad_token_id": 1,
-  "scale_embedding": true,
-  "torch_dtype": "float16",
-  "transformers_version": "4.18.0.dev0",
+  "bos_token_id": 32013,
+  "eos_token_id": 32021,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5504,
+  "max_position_embeddings": 16384,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 4.0,
+    "type": "linear"
+  },
+  "rope_theta": 100000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.33.1",
   "use_cache": true,
-  "vocab_size": 50518
-}
+  "vocab_size": 32256
+}