Update config.json

config.json

@@ -1,38 +1,29 @@
 {
-  "_num_labels": 1,
-  "activation_function": "gelu_new",
+  "_name_or_path": "lcz_v2",
+  "_attn_implementation": "eager",
   "architectures": [
-    "GPT2LMHeadModel"
+    "LlamaForCausalLM"
   ],
-  "attn_pdrop": 0.1,
+  "attention_bias": true,
+  "attention_dropout": 0.0,
   "bos_token_id": 50256,
-  "embd_pdrop": 0.1,
   "eos_token_id": 50256,
-  "id2label": {
-    "0": "LABEL_0"
-  },
+  "hidden_act": "silu",
+  "hidden_size": 2048,
   "initializer_range": 0.02,
-  "label2id": {
-    "LABEL_0": 0
-  },
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "gpt2",
-  "n_ctx": 1024,
-  "n_embd": 768,
-  "n_head": 12,
-  "n_layer": 6,
-  "n_positions": 1024,
-  "resid_pdrop": 0.1,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
-  "task_specific_params": {
-    "text-generation": {
-      "do_sample": true,
-      "max_length": 50
-    }
-  },
+  "intermediate_size": 6112,
+  "max_position_embeddings": 1024,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.0",
+  "use_cache": false,
   "vocab_size": 50257
 }