Update config.json

config.json

@@ -1,40 +1,36 @@
 {
+  "_name_or_path": "meta-llama/Llama-3.2-1B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
   "model_type": "llama",
-  "architectures": ["LlamaForCausalLM"],
-  "hidden_size": 4096,
   "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_labels": 50257,
-  "vocab_size": 50257,
-  "max_position_embeddings": 2048,
-  "hidden_dropout_prob": 0.1,
-  "attention_probs_dropout_prob": 0.1,
-  "initializer_range": 0.02,
-  "layer_norm_eps": 1e-5,
-  "gradient_checkpointing": true,
-  "use_cache": false,
-  "quantization": {
-    "enabled": true,
-    "bits": 4,
-    "method": "PTQ",
-    "reduce_precision": true
-  },
-  "training": {
-    "epochs": 3,
-    "batch_size": 16,
-    "learning_rate": 5e-5,
-    "warmup_steps": 100,
-    "weight_decay": 0.01,
-    "logging_steps": 50,
-    "save_steps": 500,
-    "eval_steps": 100
-  },
-  "tokenizer": {
-    "type": "LlamaTokenizer",
-    "model_max_length": 2048
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
   },
-  "output_dir": "./output",
-  "overwrite_output_dir": true,
-  "save_total_limit": 3,
-  "evaluation_strategy": "epoch"
-}
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 128256
+}