Update config.json

config.json

@@ -1,37 +1,39 @@
 {
-  "_name_or_path": "lilmeaty/abcdef",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
-  "attention_dropout": 0.1,
-  "bos_token_id": 0,
-  "eos_token_id": 1,
-  "head_dim": 64,
-  "output_dim": 256,
-  "hidden_size": 1024,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
   "hidden_act": "silu",
-  "initializer_range": 0.01,
-  "max_position_embeddings": 1024,
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
   "mlp_bias": false,
   "model_type": "llama",
-  "num_attention_heads": 8,
-  "num_hidden_layers": 1,
-  "num_key_value_heads": 4,
-  "pad_token_id": 1,
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "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": 1023,
+    "original_max_position_embeddings": 8192,
     "rope_type": "llama3"
   },
   "rope_theta": 500000.0,
-  "tie_word_embeddings": false,
-  "transformers_version": "4.46.1",
-  "unsloth_version": "2024.9.post3",
-  "use_cache": false,
-  "vocab_size": 50257
-}
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256
+}