Trained with Unsloth - config

config.json

@@ -6,25 +6,32 @@
     "attention_dropout": 0.0,
     "bos_token_id": 128000,
     "torch_dtype": "float16",
-    "eos_token_id": 128001,
-    "head_dim": 128,
+    "eos_token_id": 128009,
+    "head_dim": 64,
     "hidden_act": "silu",
-    "hidden_size": 4096,
+    "hidden_size": 2048,
     "initializer_range": 0.02,
-    "intermediate_size": 14336,
-    "max_position_embeddings": 8192,
+    "intermediate_size": 8192,
+    "max_position_embeddings": 131072,
     "mlp_bias": false,
     "model_type": "llama",
     "num_attention_heads": 32,
-    "num_hidden_layers": 32,
+    "num_hidden_layers": 16,
     "num_key_value_heads": 8,
-    "pad_token_id": 128255,
+    "pad_token_id": 128004,
     "pretraining_tp": 1,
     "rms_norm_eps": 1e-05,
-    "rope_scaling": null,
+    "rope_scaling": {
+        "factor": 32.0,
+        "high_freq_factor": 4.0,
+        "low_freq_factor": 1.0,
+        "original_max_position_embeddings": 8192,
+        "rope_type": "llama3"
+    },
     "rope_theta": 500000.0,
-    "tie_word_embeddings": false,
+    "tie_word_embeddings": true,
     "transformers_version": "4.56.2",
+    "unsloth_fixed": true,
     "unsloth_version": "2025.10.8",
     "use_cache": true,
     "vocab_size": 128256