Trained with Unsloth - config

config.json

@@ -6,16 +6,16 @@
     "attention_dropout": 0.0,
     "bos_token_id": 128000,
     "eos_token_id": 128009,
-    "head_dim": 128,
+    "head_dim": 64,
     "hidden_act": "silu",
-    "hidden_size": 3072,
+    "hidden_size": 2048,
     "initializer_range": 0.02,
     "intermediate_size": 8192,
     "max_position_embeddings": 131072,
     "mlp_bias": false,
     "model_type": "llama",
-    "num_attention_heads": 24,
-    "num_hidden_layers": 28,
+    "num_attention_heads": 32,
+    "num_hidden_layers": 16,
     "num_key_value_heads": 8,
     "pad_token_id": 128004,
     "pretraining_tp": 1,