Merge branch 'main' into adding-dpo-training

llms/mlx_lm/examples/lora_config.yaml

@@ -20,6 +20,15 @@ training_mode: normal
 # reference_model_path: "mlx_model"
 # train_bias_only: False
 
+# The Optimizer with its possible inputs
+optimizer: adamw
+# optimizer_config:
+#   adamw:
+#     betas: [0.9, 0.98]
+#     eps: 1e-6
+#     weight_decay: 0.05
+#     bias_correction: true
+
 # Directory with {train, valid, test}.jsonl files
 data: "/path/to/training/data"