chore: correct data paths in dpo config
This commit is contained in:
@@ -1,14 +1,14 @@
|
||||
# MLX DPO Training Configuration for Hermes 4 (8B Class)
|
||||
# Optimized for Apple Silicon execution (daily driver capability).
|
||||
|
||||
model: "NousResearch/Hermes-4-8B"
|
||||
model: "mlx-community/Hermes-3-Llama-3.1-8B-4bit"
|
||||
train: true
|
||||
|
||||
# Use the curated DPO preference pairs dataset
|
||||
data: "data/"
|
||||
data: "autolora/data/dpo/"
|
||||
|
||||
# Output adapter configuration
|
||||
adapter_path: "adapters/dpo_8b_adapter"
|
||||
adapter_path: "autolora/adapters/dpo-8b-adapter"
|
||||
save_every: 200
|
||||
|
||||
# DPO parameters
|
||||
|
||||
Reference in New Issue
Block a user