diff options
Diffstat (limited to 'collaborativeagents/adapters/reflection_grpo_adapter.py')
| -rw-r--r-- | collaborativeagents/adapters/reflection_grpo_adapter.py | 9 |
1 files changed, 5 insertions, 4 deletions
diff --git a/collaborativeagents/adapters/reflection_grpo_adapter.py b/collaborativeagents/adapters/reflection_grpo_adapter.py index 09c5b26..3c10942 100644 --- a/collaborativeagents/adapters/reflection_grpo_adapter.py +++ b/collaborativeagents/adapters/reflection_grpo_adapter.py @@ -18,10 +18,11 @@ import torch from transformers import AutoModelForCausalLM, AutoTokenizer from json_repair import repair_json -# Model paths - Use GRPO-trained model if available, fallback to base -GRPO_MODEL_PATH = "/projects/bfqt/users/yurenh2/ml-projects/personalization-user-model/collaborativeagents/training/outputs/grpo_reflection/final" -SFT_MODEL_PATH = "/projects/bfqt/users/yurenh2/ml-projects/personalization-user-model/collaborativeagents/training/outputs/sft_reflection" -DEFAULT_MODEL_PATH = "/projects/bfqt/users/yurenh2/ml-projects/personalization-user-model/models/llama-3.1-8b-instruct" +# Model paths - computed relative to project root +_PROJECT_ROOT = Path(__file__).parent.parent.parent +GRPO_MODEL_PATH = str(_PROJECT_ROOT / "collaborativeagents/training/outputs/grpo_reflection/final") +SFT_MODEL_PATH = str(_PROJECT_ROOT / "collaborativeagents/training/outputs/sft_reflection") +DEFAULT_MODEL_PATH = str(_PROJECT_ROOT / "models/llama-3.1-8b-instruct") def get_best_available_model(): """Get the best available model path (GRPO > SFT > base).""" |