handle warnings from v5 upgrade (#3376)

requirements.txt

@@ -16,7 +16,7 @@ transformers==5.0.0
 accelerate==1.12.0
 datasets==4.5.0
 deepspeed>=0.18.3
-trl==0.27.0
+trl==0.27.1
 hf_xet==1.2.0
 kernels==0.11.5
 

src/axolotl/cli/__init__.py

@@ -5,6 +5,6 @@ import os
 from axolotl.logging_config import configure_logging
 
 os.environ.setdefault("TOKENIZERS_PARALLELISM", "false")
-os.environ.setdefault("HF_HUB_ENABLE_HF_TRANSFER", "1")
+os.environ.setdefault("HF_XET_HIGH_PERFORMANCE", "1")
 
 configure_logging()

src/axolotl/core/trainers/trl.py

@@ -1,12 +1,10 @@
 """Module for TRL RL trainers"""
 
-from trl import (
-    CPOTrainer,
-    KTOTrainer,
-    ORPOTrainer,
-    PRMTrainer,
-    RewardTrainer,
-)
+from trl import RewardTrainer
+from trl.experimental.cpo import CPOTrainer
+from trl.experimental.kto import KTOTrainer
+from trl.experimental.orpo import ORPOTrainer
+from trl.experimental.prm import PRMTrainer
 
 from axolotl.core.trainers.mixins import DistributedParallelMixin, RngLoaderMixin
 from axolotl.core.trainers.mixins.optimizer import OptimizerInitMixin, OptimizerMixin

src/axolotl/core/training_args.py

@@ -8,7 +8,11 @@ from dataclasses import dataclass, field
 from typing import Optional, Type
 
 from transformers import TrainingArguments
-from trl import CPOConfig, KTOConfig, ORPOConfig, PRMConfig, RewardConfig
+from trl import RewardConfig
+from trl.experimental.cpo import CPOConfig
+from trl.experimental.kto import KTOConfig
+from trl.experimental.orpo import ORPOConfig
+from trl.experimental.prm import PRMConfig
 
 from axolotl.integrations.config import merge_training_args
 

tests/prompt_strategies/conftest.py

@@ -141,6 +141,7 @@ def fixture_phi35_tokenizer():
 
 
 @pytest.fixture(name="phi4_tokenizer", scope="session", autouse=True)
+@enable_hf_offline
 def fixture_phi4_tokenizer():
     tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-4-reasoning")
     return tokenizer
@@ -178,6 +179,7 @@ def fixture_devstral_1_1_tokenizer():
 
 
 @pytest.fixture(name="qwen3_tokenizer")
+@enable_hf_offline
 def qwen3_tokenizer_fixture(
     download_qwen3_half_billion_model,
 ):  # pylint: disable=unused-argument,redefined-outer-name