upgrade transformers==5.3.0 trl==0.29.0 kernels (#3459)

* upgrade transformers==5.3.0 trl==0.29.0 kernels

* use latest deepspeed fixes

* use corect image for cleanup

* fix test outputs for tokenizer fixes upstream

* fix import:

* keep trl at 0.28.0

* handle updated API

* use latest trl since 0.28.0 doesn't work with latest transformers

* use trl experimental for pad to length

* monkeypatch trl with ORPOTrainer so liger doesn't croak

* upgrade accelerate

* more fixes

* move patch for orpotrainer

* load the imports later

* remove use_logits_to_keep

* fix loss_type arg as a list

* fetch hf cache from s3

* just manually download the missing model for now

* lint for pre-commit update

* a few more missing models on disk

* fix: loss_type internally now list

* fix: remove deprecated code and raise deprecate

* fix: remove unneeded blocklist

* fix: remove reliance on transformers api to find package available

* chore: refactor shim for less sideeffect

* fix: silent trl experimental warning

---------

Co-authored-by: NanoCode012 <nano@axolotl.ai>

src/axolotl/integrations/liger/plugin.py

@@ -8,9 +8,6 @@ import sys
 from axolotl.integrations.base import BasePlugin
 from axolotl.utils.logging import get_logger
 
-from .models.base import patch_lce_forward
-from .utils import patch_with_compile_disable
-
 LOG = get_logger(__name__)
 
 
@@ -23,10 +20,18 @@ class LigerPlugin(BasePlugin):
         return "axolotl.integrations.liger.LigerArgs"
 
     def pre_model_load(self, cfg):
+        # shim: liger-kernel 0.7.0 imports ORPOTrainer from old trl path
+        import trl.trainer
+        from trl.experimental.orpo import ORPOTrainer
+
+        trl.trainer.ORPOTrainer = ORPOTrainer
+
         if cfg.torch_compile:
             # torch compile will unnecessarily attempt to optimize the triton kernel unless explicitly disabled
             import liger_kernel.ops.fused_linear_cross_entropy
 
+            from .utils import patch_with_compile_disable
+
             patch_with_compile_disable(
                 liger_kernel.ops.fused_linear_cross_entropy,
                 "fused_linear_cross_entropy_forward",
@@ -35,6 +40,7 @@ class LigerPlugin(BasePlugin):
                 liger_kernel.ops.fused_linear_cross_entropy,
                 "fused_linear_cross_entropy_backward",
             )
+
         from liger_kernel.transformers.cross_entropy import LigerCrossEntropyLoss
         from liger_kernel.transformers.functional import liger_cross_entropy
         from liger_kernel.transformers.layer_norm import LigerLayerNorm
@@ -192,6 +198,8 @@ class LigerPlugin(BasePlugin):
             )
         elif cfg.liger_fused_linear_cross_entropy:
             try:
+                from .models.base import patch_lce_forward
+
                 patch_lce_forward(cfg.model_config_type)
                 LOG.warning_once(
                     f"Applied ONLY liger_fused_linear_cross_entropy genericpatches for model type: {cfg.model_config_type}"