From d50436b01c51d4b4b0b9c97c03be2fa9a1fd04ef Mon Sep 17 00:00:00 2001
From: "github-actions[bot]"
 <41898282+github-actions[bot]@users.noreply.github.com>
Date: Wed, 12 Feb 2025 22:23:00 +0400
Subject: [PATCH] Upgrade transformers to 4.47 (#752) (#759)

---
 eland/ml/pytorch/transformers.py | 4 ++--
 setup.py                         | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/eland/ml/pytorch/transformers.py b/eland/ml/pytorch/transformers.py
index fb1bb69..40e5650 100644
--- a/eland/ml/pytorch/transformers.py
+++ b/eland/ml/pytorch/transformers.py
@@ -570,7 +570,7 @@ class _TraceableTextEmbeddingModel(_TransformerTraceableModel):
     def _prepare_inputs(self) -> transformers.BatchEncoding:
         return self._tokenizer(
             "This is an example sentence.",
-            padding="max_length",
+            padding="longest",
             return_tensors="pt",
         )
 
@@ -759,7 +759,7 @@ class TransformerModel:
         # a random or very large value.
         REASONABLE_MAX_LENGTH = 8192
         max_len = getattr(self._tokenizer, "model_max_length", None)
-        if max_len is not None and max_len < REASONABLE_MAX_LENGTH:
+        if max_len is not None and max_len <= REASONABLE_MAX_LENGTH:
             return int(max_len)
 
         max_sizes = getattr(self._tokenizer, "max_model_input_sizes", dict())
diff --git a/setup.py b/setup.py
index 2ad02ff..4ac65d1 100644
--- a/setup.py
+++ b/setup.py
@@ -65,7 +65,7 @@ extras = {
         "sentence-transformers>=2.1.0,<=2.7.0",
         # sentencepiece is a required dependency for the slow tokenizers
         # https://huggingface.co/transformers/v4.4.2/migration.html#sentencepiece-is-removed-from-the-required-dependencies
-        "transformers[sentencepiece]>=4.31.0,<4.44.0",
+        "transformers[sentencepiece]>=4.47.0",
     ],
 }
 extras["all"] = list({dep for deps in extras.values() for dep in deps})