Fix issue with new caching mechanism in transformers and bump versions (#313)

*Issue #, if available:* Fixes #310 and closes #302

*Description of changes:* This PR fixes an issue related to the new
caching mechanism for T5 introduced in `transformers==4.54`. [Prior
versions
set](https://github.com/huggingface/transformers/blob/v4.53.3/src/transformers/models/t5/modeling_t5.py#L1328)
`encoder_config.is_encoder_decoder = False` when initializing encoder
and decoder. Following transformers, we also initialized Chronos-Bolt in
the same way. However, in v4.54 this line [has been
removed](https://github.com/huggingface/transformers/blob/3fd456b200ba434e567412cc4517309482653f60/src/transformers/models/t5/modeling_t5.py#L1301)
and [new logic has been
added](https://github.com/huggingface/transformers/blob/3fd456b200ba434e567412cc4517309482653f60/src/transformers/models/t5/modeling_t5.py#L494)
which relies on `is_encoder_decoder` [being
True](https://github.com/huggingface/transformers/blob/3fd456b200ba434e567412cc4517309482653f60/src/transformers/models/t5/modeling_t5.py#L1007).
This causes Chronos-Bolt to break as described in #310. This PR removes
`is_encoder_decoder = False` for both encoder and decoder which fixes
the issue. I re-ran our mini eval in the CI and got the same results for
v4.54 and v4.48 (our current lower bound).

This PR also bumps package versions. 


By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.

Author: abdulfatir

pyproject.toml

@@ -1,25 +1,21 @@
 [project]
 name = "chronos-forecasting"
-version = "1.5.2"
+version = "1.5.3"
 authors = [
-  { name="Abdul Fatir Ansari", email="ansarnd@amazon.com" },
-  { name="Lorenzo Stella", email="stellalo@amazon.com" },
-  { name="Caner Turkmen", email="atturkm@amazon.com" },
+  { name = "Abdul Fatir Ansari", email = "ansarnd@amazon.com" },
+  { name = "Lorenzo Stella", email = "stellalo@amazon.com" },
+  { name = "Caner Turkmen", email = "atturkm@amazon.com" },
 ]
 description = "Chronos: Pretrained models for time series forecasting"
 readme = "README.md"
 license = { file = "LICENSE" }
 requires-python = ">=3.9"
-dependencies = [
-    "torch>=2.0,<3",         # package was tested on 2.2
-    "transformers>=4.48,<5",
-    "accelerate>=0.32,<2",
-]
+dependencies = ["torch>=2.0,<3", "transformers>=4.48,<5", "accelerate>=0.32,<2"]
 classifiers = [
-    "Programming Language :: Python :: 3",
-    "License :: OSI Approved :: Apache Software License",
-    "Operating System :: OS Independent",
-    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+  "Programming Language :: Python :: 3",
+  "License :: OSI Approved :: Apache Software License",
+  "Operating System :: OS Independent",
+  "Topic :: Scientific/Engineering :: Artificial Intelligence",
 ]
 
 [build-system]
@@ -30,10 +26,24 @@ build-backend = "hatchling.build"
 packages = ["src/chronos"]
 
 [project.optional-dependencies]
-test = ["pytest~=8.0", "numpy~=1.21"]
+test = ["pytest~=8.0", "numpy>=1.21,<3"]
 typecheck = ["mypy~=1.9"]
-training = ["gluonts[pro]~=0.15", "numpy~=1.21", "datasets~=2.18", "typer", "typer-config", "joblib", "scikit-learn", "tensorboard"]
-evaluation = ["gluonts[pro]~=0.15", "numpy~=1.21", "datasets~=2.18", "typer"]
+training = [
+  "gluonts[pro]~=0.15",
+  "numpy>=1.21,<3",
+  "datasets>=2.18,<4",
+  "typer",
+  "typer-config",
+  "joblib",
+  "scikit-learn",
+  "tensorboard",
+]
+evaluation = [
+  "gluonts[pro]~=0.15",
+  "numpy>=1.21,<3",
+  "datasets>=2.18,<4",
+  "typer",
+]
 
 [project.urls]
 Homepage = "https://github.com/amazon-science/chronos-forecasting"
@@ -42,3 +52,11 @@ Paper = "https://arxiv.org/abs/2403.07815"
 
 [tool.mypy]
 ignore_missing_imports = true
+
+[tool.ruff]
+line-length = 88
+lint.ignore = [
+  "E501", # Line too long
+  "E731", # Do not assign a `lambda` expression, use a `def`
+  "E722", # Do not use bare `except`
+]

src/chronos/chronos.py

@@ -302,10 +302,12 @@ def encode(
             A tensor of encoder embeddings with shape
             (batch_size, sequence_length, d_model).
         """
-        assert (
-            self.config.model_type == "seq2seq"
-        ), "Encoder embeddings are only supported for encoder-decoder models"
-        assert hasattr(self.model, "encoder")
+        assert self.config.model_type == "seq2seq", (
+            "Encoder embeddings are only supported for encoder-decoder models"
+        )
+        assert hasattr(self.model, "encoder") and isinstance(
+            self.model.encoder, nn.Module
+        )
 
         return self.model.encoder(
             input_ids=input_ids, attention_mask=attention_mask
@@ -346,7 +348,7 @@ def forward(
         if top_p is None:
             top_p = self.config.top_p
 
-        assert hasattr(self.model, "generate")
+        assert callable(getattr(self.model, "generate", None))
 
         preds = self.model.generate(
             input_ids=input_ids,
@@ -362,7 +364,7 @@ def forward(
                 top_k=top_k,
                 top_p=top_p,
             ),
-        )
+        )  # type: ignore
 
         if self.config.model_type == "seq2seq":
             preds = preds[..., 1:]  # remove the decoder start token

src/chronos/chronos_bolt.py

@@ -179,7 +179,6 @@ def __init__(self, config: T5Config):
         encoder_config = copy.deepcopy(config)
         encoder_config.is_decoder = False
         encoder_config.use_cache = False
-        encoder_config.is_encoder_decoder = False
         self.encoder = T5Stack(encoder_config, self.shared)
 
         self._init_decoder(config)
@@ -381,7 +380,6 @@ def forward(
     def _init_decoder(self, config):
         decoder_config = copy.deepcopy(config)
         decoder_config.is_decoder = True
-        decoder_config.is_encoder_decoder = False
         decoder_config.num_layers = config.num_decoder_layers
         self.decoder = T5Stack(decoder_config, self.shared)