Update pre-commit-config.yaml + pyproject.toml + ceil rerun & transformer dependencies version (#1520)

* chore: update .gitignore

* chore: update pre-commit

* chore(deps): update pyproject

* fix(ci): multiple fixes

* chore: pre-commit apply

* chore: address review comments

* Update pyproject.toml

Co-authored-by: Ben Zhang <5977478+ben-z@users.noreply.github.com>
Signed-off-by: Steven Palma <imstevenpmwork@ieee.org>

* chore(deps): add todo

---------

Signed-off-by: Steven Palma <imstevenpmwork@ieee.org>
Co-authored-by: Ben Zhang <5977478+ben-z@users.noreply.github.com>

src/lerobot/policies/act/modeling_act.py

@@ -21,8 +21,8 @@ The majority of changes here involve removing unused code, unifying naming, and
 
 import math
 from collections import deque
+from collections.abc import Callable
 from itertools import chain
-from typing import Callable
 
 import einops
 import numpy as np
@@ -216,7 +216,7 @@ class ACTTemporalEnsembler:
                 continue
             avg *= exp_weights[:i].sum()
             avg += item * exp_weights[i]
-            avg /= exp_weights[:i+1].sum()
+            avg /= exp_weights[: i + 1].sum()
         print("online", avg)
         ```
         """

src/lerobot/policies/diffusion/modeling_diffusion.py

@@ -22,7 +22,7 @@ TODO(alexander-soare):
 
 import math
 from collections import deque
-from typing import Callable
+from collections.abc import Callable
 
 import einops
 import numpy as np

src/lerobot/policies/pi0/paligemma_with_expert.py

@@ -12,7 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from typing import List, Optional, Union
 
 import torch
 import torch.version
@@ -228,12 +227,12 @@ class PaliGemmaWithExpertModel(PreTrainedModel):
     # TODO: break down this huge forward into modules or functions
     def forward(
         self,
-        attention_mask: Optional[torch.Tensor] = None,
-        position_ids: Optional[torch.LongTensor] = None,
-        past_key_values: Optional[Union[List[torch.FloatTensor], Cache]] = None,
-        inputs_embeds: List[torch.FloatTensor] = None,
-        use_cache: Optional[bool] = None,
-        fill_kv_cache: Optional[bool] = None,
+        attention_mask: torch.Tensor | None = None,
+        position_ids: torch.LongTensor | None = None,
+        past_key_values: list[torch.FloatTensor] | Cache | None = None,
+        inputs_embeds: list[torch.FloatTensor] = None,
+        use_cache: bool | None = None,
+        fill_kv_cache: bool | None = None,
     ):
         models = [self.paligemma.language_model, self.gemma_expert.model]
 

src/lerobot/policies/pretrained.py

@@ -12,20 +12,20 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 import abc
+import builtins
 import logging
 import os
 from importlib.resources import files
 from pathlib import Path
 from tempfile import TemporaryDirectory
-from typing import List, Type, TypeVar
+from typing import TypeVar
 
 import packaging
 import safetensors
 from huggingface_hub import HfApi, ModelCard, ModelCardData, hf_hub_download
 from huggingface_hub.constants import SAFETENSORS_SINGLE_FILE
 from huggingface_hub.errors import HfHubHTTPError
-from safetensors.torch import load_model as load_model_as_safetensor
-from safetensors.torch import save_model as save_model_as_safetensor
+from safetensors.torch import load_model as load_model_as_safetensor, save_model as save_model_as_safetensor
 from torch import Tensor, nn
 
 from lerobot.configs.policies import PreTrainedConfig
@@ -67,7 +67,7 @@ class PreTrainedPolicy(nn.Module, HubMixin, abc.ABC):
 
     @classmethod
     def from_pretrained(
-        cls: Type[T],
+        cls: builtins.type[T],
         pretrained_name_or_path: str | Path,
         *,
         config: PreTrainedConfig | None = None,
@@ -223,7 +223,7 @@ class PreTrainedPolicy(nn.Module, HubMixin, abc.ABC):
             logging.info(f"Model pushed to {commit_info.repo_url.url}")
 
     def generate_model_card(
-        self, dataset_repo_id: str, model_type: str, license: str | None, tags: List[str] | None
+        self, dataset_repo_id: str, model_type: str, license: str | None, tags: list[str] | None
     ) -> ModelCard:
         base_model = "lerobot/smolvla_base" if model_type == "smolvla" else None  # Set a base model
 

src/lerobot/policies/sac/modeling_sac.py

@@ -16,8 +16,9 @@
 # limitations under the License.
 
 import math
+from collections.abc import Callable
 from dataclasses import asdict
-from typing import Callable, Literal
+from typing import Literal
 
 import einops
 import numpy as np

src/lerobot/policies/smolvla/smolvlm_with_expert.py

@@ -13,7 +13,6 @@
 # limitations under the License.
 
 import copy
-from typing import List, Optional
 
 import torch
 from torch import nn
@@ -403,12 +402,12 @@ class SmolVLMWithExpertModel(nn.Module):
 
     def forward(
         self,
-        attention_mask: Optional[torch.Tensor] = None,
-        position_ids: Optional[torch.LongTensor] = None,
-        past_key_values: Optional[List[torch.FloatTensor]] = None,
-        inputs_embeds: List[torch.FloatTensor] = None,
-        use_cache: Optional[bool] = None,
-        fill_kv_cache: Optional[bool] = None,
+        attention_mask: torch.Tensor | None = None,
+        position_ids: torch.LongTensor | None = None,
+        past_key_values: list[torch.FloatTensor] | None = None,
+        inputs_embeds: list[torch.FloatTensor] = None,
+        use_cache: bool | None = None,
+        fill_kv_cache: bool | None = None,
     ):
         models = [self.get_vlm_model().text_model, self.lm_expert]
         model_layers = self.get_model_layers(models)

src/lerobot/policies/tdmpc/modeling_tdmpc.py

@@ -24,9 +24,9 @@ The comments in this code may sometimes refer to these references:
 # ruff: noqa: N806
 
 from collections import deque
+from collections.abc import Callable
 from copy import deepcopy
 from functools import partial
-from typing import Callable
 
 import einops
 import numpy as np

src/lerobot/policies/vqbet/modeling_vqbet.py

@@ -18,7 +18,7 @@
 
 import warnings
 from collections import deque
-from typing import Callable, List
+from collections.abc import Callable
 
 import einops
 import numpy as np
@@ -901,7 +901,7 @@ class MLP(torch.nn.Sequential):
     def __init__(
         self,
         in_channels: int,
-        hidden_channels: List[int],
+        hidden_channels: list[int],
     ):
         layers = []
         in_dim = in_channels

src/lerobot/policies/vqbet/vqbet_utils.py

@@ -17,10 +17,10 @@
 # limitations under the License.
 
 import math
+from collections.abc import Callable
 from functools import partial
 from math import ceil
 from random import randrange
-from typing import Callable
 
 import torch
 import torch.distributed as distributed
@@ -198,7 +198,7 @@ class GPT(nn.Module):
 
         # report number of parameters
         n_params = sum(p.numel() for p in self.parameters())
-        print("number of parameters: {:.2f}M".format(n_params / 1e6))
+        print(f"number of parameters: {n_params / 1e6:.2f}M")
 
     def forward(self, input, targets=None):
         device = input.device
@@ -255,7 +255,7 @@ class GPT(nn.Module):
         blacklist_weight_modules = (torch.nn.LayerNorm, torch.nn.Embedding)
         for mn, m in self.named_modules():
             for pn, _p in m.named_parameters():
-                fpn = "{}.{}".format(mn, pn) if mn else pn  # full param name
+                fpn = f"{mn}.{pn}" if mn else pn  # full param name
                 if pn.endswith("bias"):
                     # all biases will not be decayed
                     no_decay.add(fpn)