©️ Copyrights update (#2454)

* First changes * Other files * Finally * rm comment * fix nashmd * Fix example * Fix example [ci skip]
huggingface · Dec 10, 2024 · 9410874 · 9410874
1 parent 9c5388b
commit 9410874
Show file tree

Hide file tree

Showing 141 changed files with 191 additions and 181 deletions.
diff --git a/examples/datasets/hh-rlhf-helpful-base.py b/examples/datasets/hh-rlhf-helpful-base.py
@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diff --git a/examples/datasets/lm-human-preferences-descriptiveness.py b/examples/datasets/lm-human-preferences-descriptiveness.py
@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diff --git a/examples/datasets/lm-human-preferences-sentiment.py b/examples/datasets/lm-human-preferences-sentiment.py
@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diff --git a/examples/datasets/prm800k.py b/examples/datasets/prm800k.py
@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diff --git a/examples/datasets/rlaif-v.py b/examples/datasets/rlaif-v.py
@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diff --git a/examples/datasets/tldr.py b/examples/datasets/tldr.py
@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diff --git a/examples/datasets/tldr_preference.py b/examples/datasets/tldr_preference.py
@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diff --git a/examples/datasets/tokenize_ds.py b/examples/datasets/tokenize_ds.py
@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diff --git a/examples/datasets/ultrafeedback-prompt.py b/examples/datasets/ultrafeedback-prompt.py
@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diff --git a/examples/datasets/ultrafeedback.py b/examples/datasets/ultrafeedback.py
@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diff --git a/examples/research_projects/stack_llama/scripts/merge_peft_adapter.py b/examples/research_projects/stack_llama/scripts/merge_peft_adapter.py
@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diff --git a/examples/research_projects/stack_llama/scripts/reward_modeling.py b/examples/research_projects/stack_llama/scripts/reward_modeling.py
@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diff --git a/examples/research_projects/stack_llama/scripts/rl_training.py b/examples/research_projects/stack_llama/scripts/rl_training.py
@@ -1,4 +1,4 @@
-# Copyright 2022 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -11,6 +11,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+
 from dataclasses import dataclass, field
 from typing import Optional
 

diff --git a/examples/research_projects/stack_llama/scripts/supervised_finetuning.py b/examples/research_projects/stack_llama/scripts/supervised_finetuning.py
@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diff --git a/examples/research_projects/stack_llama_2/scripts/dpo_llama2.py b/examples/research_projects/stack_llama_2/scripts/dpo_llama2.py
@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diff --git a/examples/research_projects/stack_llama_2/scripts/sft_llama2.py b/examples/research_projects/stack_llama_2/scripts/sft_llama2.py
@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diff --git a/examples/research_projects/tools/calculator.py b/examples/research_projects/tools/calculator.py
@@ -1,4 +1,4 @@
-# Copyright 2023 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diff --git a/examples/research_projects/tools/python_interpreter.py b/examples/research_projects/tools/python_interpreter.py
@@ -1,4 +1,4 @@
-# Copyright 2023 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diff --git a/examples/research_projects/tools/triviaqa.py b/examples/research_projects/tools/triviaqa.py
@@ -1,4 +1,4 @@
-# Copyright 2023 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diff --git a/examples/research_projects/toxicity/scripts/evaluate-toxicity.py b/examples/research_projects/toxicity/scripts/evaluate-toxicity.py
@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diff --git a/examples/research_projects/toxicity/scripts/gpt-j-6b-toxicity.py b/examples/research_projects/toxicity/scripts/gpt-j-6b-toxicity.py
@@ -1,4 +1,4 @@
-# Copyright 2023 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -11,6 +11,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+
 from dataclasses import dataclass, field
 from typing import Optional
 

diff --git a/examples/scripts/alignprop.py b/examples/scripts/alignprop.py
@@ -1,4 +1,4 @@
-# Copyright 2023 metric-space, The HuggingFace Team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -11,6 +11,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+
 """
 Total Batch size = 128 = 4 (num_gpus) * 8 (per_device_batch) * 4 (accumulation steps)
 Feel free to reduce batch size or increasing truncated_rand_backprop_min to a higher value to reduce memory usage.

diff --git a/examples/scripts/bco.py b/examples/scripts/bco.py
@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diff --git a/examples/scripts/chat.py b/examples/scripts/chat.py
@@ -12,7 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-
 import copy
 import json
 import os

diff --git a/examples/scripts/cpo.py b/examples/scripts/cpo.py
@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -11,6 +11,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+
 """
 Run the CPO training script with the following command with some example arguments.
 In general, the optimal configuration for CPO will be similar to that of DPO:

diff --git a/examples/scripts/ddpo.py b/examples/scripts/ddpo.py
@@ -1,4 +1,4 @@
-# Copyright 2023 metric-space, The HuggingFace Team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -11,6 +11,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+
 """
 python examples/scripts/ddpo.py \
     --num_epochs=200 \

diff --git a/examples/scripts/dpo.py b/examples/scripts/dpo.py
@@ -1,4 +1,4 @@
-# Copyright 2023 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -11,6 +11,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+
 """
 # Full training
 python examples/scripts/dpo.py \

diff --git a/examples/scripts/dpo_online.py b/examples/scripts/dpo_online.py
@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -11,6 +11,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+
 """
 Usage:
 

diff --git a/examples/scripts/dpo_vlm.py b/examples/scripts/dpo_vlm.py
@@ -1,4 +1,4 @@
-# Copyright 2023 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -11,6 +11,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+
 """
 accelerate launch examples/scripts/dpo_vlm.py \
     --dataset_name HuggingFaceH4/rlaif-v_formatted \

diff --git a/examples/scripts/evals/judge_tldr.py b/examples/scripts/evals/judge_tldr.py
@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diff --git a/examples/scripts/gkd.py b/examples/scripts/gkd.py
@@ -1,4 +1,4 @@
-# Copyright 2023 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -11,6 +11,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+
 """
 # Full training:
 python examples/scripts/gkd.py \

diff --git a/examples/scripts/kto.py b/examples/scripts/kto.py
@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diff --git a/examples/scripts/nash_md.py b/examples/scripts/nash_md.py
@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -11,6 +11,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+
 """
 Usage:
 

diff --git a/examples/scripts/orpo.py b/examples/scripts/orpo.py
@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -11,6 +11,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+
 """
 Run the ORPO training script with the following command with some example arguments.
 In general, the optimal configuration for ORPO will be similar to that of DPO without the need for a reference model:

diff --git a/examples/scripts/ppo/ppo.py b/examples/scripts/ppo/ppo.py
@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diff --git a/examples/scripts/ppo/ppo_tldr.py b/examples/scripts/ppo/ppo_tldr.py
@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diff --git a/examples/scripts/reward_modeling.py b/examples/scripts/reward_modeling.py
@@ -1,4 +1,4 @@
-# Copyright 2023 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -11,6 +11,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+
 """
 Full training:
 python examples/scripts/reward_modeling.py \

diff --git a/examples/scripts/rloo/rloo.py b/examples/scripts/rloo/rloo.py
@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diff --git a/examples/scripts/rloo/rloo_tldr.py b/examples/scripts/rloo/rloo_tldr.py
@@ -1,4 +1,4 @@
-# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diff --git a/examples/scripts/sft.py b/examples/scripts/sft.py
@@ -1,4 +1,4 @@
-# Copyright 2023 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -11,6 +11,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+
 """
 # Full training
 python examples/scripts/sft.py \

diff --git a/examples/scripts/sft_video_llm.py b/examples/scripts/sft_video_llm.py
@@ -1,4 +1,4 @@
-# Copyright 2024. All rights reserved.
+# Copyright 2024 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -11,6 +11,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+
 """
 Example usage:
 accelerate launch \
@@ -53,20 +54,9 @@
 from datasets import load_dataset
 from peft import LoraConfig
 from qwen_vl_utils import process_vision_info
-from transformers import (
-    AutoModelForVision2Seq,
-    AutoProcessor,
-    BitsAndBytesConfig,
-    Qwen2VLProcessor,
-)
-
-from trl import (
-    SFTConfig,
-    SFTTrainer,
-    get_kbit_device_map,
-)
-from trl.commands.cli_utils import SFTScriptArguments, TrlParser
-from trl.trainer import ModelConfig
+from transformers import AutoModelForVision2Seq, AutoProcessor, BitsAndBytesConfig, Qwen2VLProcessor
+
+from trl import ModelConfig, ScriptArguments, SFTConfig, SFTTrainer, TrlParser, get_kbit_device_map
 
 
 def download_video(url: str, cache_dir: str) -> str:
@@ -161,7 +151,7 @@ def collate_fn(examples: list[dict[str, Any]]) -> dict[str, torch.Tensor]:
 
 
 @dataclass
-class CustomScriptArguments(SFTScriptArguments):
+class CustomScriptArguments(ScriptArguments):
     video_cache_dir: str = "/tmp/videos/"