text
stringlengths
7
328k
id
stringlengths
14
166
metadata
dict
__index_level_0__
int64
0
459
# coding=utf-8 # Copyright 2021 HuggingFace Inc. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or ag...
transformers/tests/models/chinese_clip/test_image_processing_chinese_clip.py/0
{ "file_path": "transformers/tests/models/chinese_clip/test_image_processing_chinese_clip.py", "repo_id": "transformers", "token_count": 2634 }
386
# Copyright 2022 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicabl...
transformers/tests/models/clipseg/test_processor_clipseg.py/0
{ "file_path": "transformers/tests/models/clipseg/test_processor_clipseg.py", "repo_id": "transformers", "token_count": 3413 }
387
# coding=utf-8 # Copyright 2022 The HuggingFace Inc. 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless r...
transformers/tests/models/conditional_detr/test_modeling_conditional_detr.py/0
{ "file_path": "transformers/tests/models/conditional_detr/test_modeling_conditional_detr.py", "repo_id": "transformers", "token_count": 10930 }
388
# coding=utf-8 # Copyright 2023 The HuggingFace Inc. 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless r...
transformers/tests/models/efficientformer/test_modeling_tf_efficientformer.py/0
{ "file_path": "transformers/tests/models/efficientformer/test_modeling_tf_efficientformer.py", "repo_id": "transformers", "token_count": 7249 }
389
# coding=utf-8 # Copyright 2020 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless requir...
transformers/tests/models/flaubert/test_modeling_flaubert.py/0
{ "file_path": "transformers/tests/models/flaubert/test_modeling_flaubert.py", "repo_id": "transformers", "token_count": 8613 }
390
# coding=utf-8 # Copyright 2020 HuggingFace Inc. team. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law...
transformers/tests/models/funnel/test_modeling_tf_funnel.py/0
{ "file_path": "transformers/tests/models/funnel/test_modeling_tf_funnel.py", "repo_id": "transformers", "token_count": 6844 }
391
# coding=utf-8 # Copyright 2022 Google LongT5 Authors and HuggingFace Inc. team. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless ...
transformers/tests/models/longt5/test_modeling_flax_longt5.py/0
{ "file_path": "transformers/tests/models/longt5/test_modeling_flax_longt5.py", "repo_id": "transformers", "token_count": 17644 }
392
# coding=utf-8 # Copyright 2021, The HuggingFace Inc. 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless ...
transformers/tests/models/marian/test_modeling_marian.py/0
{ "file_path": "transformers/tests/models/marian/test_modeling_marian.py", "repo_id": "transformers", "token_count": 15174 }
393
# coding=utf-8 # Copyright 2022 The HuggingFace Inc. 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless r...
transformers/tests/models/mobilenet_v2/test_modeling_mobilenet_v2.py/0
{ "file_path": "transformers/tests/models/mobilenet_v2/test_modeling_mobilenet_v2.py", "repo_id": "transformers", "token_count": 5588 }
394
# Copyright 2021 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicabl...
transformers/tests/models/mt5/test_modeling_flax_mt5.py/0
{ "file_path": "transformers/tests/models/mt5/test_modeling_flax_mt5.py", "repo_id": "transformers", "token_count": 950 }
395
# coding=utf-8 # Copyright 2022 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless requir...
transformers/tests/models/nezha/test_modeling_nezha.py/0
{ "file_path": "transformers/tests/models/nezha/test_modeling_nezha.py", "repo_id": "transformers", "token_count": 9040 }
396
# coding=utf-8 # Copyright 2020 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless requir...
transformers/tests/models/openai/test_modeling_tf_openai.py/0
{ "file_path": "transformers/tests/models/openai/test_modeling_tf_openai.py", "repo_id": "transformers", "token_count": 5057 }
397
# coding=utf-8 # Copyright 2023 The HuggingFace Inc. 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless r...
transformers/tests/models/patchtst/test_modeling_patchtst.py/0
{ "file_path": "transformers/tests/models/patchtst/test_modeling_patchtst.py", "repo_id": "transformers", "token_count": 6808 }
398
# coding=utf-8 # Copyright 2018 Salesforce and HuggingFace Inc. team. # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by a...
transformers/tests/models/phobert/test_tokenization_phobert.py/0
{ "file_path": "transformers/tests/models/phobert/test_tokenization_phobert.py", "repo_id": "transformers", "token_count": 1190 }
399
# Copyright 2020 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicabl...
transformers/tests/models/rag/test_retrieval_rag.py/0
{ "file_path": "transformers/tests/models/rag/test_retrieval_rag.py", "repo_id": "transformers", "token_count": 6761 }
400
# coding=utf-8 # Copyright 2022 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless requir...
transformers/tests/models/rembert/test_tokenization_rembert.py/0
{ "file_path": "transformers/tests/models/rembert/test_tokenization_rembert.py", "repo_id": "transformers", "token_count": 6759 }
401
# coding=utf-8 # Copyright 2022 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless requir...
transformers/tests/models/roc_bert/test_tokenization_roc_bert.py/0
{ "file_path": "transformers/tests/models/roc_bert/test_tokenization_roc_bert.py", "repo_id": "transformers", "token_count": 7488 }
402
# Copyright 2022 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicabl...
transformers/tests/models/seamless_m4t/test_tokenization_seamless_m4t.py/0
{ "file_path": "transformers/tests/models/seamless_m4t/test_tokenization_seamless_m4t.py", "repo_id": "transformers", "token_count": 15190 }
403
# coding=utf-8 # Copyright 2024 The HuggingFace Inc. 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless r...
transformers/tests/models/siglip/test_modeling_siglip.py/0
{ "file_path": "transformers/tests/models/siglip/test_modeling_siglip.py", "repo_id": "transformers", "token_count": 11477 }
404
# coding=utf-8 # Copyright 2022 The HuggingFace Inc. 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless r...
transformers/tests/models/speecht5/test_modeling_speecht5.py/0
{ "file_path": "transformers/tests/models/speecht5/test_modeling_speecht5.py", "repo_id": "transformers", "token_count": 35195 }
405
# coding=utf-8 # Copyright 2023 The HuggingFace Inc. 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless r...
transformers/tests/models/swiftformer/test_modeling_swiftformer.py/0
{ "file_path": "transformers/tests/models/swiftformer/test_modeling_swiftformer.py", "repo_id": "transformers", "token_count": 4796 }
406
# coding=utf-8 # Copyright 2023 HuggingFace Inc. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or ag...
transformers/tests/models/tvlt/test_image_processor_tvlt.py/0
{ "file_path": "transformers/tests/models/tvlt/test_image_processor_tvlt.py", "repo_id": "transformers", "token_count": 5010 }
407
# coding=utf-8 # Copyright 2022 The HuggingFace Inc. 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless r...
transformers/tests/models/vit_mae/test_modeling_tf_vit_mae.py/0
{ "file_path": "transformers/tests/models/vit_mae/test_modeling_tf_vit_mae.py", "repo_id": "transformers", "token_count": 7979 }
408
# coding=utf-8 # Copyright 2021 HuggingFace Inc. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or ag...
transformers/tests/models/wav2vec2/test_feature_extraction_wav2vec2.py/0
{ "file_path": "transformers/tests/models/wav2vec2/test_feature_extraction_wav2vec2.py", "repo_id": "transformers", "token_count": 4411 }
409
# coding=utf-8 # Copyright 2021 The HuggingFace Inc. 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless r...
transformers/tests/models/wavlm/test_modeling_wavlm.py/0
{ "file_path": "transformers/tests/models/wavlm/test_modeling_wavlm.py", "repo_id": "transformers", "token_count": 10880 }
410
# coding=utf-8 # Copyright 2020 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless requir...
transformers/tests/models/xlm/test_modeling_tf_xlm.py/0
{ "file_path": "transformers/tests/models/xlm/test_modeling_tf_xlm.py", "repo_id": "transformers", "token_count": 6451 }
411
# Copyright 2020 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicabl...
transformers/tests/pipelines/test_pipelines_text_classification.py/0
{ "file_path": "transformers/tests/pipelines/test_pipelines_text_classification.py", "repo_id": "transformers", "token_count": 3566 }
412
import json import logging import os import subprocess from argparse import ArgumentParser logger = logging.getLogger(__name__) def parse_args(): parser = ArgumentParser() parsed, unknown = parser.parse_known_args() for arg in unknown: if arg.startswith(("-", "--")): parser.add_argum...
transformers/tests/sagemaker/scripts/pytorch/run_ddp.py/0
{ "file_path": "transformers/tests/sagemaker/scripts/pytorch/run_ddp.py", "repo_id": "transformers", "token_count": 694 }
413
# coding=utf-8 # Copyright 2022 HuggingFace Inc. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or ag...
transformers/tests/test_image_transforms.py/0
{ "file_path": "transformers/tests/test_image_transforms.py", "repo_id": "transformers", "token_count": 12379 }
414
# coding=utf-8 # Copyright 2023 HuggingFace Inc. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or ag...
transformers/tests/tools/test_agent_types.py/0
{ "file_path": "transformers/tests/tools/test_agent_types.py", "repo_id": "transformers", "token_count": 1583 }
415
# Copyright 2020 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicabl...
transformers/tests/trainer/test_trainer_callback.py/0
{ "file_path": "transformers/tests/trainer/test_trainer_callback.py", "repo_id": "transformers", "token_count": 4143 }
416
# coding=utf-8 # Copyright 2019-present, the HuggingFace Inc. team. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by a...
transformers/tests/utils/test_generic.py/0
{ "file_path": "transformers/tests/utils/test_generic.py", "repo_id": "transformers", "token_count": 3485 }
417
# coding=utf-8 # Copyright 2022 The HuggingFace Inc. team. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable...
transformers/utils/check_config_docstrings.py/0
{ "file_path": "transformers/utils/check_config_docstrings.py", "repo_id": "transformers", "token_count": 1293 }
418
""" Script for downloading all GLUE data. Original source: https://gist.github.com/W4ngatang/60c2bdb54d156a41194446737ce03e2e Note: for legal reasons, we are unable to host MRPC. You can either use the version hosted by the SentEval team, which is already tokenized, or you can download the original data from (https://...
transformers/utils/download_glue_data.py/0
{ "file_path": "transformers/utils/download_glue_data.py", "repo_id": "transformers", "token_count": 3917 }
419
# pip install openrlbenchmark==0.2.1a5 # see https://github.com/openrlbenchmark/openrlbenchmark#get-started for documentation BASELINE_PR_TAG=v0.4.7-55-g110e672 BASELINE_PR_NAME=PR-662 python -m openrlbenchmark.rlops_multi_metrics \ --filters '?we=huggingface&wpn=trl&xaxis=_step&ceik=trl_ppo_trainer_config.value.r...
trl/benchmark/plot.sh/0
{ "file_path": "trl/benchmark/plot.sh", "repo_id": "trl", "token_count": 1454 }
420
# DPO Trainer TRL supports the DPO Trainer for training language models from preference data, as described in the paper [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://arxiv.org/abs/2305.18290) by Rafailov et al., 2023. For a full example have a look at [`examples/scripts/dpo....
trl/docs/source/dpo_trainer.mdx/0
{ "file_path": "trl/docs/source/dpo_trainer.mdx", "repo_id": "trl", "token_count": 3902 }
421
# Supervised Fine-tuning Trainer Supervised fine-tuning (or SFT for short) is a crucial step in RLHF. In TRL we provide an easy-to-use API to create your SFT models and train them with few lines of code on your dataset. Check out a complete flexible example at [`examples/scripts/sft.py`](https://github.com/huggingfac...
trl/docs/source/sft_trainer.mdx/0
{ "file_path": "trl/docs/source/sft_trainer.mdx", "repo_id": "trl", "token_count": 8707 }
422
# Copyright 2023 The HuggingFace Inc. 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by appl...
trl/examples/research_projects/tools/triviaqa.py/0
{ "file_path": "trl/examples/research_projects/tools/triviaqa.py", "repo_id": "trl", "token_count": 2555 }
423
# 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicabl...
trl/scripts/log_reports.py/0
{ "file_path": "trl/scripts/log_reports.py", "repo_id": "trl", "token_count": 2727 }
424
import subprocess def test_hello_world(): subprocess.run( "python examples/hello_world.py", shell=True, check=True, )
trl/tests/test_e2e.py/0
{ "file_path": "trl/tests/test_e2e.py", "repo_id": "trl", "token_count": 69 }
425
# Copyright 2022 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicabl...
trl/trl/core.py/0
{ "file_path": "trl/trl/core.py", "repo_id": "trl", "token_count": 5038 }
426
# Copyright 2023 DDPO-pytorch authors (Kevin Black), metric-space, 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. # You may obtain a copy of the License at # # http://www.apache.org/lic...
trl/trl/trainer/ddpo_trainer.py/0
{ "file_path": "trl/trl/trainer/ddpo_trainer.py", "repo_id": "trl", "token_count": 12350 }
427
<!--- 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. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or ...
accelerate/docker/README.md/0
{ "file_path": "accelerate/docker/README.md", "repo_id": "accelerate", "token_count": 796 }
0
<!--Copyright 2022 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. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed...
accelerate/docs/source/concept_guides/gradient_synchronization.md/0
{ "file_path": "accelerate/docs/source/concept_guides/gradient_synchronization.md", "repo_id": "accelerate", "token_count": 2842 }
1
<!--Copyright 2023 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. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed...
accelerate/docs/source/usage_guides/low_precision_training.md/0
{ "file_path": "accelerate/docs/source/usage_guides/low_precision_training.md", "repo_id": "accelerate", "token_count": 1463 }
2
# Copyright 2021 The HuggingFace Inc. 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by appl...
accelerate/examples/by_feature/gradient_accumulation.py/0
{ "file_path": "accelerate/examples/by_feature/gradient_accumulation.py", "repo_id": "accelerate", "token_count": 3352 }
3
#!/usr/bin/env python # Copyright 2021 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unles...
accelerate/src/accelerate/commands/launch.py/0
{ "file_path": "accelerate/src/accelerate/commands/launch.py", "repo_id": "accelerate", "token_count": 17932 }
4
#!/usr/bin/env python # Copyright 2023 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unles...
accelerate/src/accelerate/test_utils/scripts/test_ops.py/0
{ "file_path": "accelerate/src/accelerate/test_utils/scripts/test_ops.py", "repo_id": "accelerate", "token_count": 2347 }
5
# Copyright 2022 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicabl...
accelerate/src/accelerate/utils/memory.py/0
{ "file_path": "accelerate/src/accelerate/utils/memory.py", "repo_id": "accelerate", "token_count": 2210 }
6
# Copyright 2022 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicabl...
accelerate/tests/test_big_modeling.py/0
{ "file_path": "accelerate/tests/test_big_modeling.py", "repo_id": "accelerate", "token_count": 19558 }
7
# Copyright 2022 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicabl...
accelerate/tests/test_modeling_utils.py/0
{ "file_path": "accelerate/tests/test_modeling_utils.py", "repo_id": "accelerate", "token_count": 14449 }
8
# Copyright 2022 The HuggingFace Team, the AllenNLP library authors. 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # ...
accelerate/utils/stale.py/0
{ "file_path": "accelerate/utils/stale.py", "repo_id": "accelerate", "token_count": 1013 }
9
# Model arguments model_name_or_path: BramVanroy/gpt2-cpt-dutch model_revision: main torch_dtype: bfloat16 # Data training arguments chat_template: "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|syst...
alignment-handbook/recipes/gpt2-nl/sft/config_full.yaml/0
{ "file_path": "alignment-handbook/recipes/gpt2-nl/sft/config_full.yaml", "repo_id": "alignment-handbook", "token_count": 553 }
10
# Model arguments model_name_or_path: google/gemma-7b model_revision: main tokenizer_name_or_path: philschmid/gemma-tokenizer-chatml # Custom tokenizer with <|im_start|> and <|im_end|> tokens torch_dtype: bfloat16 use_flash_attention_2: true # Data training arguments dataset_mixer: HuggingFaceH4/deita-10k-v0-sft: 1....
alignment-handbook/recipes/zephyr-7b-gemma/sft/config_full.yaml/0
{ "file_path": "alignment-handbook/recipes/zephyr-7b-gemma/sft/config_full.yaml", "repo_id": "alignment-handbook", "token_count": 480 }
11
# Copyright 2023 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. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicabl...
alignment-handbook/tests/test_configs.py/0
{ "file_path": "alignment-handbook/tests/test_configs.py", "repo_id": "alignment-handbook", "token_count": 697 }
12
# Hello world! We will now create the hello world of the ML world, building a model capable of solving MNIST dataset. Open `src/main.rs` and fill in this content: ```rust # extern crate candle_core; use candle_core::{Device, Result, Tensor}; struct Model { first: Tensor, second: Tensor, } impl Model { ...
candle/candle-book/src/guide/hello_world.md/0
{ "file_path": "candle/candle-book/src/guide/hello_world.md", "repo_id": "candle", "token_count": 2069 }
13
# candle Minimalist ML framework for Rust
candle/candle-core/README.md/0
{ "file_path": "candle/candle-core/README.md", "repo_id": "candle", "token_count": 11 }
14
use super::{Cpu, CpuF16}; #[cfg(target_arch = "x86")] use core::arch::x86::*; #[cfg(target_arch = "x86_64")] use core::arch::x86_64::*; use half::f16; pub struct CurrentCpu {} const STEP: usize = 32; const EPR: usize = 8; const ARR: usize = STEP / EPR; impl Cpu<ARR> for CurrentCpu { type Unit = __m256; type...
candle/candle-core/src/cpu/avx.rs/0
{ "file_path": "candle/candle-core/src/cpu/avx.rs", "repo_id": "candle", "token_count": 2094 }
15
use crate::{Error, Result, Shape}; #[derive(Debug, PartialEq, Eq, Clone)] pub struct Layout { shape: Shape, // The strides are given in number of elements and not in bytes. stride: Vec<usize>, start_offset: usize, } impl Layout { pub fn new(shape: Shape, stride: Vec<usize>, start_offset: usize) ->...
candle/candle-core/src/layout.rs/0
{ "file_path": "candle/candle-core/src/layout.rs", "repo_id": "candle", "token_count": 4349 }
16
use super::k_quants::{ BlockQ2K, BlockQ3K, BlockQ4K, BlockQ4_0, BlockQ5K, BlockQ6K, BlockQ8K, BlockQ8_0, QK8_0, QK_K, }; use crate::Result; use byteorder::{ByteOrder, LittleEndian}; #[allow(unused_imports)] #[cfg(target_arch = "arm")] use core::arch::arm::*; #[allow(unused_imports)] #[cfg(target_arch = "aarch64")...
candle/candle-core/src/quantized/neon.rs/0
{ "file_path": "candle/candle-core/src/quantized/neon.rs", "repo_id": "candle", "token_count": 15290 }
17
# candle-datasets
candle/candle-datasets/README.md/0
{ "file_path": "candle/candle-datasets/README.md", "repo_id": "candle", "token_count": 7 }
18
# candle-blip The [blip-image-captioning](https://huggingface.co/Salesforce/blip-image-captioning-base) model can generate captions for an input image. ## Running on an example ```bash cargo run --example blip --release -- --image candle-examples/examples/yolo-v8/assets/bike.jpg ``` ``` Running on CPU, to run on GP...
candle/candle-examples/examples/blip/README.md/0
{ "file_path": "candle/candle-examples/examples/blip/README.md", "repo_id": "candle", "token_count": 190 }
19
#[cfg(feature = "mkl")] extern crate intel_mkl_src; #[cfg(feature = "accelerate")] extern crate accelerate_src; use clap::{Parser, ValueEnum}; use candle::{DType, IndexOp, D}; use candle_nn::{Module, VarBuilder}; use candle_transformers::models::efficientvit; #[derive(Clone, Copy, Debug, ValueEnum)] enum Which { ...
candle/candle-examples/examples/efficientvit/main.rs/0
{ "file_path": "candle/candle-examples/examples/efficientvit/main.rs", "repo_id": "candle", "token_count": 1278 }
20
# candle-mamba-minimal: minimal implementation of Mamba This is based on [mamba-minimal](https://github.com/johnma2006/mamba-minimal). Compared to the mamba example, this version can handle training but is much slower. ## Running the example ```bash $ cargo run --example mamba-minimal --release -- --prompt "Mamba i...
candle/candle-examples/examples/mamba-minimal/README.md/0
{ "file_path": "candle/candle-examples/examples/mamba-minimal/README.md", "repo_id": "candle", "token_count": 206 }
21
#[cfg(feature = "mkl")] extern crate intel_mkl_src; #[cfg(feature = "accelerate")] extern crate accelerate_src; use clap::{Parser, ValueEnum}; use candle::{DType, IndexOp, D}; use candle_nn::{Module, VarBuilder}; use candle_transformers::models::mobileone; #[derive(Clone, Copy, Debug, ValueEnum)] enum Which { S...
candle/candle-examples/examples/mobileone/main.rs/0
{ "file_path": "candle/candle-examples/examples/mobileone/main.rs", "repo_id": "candle", "token_count": 1213 }
22
use std::collections::VecDeque; use std::fmt::Display; use candle::{DType, Device, Error, Module, Result, Tensor, Var}; use candle_nn::{ func, linear, sequential::seq, Activation, AdamW, Optimizer, ParamsAdamW, Sequential, VarBuilder, VarMap, }; use rand::{distributions::Uniform, thread_rng, Rng}; use super::...
candle/candle-examples/examples/reinforcement-learning/ddpg.rs/0
{ "file_path": "candle/candle-examples/examples/reinforcement-learning/ddpg.rs", "repo_id": "candle", "token_count": 8524 }
23
[ { "index": 1, "color": "#787878", "label": "wall" }, { "index": 2, "color": "#B47878", "label": "building;edifice" }, { "index": 3, "color": "#06E6E6", "label": "sky" }, { "index": 4, "color": "#503232", "label": "floor;flooring" }, { "index": 5, ...
candle/candle-examples/examples/segformer/assets/labels.json/0
{ "file_path": "candle/candle-examples/examples/segformer/assets/labels.json", "repo_id": "candle", "token_count": 6397 }
24
use symphonia::core::audio::{AudioBufferRef, Signal}; use symphonia::core::codecs::{DecoderOptions, CODEC_TYPE_NULL}; use symphonia::core::conv::FromSample; fn conv<T>(samples: &mut Vec<f32>, data: std::borrow::Cow<symphonia::core::audio::AudioBuffer<T>>) where T: symphonia::core::sample::Sample, f32: symphoni...
candle/candle-examples/examples/whisper/pcm_decode.rs/0
{ "file_path": "candle/candle-examples/examples/whisper/pcm_decode.rs", "repo_id": "candle", "token_count": 1267 }
25
use candle::{Result, Tensor}; // https://github.com/facebookresearch/audiocraft/blob/69fea8b290ad1b4b40d28f92d1dfc0ab01dbab85/audiocraft/data/audio_utils.py#L57 pub fn normalize_loudness( wav: &Tensor, sample_rate: u32, loudness_compressor: bool, ) -> Result<Tensor> { let energy = wav.sqr()?.mean_all()...
candle/candle-examples/src/audio.rs/0
{ "file_path": "candle/candle-examples/src/audio.rs", "repo_id": "candle", "token_count": 458 }
26
/****************************************************************************** * Copyright (c) 2023, Tri Dao. ******************************************************************************/ #pragma once #include "cute/algorithm/copy.hpp" #include "cutlass/cutlass.h" #include "cutlass/layout/layout.h" #include <cu...
candle/candle-flash-attn/kernels/kernel_traits.h/0
{ "file_path": "candle/candle-flash-attn/kernels/kernel_traits.h", "repo_id": "candle", "token_count": 9290 }
27
#include "cuda_fp16.h" #include "cuda_bf16.h" // Table showing which features are supported on which compute capability // https://docs.nvidia.com/cuda/cuda-c-programming-guide/#features-and-technical-specifications // FIXME: the minimum compute capabilities are just guesses since the table is not specific enough #i...
candle/candle-kernels/src/compatibility.cuh/0
{ "file_path": "candle/candle-kernels/src/compatibility.cuh", "repo_id": "candle", "token_count": 2734 }
28
#include <metal_stdlib> using namespace metal; template<typename TYPENAME, typename INDEX_TYPENAME> METAL_FUNC void index( constant size_t &dst_size, constant size_t &left_size, constant size_t &src_dim_size, constant size_t &right_size, constant size_t &ids_size, const device TYPENAME *i...
candle/candle-metal-kernels/src/indexing.metal/0
{ "file_path": "candle/candle-metal-kernels/src/indexing.metal", "repo_id": "candle", "token_count": 3485 }
29
/// This example contains some simple benchmarks so that it's easy to run them in perf etc. #[cfg(feature = "mkl")] extern crate intel_mkl_src; #[cfg(feature = "accelerate")] extern crate accelerate_src; use candle::quantized::GgmlType; use candle::{CpuStorage, Device, Layout, Module, Result, Shape, Tensor, D}; use c...
candle/candle-nn/examples/cpu_benchmarks.rs/0
{ "file_path": "candle/candle-nn/examples/cpu_benchmarks.rs", "repo_id": "candle", "token_count": 5543 }
30
//! A sequential layer used to chain multiple layers and closures. use candle::{Module, Result, Tensor}; /// A sequential layer combining multiple other layers. pub struct Sequential { layers: Vec<Box<dyn Module>>, } /// Creates a new empty sequential layer. pub fn seq() -> Sequential { Sequential { layers: v...
candle/candle-nn/src/sequential.rs/0
{ "file_path": "candle/candle-nn/src/sequential.rs", "repo_id": "candle", "token_count": 705 }
31
// // WARNING: This file is automatically generated! Please edit onnx.in.proto. // // SPDX-License-Identifier: Apache-2.0 syntax = "proto3"; package onnx; // Overview // // ONNX is an open specification that is comprised of the following components: // // 1) A definition of an extensible computation graph model...
candle/candle-onnx/src/onnx.proto3/0
{ "file_path": "candle/candle-onnx/src/onnx.proto3", "repo_id": "candle", "token_count": 10183 }
32
# see https://github.com/pytorch/pytorch/blob/main/torch/nn/modules/container.py from .module import Module from typing import ( Any, Dict, Iterable, Iterator, Mapping, Optional, overload, Tuple, TypeVar, Union, ) from collections import OrderedDict, abc as container_abcs import ...
candle/candle-pyo3/py_src/candle/nn/container.py/0
{ "file_path": "candle/candle-pyo3/py_src/candle/nn/container.py", "repo_id": "candle", "token_count": 7602 }
33
use pyo3::exceptions::PyValueError; use pyo3::prelude::*; pub fn wrap_err(err: ::candle::Error) -> PyErr { PyErr::new::<PyValueError, _>(format!("{err:?}")) }
candle/candle-pyo3/src/utils.rs/0
{ "file_path": "candle/candle-pyo3/src/utils.rs", "repo_id": "candle", "token_count": 74 }
34
use candle::{DType, Device, IndexOp, Result, Tensor, D}; use candle_nn::{embedding, linear_b as linear, Embedding, LayerNorm, Linear, Module, VarBuilder}; fn layer_norm(size: usize, eps: f64, vb: VarBuilder) -> Result<LayerNorm> { let weight = vb.get(size, "weight")?; let bias = vb.get(size, "bias")?; Ok(L...
candle/candle-transformers/src/models/bigcode.rs/0
{ "file_path": "candle/candle-transformers/src/models/bigcode.rs", "repo_id": "candle", "token_count": 6280 }
35
use byteorder::{LittleEndian, ReadBytesExt}; use candle::{DType, Device, IndexOp, Result, Shape, Tensor}; use candle_nn::VarBuilder; use super::llama2_c::Config; pub struct TransformerWeights { // token embedding table token_embedding_table: Tensor, // (vocab_size, dim) // weights for rmsnorms rms_att...
candle/candle-transformers/src/models/llama2_c_weights.rs/0
{ "file_path": "candle/candle-transformers/src/models/llama2_c_weights.rs", "repo_id": "candle", "token_count": 3322 }
36
use crate::quantized_nn::{linear_b, Embedding, Linear, RmsNorm}; pub use crate::quantized_var_builder::VarBuilder; use crate::models::metavoice::repeat_interleave; use candle::{Module, Result, Tensor, D}; pub mod transformer { use super::*; type Config = crate::models::metavoice::transformer::Config; #[...
candle/candle-transformers/src/models/quantized_metavoice.rs/0
{ "file_path": "candle/candle-transformers/src/models/quantized_metavoice.rs", "repo_id": "candle", "token_count": 5029 }
37
pub use crate::models::with_tracing::Linear; use candle::{Result, Tensor}; use candle_nn::{Module, VarBuilder}; pub mod image_encoder; pub mod mask_decoder; pub mod prompt_encoder; pub mod sam; pub mod tiny_vit; pub mod transformer; pub fn linear(vb: VarBuilder, in_dim: usize, out_dim: usize, bias: bool) -> Result<Li...
candle/candle-transformers/src/models/segment_anything/mod.rs/0
{ "file_path": "candle/candle-transformers/src/models/segment_anything/mod.rs", "repo_id": "candle", "token_count": 1119 }
38
use candle::{Device, Result, Tensor}; pub fn linspace(start: f64, stop: f64, steps: usize) -> Result<Tensor> { if steps == 0 { Tensor::from_vec(Vec::<f64>::new(), steps, &Device::Cpu) } else if steps == 1 { Tensor::from_vec(vec![start], steps, &Device::Cpu) } else { let delta = (sto...
candle/candle-transformers/src/models/stable_diffusion/utils.rs/0
{ "file_path": "candle/candle-transformers/src/models/stable_diffusion/utils.rs", "repo_id": "candle", "token_count": 979 }
39
use super::common::{AttnBlock, GlobalResponseNorm, LayerNormNoWeights, TimestepBlock, WLayerNorm}; use candle::{DType, Module, Result, Tensor, D}; use candle_nn::VarBuilder; #[derive(Debug)] pub struct ResBlockStageB { depthwise: candle_nn::Conv2d, norm: WLayerNorm, channelwise_lin1: candle_nn::Linear, ...
candle/candle-transformers/src/models/wuerstchen/diffnext.rs/0
{ "file_path": "candle/candle-transformers/src/models/wuerstchen/diffnext.rs", "repo_id": "candle", "token_count": 8148 }
40
<html> <head> <meta content="text/html;charset=utf-8" http-equiv="Content-Type" /> <title>Candle Bert</title> </head> <body></body> </html> <!DOCTYPE html> <html> <head> <meta charset="UTF-8" /> <meta name="viewport" content="width=device-width, initial-scale=1.0" /> <style> @import u...
candle/candle-wasm-examples/bert/lib-example.html/0
{ "file_path": "candle/candle-wasm-examples/bert/lib-example.html", "repo_id": "candle", "token_count": 6066 }
41
<html> <head> <meta content="text/html;charset=utf-8" http-equiv="Content-Type" /> <title>Candle Llama.c Rust/WASM</title> </head> <body></body> </html> <!DOCTYPE html> <html> <head> <meta charset="UTF-8" /> <meta name="viewport" content="width=device-width, initial-scale=1.0" /> <style> ...
candle/candle-wasm-examples/llama2-c/lib-example.html/0
{ "file_path": "candle/candle-wasm-examples/llama2-c/lib-example.html", "repo_id": "candle", "token_count": 6089 }
42
[package] name = "candle-wasm-example-sam" version.workspace = true edition.workspace = true description.workspace = true repository.workspace = true keywords.workspace = true categories.workspace = true license.workspace = true [dependencies] candle = { workspace = true } candle-nn = { workspace = true } candle-trans...
candle/candle-wasm-examples/segment-anything/Cargo.toml/0
{ "file_path": "candle/candle-wasm-examples/segment-anything/Cargo.toml", "repo_id": "candle", "token_count": 264 }
43
export async function extractEmbeddings( worker, weightsURL, tokenizerURL, configURL, modelID, sentences, updateStatus, normalize_embeddings = true ) { return new Promise((resolve, reject) => { worker.postMessage({ weightsURL, tokenizerURL, configURL, modelID, sentenc...
candle/candle-wasm-examples/t5/utils.js/0
{ "file_path": "candle/candle-wasm-examples/t5/utils.js", "repo_id": "candle", "token_count": 2339 }
44
[package] name = "candle-wasm-example-yolo" version.workspace = true edition.workspace = true description.workspace = true repository.workspace = true keywords.workspace = true categories.workspace = true license.workspace = true [dependencies] candle = { workspace = true } candle-nn = { workspace = true } num-traits ...
candle/candle-wasm-examples/yolo/Cargo.toml/0
{ "file_path": "candle/candle-wasm-examples/yolo/Cargo.toml", "repo_id": "candle", "token_count": 463 }
45
pub fn add(left: usize, right: usize) -> usize { left + right } #[cfg(test)] mod tests { use super::*; #[test] fn it_works() { let result = add(2, 2); assert_eq!(result, 4); } }
candle/candle-wasm-tests/src/lib.rs/0
{ "file_path": "candle/candle-wasm-tests/src/lib.rs", "repo_id": "candle", "token_count": 108 }
46
## Privacy > Last updated: October 4, 2023 Users of HuggingChat are authenticated through their HF user account. By default, your conversations may be shared with the respective models' authors to improve their training data and model over time. Model authors are the custodians of the data collected by their model, ...
chat-ui/PRIVACY.md/0
{ "file_path": "chat-ui/PRIVACY.md", "repo_id": "chat-ui", "token_count": 762 }
47
import type { EndpointParameters } from "./server/endpoints/endpoints"; import type { BackendModel } from "./server/models"; type buildPromptOptions = Pick<EndpointParameters, "messages" | "preprompt" | "continueMessage"> & { model: BackendModel; }; export async function buildPrompt({ messages, model, preprompt, ...
chat-ui/src/lib/buildPrompt.ts/0
{ "file_path": "chat-ui/src/lib/buildPrompt.ts", "repo_id": "chat-ui", "token_count": 327 }
48
<script lang="ts"> import CarbonCaretLeft from "~icons/carbon/caret-left"; import CarbonCaretRight from "~icons/carbon/caret-right"; export let href: string; export let direction: "next" | "previous"; export let isDisabled = false; </script> <a class="flex items-center rounded-lg px-2.5 py-1 hover:bg-gray-50 da...
chat-ui/src/lib/components/PaginationArrow.svelte/0
{ "file_path": "chat-ui/src/lib/components/PaginationArrow.svelte", "repo_id": "chat-ui", "token_count": 226 }
49
<script lang="ts"> import { onDestroy } from "svelte"; import CarbonImage from "~icons/carbon/image"; // import EosIconsLoading from "~icons/eos-icons/loading"; export let files: File[]; let file_error_message = ""; let errorTimeout: ReturnType<typeof setTimeout>; export let onDrag = false; async function d...
chat-ui/src/lib/components/chat/FileDropzone.svelte/0
{ "file_path": "chat-ui/src/lib/components/chat/FileDropzone.svelte", "repo_id": "chat-ui", "token_count": 1232 }
50
import { Issuer, BaseClient, type UserinfoResponse, TokenSet, custom } from "openid-client"; import { addHours, addWeeks } from "date-fns"; import { COOKIE_NAME, OPENID_CLIENT_ID, OPENID_CLIENT_SECRET, OPENID_PROVIDER_URL, OPENID_SCOPES, OPENID_TOLERANCE, OPENID_RESOURCE, OPENID_CONFIG, } from "$env/static/priv...
chat-ui/src/lib/server/auth.ts/0
{ "file_path": "chat-ui/src/lib/server/auth.ts", "repo_id": "chat-ui", "token_count": 1500 }
51
import { error } from "@sveltejs/kit"; import { collections } from "../database"; import type { Conversation } from "$lib/types/Conversation"; import type { SharedConversation } from "$lib/types/SharedConversation"; export async function downloadFile( sha256: string, convId: Conversation["_id"] | SharedConversation[...
chat-ui/src/lib/server/files/downloadFile.ts/0
{ "file_path": "chat-ui/src/lib/server/files/downloadFile.ts", "repo_id": "chat-ui", "token_count": 383 }
52
import { base } from "$app/paths"; import { ERROR_MESSAGES, error } from "$lib/stores/errors"; import { share } from "./utils/share"; import { page } from "$app/stores"; import { get } from "svelte/store"; import { getShareUrl } from "./utils/getShareUrl"; export async function shareConversation(id: string, title: stri...
chat-ui/src/lib/shareConversation.ts/0
{ "file_path": "chat-ui/src/lib/shareConversation.ts", "repo_id": "chat-ui", "token_count": 359 }
53
import type { WebSearchSource } from "./WebSearch"; export type FinalAnswer = { type: "finalAnswer"; text: string; }; export type TextStreamUpdate = { type: "stream"; token: string; }; export type AgentUpdate = { type: "agent"; agent: string; content: string; binary?: Blob; }; export type WebSearchUpdate = ...
chat-ui/src/lib/types/MessageUpdate.ts/0
{ "file_path": "chat-ui/src/lib/types/MessageUpdate.ts", "repo_id": "chat-ui", "token_count": 273 }
54
import { browser } from "$app/environment"; export function cookiesAreEnabled(): boolean { if (!browser) return false; if (navigator.cookieEnabled) return navigator.cookieEnabled; // Create cookie document.cookie = "cookietest=1"; const ret = document.cookie.indexOf("cookietest=") != -1; // Delete cookie docum...
chat-ui/src/lib/utils/cookiesAreEnabled.ts/0
{ "file_path": "chat-ui/src/lib/utils/cookiesAreEnabled.ts", "repo_id": "chat-ui", "token_count": 127 }
55
export async function share(url: string, title: string) { if (navigator.share) { navigator.share({ url, title }); } else { await navigator.clipboard.writeText(url); } }
chat-ui/src/lib/utils/share.ts/0
{ "file_path": "chat-ui/src/lib/utils/share.ts", "repo_id": "chat-ui", "token_count": 63 }
56
<script lang="ts"> import { page } from "$app/stores"; </script> <div class="flex items-center justify-center bg-gradient-to-t from-gray-200 text-gray-800 dark:from-gray-700 dark:text-gray-300" > <div class="align-center -mt-24 flex flex-col justify-center rounded-xl border bg-white px-8 pb-2 pt-4 text-center dar...
chat-ui/src/routes/+error.svelte/0
{ "file_path": "chat-ui/src/routes/+error.svelte", "repo_id": "chat-ui", "token_count": 241 }
57