SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

fix block mask typing (#36661)

Browse Source 
* fix block mask typing

* updated

Co-authored-by: Cyril Vallez <cyril.vallez@gmail.com>

* gemma

* fix

---------

Co-authored-by: Cyril Vallez <cyril.vallez@gmail.com>
This commit is contained in:
Arthur
2025-03-12 11:29:11 +01:00
committed by GitHub
parent 89f6956015
commit 2829013d2d
4 changed files with 76 additions and 75 deletions
Download Patch File Download Diff File Expand all files Collapse all files

139
docs/source/en/_toctree.yml
View File

@@ -1,16 +1,14 @@
- title: Get started
sections:
- sections:
- local: index
title: Transformers
- local: installation
title: Installation
- local: quicktour
title: Quickstart
- title: Base classes
isExpanded: False
title: Get started
- isExpanded: false
sections:
- title: Models
sections:
- sections:
- local: models
title: Loading models
- local: custom_models
@@ -31,8 +29,8 @@
title: The Transformer model family
- local: attention
title: Attention mechanisms
- title: Preprocessors
sections:
title: Models
- sections:
- local: fast_tokenizers
title: Tokenizers
- local: image_processors
@@ -47,11 +45,11 @@
title: Summary of the tokenizers
- local: pad_truncation
title: Padding and truncation
- title: Inference
isExpanded: False
title: Preprocessors
title: Base classes
- isExpanded: false
sections:
- title: Pipeline API
sections:
- sections:
- local: pipeline_tutorial
title: Pipeline
- local: pipeline_gradio
@@ -60,8 +58,8 @@
title: Web server inference
- local: add_new_pipeline
title: Adding a new pipeline
- title: LLMs
sections:
title: Pipeline API
- sections:
- local: llm_tutorial
title: Text generation
- local: generation_strategies
@@ -82,8 +80,8 @@
title: Getting the most out of LLMs
- local: perplexity
title: Perplexity of fixed-length models
- title: Chat with models
sections:
title: LLMs
- sections:
- local: conversations
title: Chat basics
- local: chat_templating
@@ -94,8 +92,8 @@
title: Template writing
- local: chat_extras
title: Tools and RAG
- title: Optimization
sections:
title: Chat with models
- sections:
- local: perf_torch_compile
title: torch.compile
- local: perf_infer_gpu_one
@@ -106,15 +104,15 @@
title: CPU
- local: tf_xla
title: XLA
title: Optimization
- local: agents
title: Agents
- local: tools
title: Tools
- title: Training
isExpanded: False
title: Inference
- isExpanded: false
sections:
- title: Trainer API
sections:
- sections:
- local: trainer
title: Trainer
- local: training
@@ -123,8 +121,8 @@
title: Optimizers
- local: hpo_train
title: Hyperparameter search
- title: Distributed training
sections:
title: Trainer API
- sections:
- local: gpu_selection
title: GPU selection
- local: accelerate
@@ -139,8 +137,8 @@
title: Distributed CPUs
- local: perf_train_gpu_many
title: Parallelism methods
- title: Hardware
sections:
title: Distributed training
- sections:
- local: perf_train_gpu_one
title: GPU
- local: perf_train_cpu
@@ -151,12 +149,13 @@
title: Apple Silicon
- local: perf_hardware
title: Build your own machine
title: Hardware
- local: peft
title: PEFT
- local: model_memory_anatomy
title: Model training anatomy
- title: Quantization
isExpanded: False
title: Training
- isExpanded: false
sections:
- local: quantization/overview
title: Overview
@@ -196,8 +195,8 @@
title: VPTQ
- local: quantization/contribute
title: Contribute
- title: Export to production
isExpanded: False
title: Quantization
- isExpanded: false
sections:
- local: serialization
title: ONNX
@@ -207,13 +206,11 @@
title: ExecuTorch
- local: torchscript
title: TorchScript
- title: Resources
isExpanded: False
title: Export to production
- isExpanded: false
sections:
- title: Task recipes
sections:
- title: Natural language processing
sections:
- sections:
- sections:
- local: tasks/sequence_classification
title: Text classification
- local: tasks/token_classification
@@ -230,14 +227,14 @@
title: Summarization
- local: tasks/multiple_choice
title: Multiple choice
- title: Audio
sections:
title: Natural language processing
- sections:
- local: tasks/audio_classification
title: Audio classification
- local: tasks/asr
title: Automatic speech recognition
- title: Computer vision
sections:
title: Audio
- sections:
- local: tasks/image_classification
title: Image classification
- local: tasks/semantic_segmentation
@@ -262,8 +259,8 @@
title: Keypoint detection
- local: tasks/knowledge_distillation_for_image_classification
title: Knowledge Distillation for Computer Vision
- title: Multimodal
sections:
title: Computer vision
- sections:
- local: tasks/image_captioning
title: Image captioning
- local: tasks/document_question_answering
@@ -278,6 +275,8 @@
title: Image-text-to-text
- local: tasks/video_text_to_text
title: Video-text-to-text
title: Multimodal
title: Task recipes
- local: run_scripts
title: Training scripts
- local: glossary
@@ -290,8 +289,8 @@
title: Community resources
- local: troubleshooting
title: Troubleshoot
- title: Contribute
isExpanded: False
title: Resources
- isExpanded: false
sections:
- local: contributing
title: Contribute to Transformers
@@ -299,11 +298,10 @@
title: Transformers model tests
- local: pr_checks
title: Pull request checks
- title: API
isExpanded: False
title: Contribute
- isExpanded: false
sections:
- title: Main classes
sections:
- sections:
- local: main_classes/agent
title: Agents and Tools
- local: model_doc/auto
@@ -350,10 +348,9 @@
title: Feature Extractor
- local: main_classes/image_processor
title: Image Processor
- title: Models
sections:
- title: Text models
sections:
title: Main classes
- sections:
- sections:
- local: model_doc/albert
title: ALBERT
- local: model_doc/bamba
@@ -662,8 +659,8 @@
title: Zamba
- local: model_doc/zamba2
title: Zamba2
- title: Vision models
sections:
title: Text models
- sections:
- local: model_doc/beit
title: BEiT
- local: model_doc/bit
@@ -790,8 +787,8 @@
title: YOLOS
- local: model_doc/zoedepth
title: ZoeDepth
- title: Audio models
sections:
title: Vision models
- sections:
- local: model_doc/audio-spectrogram-transformer
title: Audio Spectrogram Transformer
- local: model_doc/bark
@@ -860,16 +857,16 @@
title: XLS-R
- local: model_doc/xlsr_wav2vec2
title: XLSR-Wav2Vec2
- title: Video models
sections:
title: Audio models
- sections:
- local: model_doc/timesformer
title: TimeSformer
- local: model_doc/videomae
title: VideoMAE
- local: model_doc/vivit
title: ViViT
- title: Multimodal models
sections:
title: Video models
- sections:
- local: model_doc/align
title: ALIGN
- local: model_doc/altclip
@@ -908,6 +905,8 @@
title: Emu3
- local: model_doc/flava
title: FLAVA
- local: model_doc/gemma3
title: Gemma3
- local: model_doc/git
title: GIT
- local: model_doc/got_ocr2
@@ -1012,14 +1011,14 @@
title: VisualBERT
- local: model_doc/xclip
title: X-CLIP
- title: Reinforcement learning models
sections:
title: Multimodal models
- sections:
- local: model_doc/decision_transformer
title: Decision Transformer
- local: model_doc/trajectory_transformer
title: Trajectory Transformer
- title: Time series models
sections:
title: Reinforcement learning models
- sections:
- local: model_doc/autoformer
title: Autoformer
- local: model_doc/informer
@@ -1030,12 +1029,13 @@
title: PatchTST
- local: model_doc/time_series_transformer
title: Time Series Transformer
- title: Graph models
sections:
title: Time series models
- sections:
- local: model_doc/graphormer
title: Graphormer
- title: Internal helpers
sections:
title: Graph models
title: Models
- sections:
- local: internal/modeling_utils
title: Custom Layers and Utilities
- local: internal/pipelines_utils
@@ -1054,4 +1054,5 @@
title: General Utilities
- local: internal/time_series_utils
title: Utilities for Time Series
title: Internal helpers
title: API