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

Fix broken links (#39809)

Browse Source 
Replace links in the form of `[text]((url))` to `[text](url)`. This is
the correct format of a url in the markdown.
This commit is contained in:
Tommy Chiang
2025-07-31 21:23:04 +08:00
committed by GitHub
parent b937d47455
commit 4fcf455517
10 changed files with 11 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/en/llm_tutorial_optimization.md
View File

@@ -27,7 +27,7 @@ In this guide, we will go over the effective techniques for efficient LLM deploy
2. **Flash Attention:** Flash Attention is a variation of the attention algorithm that not only provides a more memory-efficient approach but also realizes increased efficiency due to optimized GPU memory utilization.
3. **Architectural Innovations:** Considering that LLMs are always deployed in the same way during inference, namely autoregressive text generation with a long input context, specialized model architectures have been proposed that allow for more efficient inference. The most important advancement in model architectures hereby are [Alibi](https://huggingface.co/papers/2108.12409), [Rotary embeddings](https://huggingface.co/papers/2104.09864), [Multi-Query Attention (MQA)](https://huggingface.co/papers/1911.02150) and [Grouped-Query-Attention (GQA)]((https://huggingface.co/papers/2305.13245)).
3. **Architectural Innovations:** Considering that LLMs are always deployed in the same way during inference, namely autoregressive text generation with a long input context, specialized model architectures have been proposed that allow for more efficient inference. The most important advancement in model architectures hereby are [Alibi](https://huggingface.co/papers/2108.12409), [Rotary embeddings](https://huggingface.co/papers/2104.09864), [Multi-Query Attention (MQA)](https://huggingface.co/papers/1911.02150) and [Grouped-Query-Attention (GQA)](https://huggingface.co/papers/2305.13245).
Throughout this guide, we will offer an analysis of auto-regressive generation from a tensor's perspective. We delve into the pros and cons of adopting lower precision, provide a comprehensive exploration of the latest attention algorithms, and discuss improved LLM architectures. While doing so, we run practical examples showcasing each of the feature improvements.

2
docs/source/en/model_doc/mgp-str.md
View File

@@ -33,7 +33,7 @@ alt="drawing" width="600"/>
<small> MGP-STR architecture. Taken from the <a href="https://huggingface.co/papers/2209.03592">original paper</a>. </small>
MGP-STR is trained on two synthetic datasets [MJSynth]((http://www.robots.ox.ac.uk/~vgg/data/text/)) (MJ) and [SynthText](http://www.robots.ox.ac.uk/~vgg/data/scenetext/) (ST) without fine-tuning on other datasets. It achieves state-of-the-art results on six standard Latin scene text benchmarks, including 3 regular text datasets (IC13, SVT, IIIT) and 3 irregular ones (IC15, SVTP, CUTE).
MGP-STR is trained on two synthetic datasets [MJSynth](http://www.robots.ox.ac.uk/~vgg/data/text/) (MJ) and [SynthText](http://www.robots.ox.ac.uk/~vgg/data/scenetext/) (ST) without fine-tuning on other datasets. It achieves state-of-the-art results on six standard Latin scene text benchmarks, including 3 regular text datasets (IC13, SVT, IIIT) and 3 irregular ones (IC15, SVTP, CUTE).
This model was contributed by [yuekun](https://huggingface.co/yuekun). The original code can be found [here](https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/OCR/MGP-STR).
## Inference example

2
docs/source/en/model_doc/qwen2_moe.md
View File

@@ -24,7 +24,7 @@ rendered properly in your Markdown viewer.
# Qwen2MoE
[Qwen2MoE]((https://huggingface.co/papers/2407.10671) ) is a Mixture-of-Experts (MoE) variant of [Qwen2](./qwen2), available as a base model and an aligned chat model. It uses SwiGLU activation, group query attention and a mixture of sliding window attention and full attention. The tokenizer can also be adapted to multiple languages and codes.
[Qwen2MoE](https://huggingface.co/papers/2407.10671) is a Mixture-of-Experts (MoE) variant of [Qwen2](./qwen2), available as a base model and an aligned chat model. It uses SwiGLU activation, group query attention and a mixture of sliding window attention and full attention. The tokenizer can also be adapted to multiple languages and codes.
The MoE architecture uses upcyled models from the dense language models. For example, Qwen1.5-MoE-A2.7B is upcycled from Qwen-1.8B. It has 14.3B parameters but only 2.7B parameters are activated during runtime.

2
docs/source/en/quantization/spqr.md
View File

@@ -16,7 +16,7 @@ rendered properly in your Markdown viewer.
# SpQR
The [SpQR]((https://hf.co/papers/2306.03078)) quantization algorithm involves a 16x16 tiled bi-level group 3-bit quantization structure with sparse outliers.
The [SpQR](https://hf.co/papers/2306.03078) quantization algorithm involves a 16x16 tiled bi-level group 3-bit quantization structure with sparse outliers.
<div class="flex justify-center">
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/spqr-diagram.png">

2
docs/source/en/serialization.md
View File

@@ -18,7 +18,7 @@ rendered properly in your Markdown viewer.
[ONNX](http://onnx.ai) is an open standard that defines a common set of operators and a file format to represent deep learning models in different frameworks, including PyTorch and TensorFlow. When a model is exported to ONNX, the operators construct a computational graph (or *intermediate representation*) which represents the flow of data through the model. Standardized operators and data types makes it easy to switch between frameworks.
The [Optimum](https://huggingface.co/docs/optimum/index) library exports a model to ONNX with configuration objects which are supported for [many architectures]((https://huggingface.co/docs/optimum/exporters/onnx/overview)) and can be easily extended. If a model isn't supported, feel free to make a [contribution](https://huggingface.co/docs/optimum/exporters/onnx/usage_guides/contribute) to Optimum.
The [Optimum](https://huggingface.co/docs/optimum/index) library exports a model to ONNX with configuration objects which are supported for [many architectures](https://huggingface.co/docs/optimum/exporters/onnx/overview) and can be easily extended. If a model isn't supported, feel free to make a [contribution](https://huggingface.co/docs/optimum/exporters/onnx/usage_guides/contribute) to Optimum.
The benefits of exporting to ONNX include the following.

2
docs/source/en/tflite.md
View File

@@ -18,7 +18,7 @@ rendered properly in your Markdown viewer.
[LiteRT](https://ai.google.dev/edge/litert) (previously known as TensorFlow Lite) is a high-performance runtime designed for on-device machine learning.
The [Optimum](https://huggingface.co/docs/optimum/index) library exports a model to LiteRT for [many architectures]((https://huggingface.co/docs/optimum/exporters/onnx/overview)).
The [Optimum](https://huggingface.co/docs/optimum/index) library exports a model to LiteRT for [many architectures](https://huggingface.co/docs/optimum/exporters/onnx/overview).
The benefits of exporting to LiteRT include the following.