Find agent skills by outcome

<!---

Copyright 2023 The HuggingFace Team. All rights reserved.

repos:

- repo: https://github.com/astral-sh/ruff-pre-commit

<!---

Copyright 2020 The HuggingFace Team. All rights reserved.

Byte-compiled / optimized / DLL files

pycache/

Untitled Skill

Alpaca Instruction Following Dataset

To enable more open-source research on instruction following large language models, we use generate 52K instruction-followng demonstrations using OpenAI's text-davinci-003 model.

Alpaca Model Card

Organization developing the model

repos:

- repo: https://github.com/pre-commit/pre-commit-hooks

!# LLaMA Factory

!# LLaMA Factory

Byte-compiled / optimized / DLL files

pycache/

.vscode

.git

Auto detect text files and perform LF normalization

* text=auto

Tokenization

注：作为术语的“tokenization”在中文中尚无共识的概念对应，本文档采用英文表达以利说明。

Untitled Skill

中文&nbsp ｜ &nbspEnglish&nbsp ｜ &nbsp日本語 ｜ &nbspFrançais ｜ &nbspEspañol

Introducing Qwen-7B: Open foundation and human-aligned models (of the state-of-the-arts)

Large language models have recently attracted an extremely large amount of

Tokenization

Qwen-7B uses BPE tokenization on UTF-8 bytes using the tiktoken package.

トークン化

Qwen-7B は tiktoken パッケージを使用して、UTF-8 バイトを BPE トークン化します。

Untitled Skill

中文&nbsp ｜ &nbspEnglish&nbsp ｜ &nbsp日本語 ｜ &nbspFrançais ｜ &nbspEspañol

Untitled Skill

中文&nbsp ｜ &nbspEnglish&nbsp ｜ &nbsp日本語&nbsp ｜ &nbspFrançais ｜ &nbspEspañol

Untitled Skill

中文&nbsp ｜ &nbspEnglish&nbsp ｜ &nbsp日本語 ｜ &nbspFrançais ｜ &nbspEspañol

FAQ

Flash attention is an option for accelerating training and inference. Only NVIDIA GPUs of Turing, Ampere, Ada, and Hopper architecture, e.g., H100, A100, RTX 3090, T4, RTX 2080, can support flash atte...

Untitled Skill

中文&nbsp ｜ &nbspEnglish&nbsp ｜ &nbsp日本語 ｜ &nbspFrançais ｜ &nbspEspañol

FAQ

flash attention是一个用于加速模型训练推理的可选项，且仅适用于Turing、Ampere、Ada、Hopper架构的Nvidia GPU显卡（如H100、A100、RTX 3090、T4、RTX 2080），您可以在不安装flash attention的情况下正常使用模型进行推理。