privacyguides/i18n
1
0
Fork 0
mirror of https://github.com/privacyguides/i18n.git synced 2025-06-20 17:54:21 +00:00
Code Activity

New Crowdin translations by GitHub Action

Browse Source
This commit is contained in:
Crowdin Bot
2024-11-27 06:39:02 +00:00
parent bd1bc8691c
commit 52ed610648
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
i18n/zh-Hant/ai-chat.md
View File

@ -28,7 +28,7 @@ cover: ai-chatbots.webp
本地模型也相當容易運行。 只要 8GB 記憶體，就能以較低的速度運行較小的模型。 使用更強大的硬體，例如具有足夠 VRAM 的專用 GPU 或具有快速 LPDDR5X 記憶體的現代系統，可以提供最佳的體驗。
LLMs can usually be differentiated by the number of parameters, which can vary between 1.3B to 405B for open-source models available for end users. For example, models below 6.7B parameters are only good for basic tasks like text summaries, while models between 7B and 13B are a great compromise between quality and speed. Models with advanced reasoning capabilities are generally around 70B.
LLM 通常可以透過參數的數量來區分用途，對於提供給終端使用者的開放原始碼模型，參數的數量通常介於 1.3B 到 405B 之間。 例如，參數低於 6.7B 的模型只適合文字摘要等基本任務，而參數介於 7B 與 13B 之間的模型則是品質與速度的絕佳折衷。 具備進階推理能力的模型一般在 70B 左右。
For consumer-grade hardware, it is generally recommended to use [quantized models](https://huggingface.co/docs/optimum/en/concept_guides/quantization) for the best balance between model quality and performance. Check out the table below for more precise information about the typical requirements for different sizes of quantized models.