跳到正文
Ollama:Blog·· 2024-04-18精選AI 評分80

Llama 3 已可透過 Ollama 執行

Llama 3

AI 導讀

Llama 3 已可透過 Ollama 執行,首批提供 8B 和 70B 參數版本。其訓練數據集規模達 Llama 2 的 7 倍,上下文窗口增至 8K,詞彙表含 128K tokens,錯誤拒答少於 Llama 2 的 1/3。

推薦理由

文中從訓練數據集、上下文窗口、詞彙表和錯誤拒答比例等方面比較 Llama 3 與 Llama 2,並提供 8B、70B 版本的執行命令。

正文 · 原文

3 Ollamas

Llama 3 is now available to run using Ollama.

To get started, Download Ollama and run Llama 3:

ollama run llama3

The most capable model

Llama 3 represents a large improvement over Llama 2 and other openly available models:

  • Trained on a dataset seven times larger than Llama 2
  • Double the context length of 8K from Llama 2
  • Encodes language much more efficiently using a larger token vocabulary with 128K tokens
  • Less than 1⁄3 of the false “refusals” when compared to Llama 2

Two sizes: 8B and 70B parameters

The initial release of Llama 3 includes two sizes:

Using Llama 3 with popular tooling

LangChain

from langchain_community.llms import Ollama
llm = Ollama(model="llama3")
llm.invoke("Why is the sky blue?")

LlamaIndex

from llama_index.llms.ollama import Ollama
llm = Ollama(model="llama3")
llm.complete("Why is the sky blue?")

What’s next

Meta plans to release a 400B parameter Llama 3 model and many more. Over the coming months, they will release multiple models with new capabilities including multimodality, the ability to converse in multiple languages, a much longer context window, and stronger overall capabilities.

來源:Ollama:Blog · ollama.com