Together 分发版

The llamastack/distribution-together 分发版包含以下提供者配置。

API

提供者

代理

inline::meta-reference

数据集 IO

remote::huggingface, inline::localfs

评估

inline::meta-reference

推理

remote::together, inline::sentence-transformers

安全

inline::llama-guard

评分

inline::basic, inline::llm-as-judge, inline::braintrust

遥测

inline::meta-reference

工具运行时

remote::brave-search, remote::tavily-search, inline::rag-runtime, remote::model-context-protocol, remote::wolfram-alpha

向量 IO

inline::faiss, remote::chromadb, remote::pgvector

环境变量

可以配置以下环境变量

  • LLAMA_STACK_PORT: Llama Stack 分发服务器的端口(默认值:8321

  • TOGETHER_API_KEY: Together.AI API 密钥(默认值:``)

模型

默认提供以下模型

  • meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo (别名: meta-llama/Llama-3.1-8B-Instruct)

  • meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo (别名: meta-llama/Llama-3.1-70B-Instruct)

  • meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo (别名: meta-llama/Llama-3.1-405B-Instruct-FP8)

  • meta-llama/Llama-3.2-3B-Instruct-Turbo (别名: meta-llama/Llama-3.2-3B-Instruct)

  • meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo (别名: meta-llama/Llama-3.2-11B-Vision-Instruct)

  • meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo (别名: meta-llama/Llama-3.2-90B-Vision-Instruct)

  • meta-llama/Llama-3.3-70B-Instruct-Turbo (别名: meta-llama/Llama-3.3-70B-Instruct)

  • meta-llama/Meta-Llama-Guard-3-8B (别名: meta-llama/Llama-Guard-3-8B)

  • meta-llama/Llama-Guard-3-11B-Vision-Turbo (别名: meta-llama/Llama-Guard-3-11B-Vision)

  • togethercomputer/m2-bert-80M-8k-retrieval

  • togethercomputer/m2-bert-80M-32k-retrieval

  • meta-llama/Llama-4-Scout-17B-16E-Instruct (别名: meta-llama/Llama-4-Scout-17B-16E-Instruct, together/meta-llama/Llama-4-Scout-17B-16E-Instruct)

  • meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 (别名: meta-llama/Llama-4-Maverick-17B-128E-Instruct, together/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8)

前提条件:API 密钥

确保您拥有 Together API 密钥。您可以访问 together.xyz 获取一个。

使用 Together 运行 Llama Stack

您可以通过 Conda(构建代码)或 Docker(已有预构建镜像)来完成此操作。

通过 Docker

这种方法让您无需构建分发代码即可快速上手。

LLAMA_STACK_PORT=8321
docker run \
  -it \
  --pull always \
  -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
  llamastack/distribution-together \
  --port $LLAMA_STACK_PORT \
  --env TOGETHER_API_KEY=$TOGETHER_API_KEY

通过 Conda

llama stack build --template together --image-type conda
llama stack run ./run.yaml \
  --port $LLAMA_STACK_PORT \
  --env TOGETHER_API_KEY=$TOGETHER_API_KEY