Creat the wrangle.toml
file for cloudflare deployment:
name = "my-llm-api"
[ai]
binding = "AI"
[vars]
GPT_API_KEY = ""
GPT_BASE = ""
pnpm install
pnpm run deploy
"text-davinci-002-render-sha",
"gemini-pro",
"@cf/meta/llama-2-7b-chat-int8",
"@cf/mistral/mistral-7b-instruct-v0.1",
"@cf/meta/llama-2-7b-chat-fp16",
"@hf/thebloke/llama-2-13b-chat-awq",
"@hf/thebloke/zephyr-7b-beta-awq",
"@hf/thebloke/mistral-7b-instruct-v0.1-awq",
"@hf/thebloke/codellama-7b-instruct-awq"
and more...
This project is fully compitable with Vercel AI SDK.