node-llama-cpp

Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level

v3.13.0 URL: https://unpkg.com/node-llama-cpp@3.13.0/dist/index.js

Open Browse Files

@lenml/tokenizers

a lightweight no-dependency fork of transformers.js (only tokenizers)

v3.7.2 URL: https://unpkg.com/@lenml/tokenizers@3.7.2/dist/main.global.js

Open Browse Files

llama llama2 llama3 chatgpt mistral tokenizer transformers transformers.js gpt4 gpt4o gpt3.5 vicuna chatglm baichuan qwen

qwen-ai-provider

Vercel AI Provider for running Qwen AI models

v0.1.1 URL: https://unpkg.com/qwen-ai-provider@0.1.1/dist/index.js

Open Browse Files

qwen ai provider vercel-ai vercel ai-sdk

@kdump/gemini-any-llm

> Let the Gemini CLI access any large language model provider

v0.0.26 URL: https://unpkg.com/@kdump/gemini-any-llm@0.0.26

Open Browse Files

gemini cli gemini llm api gateway openai ai proxy chat api zhipu qwen openai