[package]
edition = "2021"
name = "utokenizer"
version = "0.1.1"
build = false
exclude = [
"validation_report*.json",
"validation_report*.csv",
"aihubmix_token_registry.json",
"aihubmix_token_count_log.jsonl",
"token_registry.json",
"token_count_log.jsonl",
"target/",
".venv/",
]
autolib = false
autobins = false
autoexamples = false
autotests = false
autobenches = false
description = "CLI tool for building a local model-tokenizer registry and counting input tokens across model families."
homepage = "https://crates.io/crates/utokenizer"
documentation = "https://docs.rs/utokenizer"
readme = "README.md"
keywords = [
"tokenizer",
"llm",
"tokens",
"cli",
"ai",
]
categories = [
"command-line-utilities",
"text-processing",
]
license = "MIT"
repository = "https://crates.io/crates/utokenizer"
[[bin]]
name = "utokenizer"
path = "src/main.rs"
[dependencies.anyhow]
version = "1"
[dependencies.chrono]
version = "0.4"
[dependencies.clap]
version = "4.5"
features = ["derive"]
[dependencies.dotenvy]
version = "0.15"
[dependencies.futures]
version = "0.3"
[dependencies.reqwest]
version = "0.12"
features = [
"json",
"rustls-tls",
]
[dependencies.serde]
version = "1"
features = ["derive"]
[dependencies.serde_json]
version = "1"
[dependencies.tokio]
version = "1"
features = [
"rt-multi-thread",
"macros",
"fs",
]