Kill tiktoken — all token counting now uses Qwen 3.5 tokenizer
Remove tiktoken-rs dependency, CoreBPE field on Agent, and the msg_token_count() function. All tokenization now goes through the global HuggingFace tokenizer in agent/tokenizer.rs. Co-Authored-By: Proof of Concept <poc@bcachefs.org>
This commit is contained in:
parent
5e4067c04f
commit
67e3228c32
4 changed files with 1 additions and 78 deletions
46
Cargo.lock
generated
46
Cargo.lock
generated
|
|
@ -219,17 +219,6 @@ dependencies = [
|
|||
"generic-array",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "bstr"
|
||||
version = "1.12.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "63044e1ae8e69f3b5a92c736ca6269b8d12fa7efe39bf34ddb06d102cf0e2cab"
|
||||
dependencies = [
|
||||
"memchr",
|
||||
"regex-automata",
|
||||
"serde",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "bumpalo"
|
||||
version = "3.20.2"
|
||||
|
|
@ -894,17 +883,6 @@ dependencies = [
|
|||
"regex",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "fancy-regex"
|
||||
version = "0.13.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "531e46835a22af56d1e3b66f04844bed63158bc094a628bec1d321d9b4c44bf2"
|
||||
dependencies = [
|
||||
"bit-set",
|
||||
"regex-automata",
|
||||
"regex-syntax",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "figment"
|
||||
version = "0.10.19"
|
||||
|
|
@ -1965,7 +1943,6 @@ dependencies = [
|
|||
"serde_json",
|
||||
"serde_urlencoded",
|
||||
"skillratings",
|
||||
"tiktoken-rs",
|
||||
"tokenizers",
|
||||
"tokio",
|
||||
"tokio-rustls",
|
||||
|
|
@ -2393,12 +2370,6 @@ dependencies = [
|
|||
"syn 1.0.109",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "rustc-hash"
|
||||
version = "1.1.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "08d43f7aa6b08d49f382cde6a7982047c3426db949b1424bc4b7ec9ae12c6ce2"
|
||||
|
||||
[[package]]
|
||||
name = "rustc_version"
|
||||
version = "0.4.1"
|
||||
|
|
@ -2784,7 +2755,7 @@ dependencies = [
|
|||
"anyhow",
|
||||
"base64 0.22.1",
|
||||
"bitflags 2.11.0",
|
||||
"fancy-regex 0.11.0",
|
||||
"fancy-regex",
|
||||
"filedescriptor",
|
||||
"finl_unicode",
|
||||
"fixedbitset",
|
||||
|
|
@ -2857,21 +2828,6 @@ dependencies = [
|
|||
"syn 2.0.117",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "tiktoken-rs"
|
||||
version = "0.9.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "3a19830747d9034cd9da43a60eaa8e552dfda7712424aebf187b7a60126bae0d"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"base64 0.22.1",
|
||||
"bstr",
|
||||
"fancy-regex 0.13.0",
|
||||
"lazy_static",
|
||||
"regex",
|
||||
"rustc-hash",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "time"
|
||||
version = "0.3.47"
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue