Cotran/onnx conversion (#145)

* onnx replacement

* onnx conversion for nli and embedding model

* fix naming

* fix naming

* fix naming

* pin version
This commit is contained in:
Co Tran 2024-10-08 14:37:48 -07:00 committed by GitHub
parent b30ad791f7
commit 80d2229053
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 61 additions and 42 deletions

View file

@ -1,5 +1,5 @@
pub const DEFAULT_EMBEDDING_MODEL: &str = "BAAI/bge-large-en-v1.5";
pub const DEFAULT_INTENT_MODEL: &str = "tasksource/deberta-base-long-nli";
pub const DEFAULT_EMBEDDING_MODEL: &str = "katanemo/bge-large-en-v1.5-onnx";
pub const DEFAULT_INTENT_MODEL: &str = "katanemo/deberta-base-nli-onnx";
pub const DEFAULT_PROMPT_TARGET_THRESHOLD: f64 = 0.8;
pub const DEFAULT_HALLUCINATED_THRESHOLD: f64 = 0.1;
pub const RATELIMIT_SELECTOR_HEADER_KEY: &str = "x-arch-ratelimit-selector";