supports small llama and gemma models

Refactor inference

dedicated crates for llama and gemma inferencing, not integrated
This commit is contained in:
geoffsee
2025-08-29 18:15:29 -04:00
parent d06b16bb12
commit 315ef17605
26 changed files with 2136 additions and 1402 deletions

View File

@@ -0,0 +1,8 @@
pub mod llama_api;
use clap::ValueEnum;
pub use llama_api::{run_llama_inference, LlamaInferenceConfig, WhichModel};
// Re-export constants and types that might be needed
pub const EOS_TOKEN: &str = "</s>";