supports small llama and gemma models

Refactor inference

dedicated crates for llama and gemma inferencing, not integrated

crates/llama-runner/src/lib.rs

@@ -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>";
+