Download serving/src/lib.rs from geraldaton20/alter_ego: direct link, hf CLI and curl.
- Browser
- Download file 3.25 kB
-
https://huggingface.co/geraldaton20/alter_ego/resolve/main/serving/src/lib.rs
- Command line
-
hf download hf://geraldaton20/alter_ego/serving/src/lib.rs
-
curl -L -o lib.rs https://huggingface.co/geraldaton20/alter_ego/resolve/main/serving/src/lib.rs
3.25 kB
| //! Alter-Ego serving system. | |
| //! | |
| //! The production home of the dual-model system: a blank-slate student (SAN) | |
| //! whose every experience is validated by an independent alter-ego judge before | |
| //! it is allowed to become permanent. This crate implements inference, the | |
| //! tri-memory system, the trust-score gate, the digestion pipeline, recall, | |
| //! LoRA-based online learning, and the real-time ecosystem loop (the "skull"). | |
| //! The student checkpoint format is identical to the one produced by the Python | |
| //! Kaggle training pipeline (`training/kernels/train.py`), so a model trained | |
| //! there loads directly here. | |
| pub mod bundle; | |
| pub mod calibration; | |
| pub mod bench; | |
| pub mod checkpoint; | |
| pub mod digestion; | |
| pub mod ecosystem; | |
| pub mod error; | |
| pub mod export; | |
| pub mod lora; | |
| pub mod jina_embedder; | |
| pub mod memory; | |
| pub mod model; | |
| pub mod og_backend; | |
| pub mod recall; | |
| pub mod server; | |
| pub mod tokenizer_bpe; | |
| pub mod trust; | |
| pub mod vector_index; | |
| pub mod needle_ffi; | |
| pub use needle_ffi::NeedleModel; | |
| pub use error::{Error, Result}; | |
| /// Shared builders (tests today; serving bootstrap later). | |
| pub mod main_helpers { | |
| use crate::model::{ParamMap, SanConfig}; | |
| use ndarray::Array2; | |
| use std::collections::HashMap; | |
| fn rand_arr(rows: usize, cols: usize) -> Array2<f32> { | |
| let n = rows * cols; | |
| let mut s: u64 = 0x853C49E6748FEA9B ^ (n as u64).rotate_left(17); | |
| let data: Vec<f32> = (0..n) | |
| .map(|_| { | |
| s ^= s << 13; | |
| s ^= s >> 7; | |
| s ^= s << 17; | |
| ((s >> 33) as f32 / (u32::MAX as f32) - 0.5) * 0.1 | |
| }) | |
| .collect(); | |
| Array2::from_shape_vec((rows, cols), data).expect("shape") | |
| } | |
| /// Deterministic random base weights for a config (frozen-base material). | |
| pub fn random_student(cfg: &SanConfig) -> crate::model::San { | |
| let d = cfg.d_model; | |
| let ffn = cfg.ffn_ratio * d; | |
| let mut p = ParamMap::new(); | |
| p.insert("tok_emb.weight".into(), rand_arr(cfg.vocab, d)); | |
| p.insert("pos".into(), rand_arr(cfg.max_seq_len, d)); | |
| p.insert("head.weight".into(), rand_arr(cfg.vocab, d)); | |
| for i in 0..cfg.n_layers { | |
| p.insert(format!("blocks.{i}.ln1.weight"), rand_arr(1, d)); | |
| p.insert(format!("blocks.{i}.ln1.bias"), rand_arr(1, d)); | |
| p.insert(format!("blocks.{i}.attn.qkv.weight"), rand_arr(3 * d, d)); | |
| p.insert(format!("blocks.{i}.attn.o.weight"), rand_arr(d, d)); | |
| p.insert(format!("blocks.{i}.ln2.weight"), rand_arr(1, d)); | |
| p.insert(format!("blocks.{i}.ln2.bias"), rand_arr(1, d)); | |
| p.insert(format!("blocks.{i}.mlp.0.weight"), rand_arr(ffn, d)); | |
| p.insert(format!("blocks.{i}.mlp.0.bias"), rand_arr(1, ffn)); | |
| p.insert(format!("blocks.{i}.mlp.2.weight"), rand_arr(d, ffn)); | |
| p.insert(format!("blocks.{i}.mlp.2.bias"), rand_arr(1, d)); | |
| } | |
| p.insert("ln_f.weight".into(), rand_arr(1, d)); | |
| p.insert("ln_f.bias".into(), rand_arr(1, d)); | |
| let cfg2 = cfg.clone(); | |
| crate::model::San::from_params(p, cfg2).expect("valid params") | |
| } | |
| } | |