Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 13 additions & 2 deletions src/encoding/config.rs
Original file line number Diff line number Diff line change
Expand Up @@ -82,7 +82,7 @@ pub struct Config {
}

/// Reasonable starting point: dictionary capped at 4 096 tokens, dynamic
/// threshold sampling 15 %.
/// threshold sampling 15 %, and deterministic sampling with seed 42.
pub const DEFAULT_CONFIG: Config = Config {
max_dict_bits: match MaxDictBits::new(12) {
Ok(b) => b,
Expand All @@ -92,7 +92,7 @@ pub const DEFAULT_CONFIG: Config = Config {
Ok(t) => t,
Err(_) => unreachable!(),
},
seed: None,
seed: Some(42),
};

impl Default for Config {
Expand Down Expand Up @@ -186,3 +186,14 @@ impl From<Config> for TrainingConfig {
}
}
}

#[cfg(test)]
mod tests {
use super::*;

#[test]
fn default_config_uses_a_deterministic_seed() {
assert_eq!(DEFAULT_CONFIG.seed, Some(42));
assert_eq!(Config::default().seed, Some(42));
}
}
Loading