Skip to content
This repository has been archived by the owner on Sep 12, 2024. It is now read-only.

fix: utf8 encode issue #49

Merged
merged 2 commits into from
May 7, 2023
Merged
Show file tree
Hide file tree
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
4 changes: 2 additions & 2 deletions packages/rwkv-cpp/src/context.rs
Original file line number Diff line number Diff line change
Expand Up @@ -104,10 +104,10 @@ impl RWKVContext {
log::info!("{}", sys_info);
}

pub fn rwkv_token_to_str(&self, token: &i32) -> Option<String> {
pub fn rwkv_tokens_to_str(&self, tokens: &[u32]) -> Option<String> {
let tokenizer = &self.tokenizer;
tokenizer
.decode(vec![(*token).try_into().unwrap()], false)
.decode(tokens.to_vec(), false)
.map(Some)
.unwrap_or(None)
}
Expand Down
29 changes: 18 additions & 11 deletions packages/rwkv-cpp/src/rwkv.rs
Original file line number Diff line number Diff line change
Expand Up @@ -102,6 +102,8 @@ impl RWKVInternal {

session.process_tokens(&tokens);

let mut accumulated_token: Vec<u32> = Vec::new();

for _i in 0..input.max_predict_length {
let logits = session.logits.as_mut();
let token = sample_logits(logits, temp, top_p, &seed);
Expand All @@ -120,18 +122,23 @@ impl RWKVInternal {
return;
}

let decoded = context.rwkv_token_to_str(&(token as i32)).unwrap();
accumulated_token.push(token as u32);

sender
.send(InferenceResult {
r#type: InferenceResultType::Data,
message: None,
data: Some(InferenceToken {
token: decoded,
completed: false,
}),
})
.unwrap();
let decoded = context.rwkv_tokens_to_str(&accumulated_token).unwrap();

if !decoded.contains('\u{FFFD}') {
accumulated_token.clear();
sender
.send(InferenceResult {
r#type: InferenceResultType::Data,
message: None,
data: Some(InferenceToken {
token: decoded,
completed: false,
}),
})
.unwrap();
}

session.process_tokens(&[token.try_into().unwrap()]);
}
Expand Down