Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-11 13:00:25 +01:00
Code Issues Packages Projects Releases Wiki Activity

llama : fix typo in <|im_end|> token text (#6745)

Browse Source
This commit is contained in:
Georgi Gerganov 2024-04-22 15:41:11 +03:00
parent c0956b09ba
commit 8960fe86ae
No known key found for this signature in database
GPG Key ID: BF970631944C16B7
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
llama.cpp
View File

@ -4340,7 +4340,7 @@ static void llm_load_vocab(
}
}
// find EOT token: "<|eot_id|>", "<|im_emd|>", "<end_of_turn>", etc.
// find EOT token: "<|eot_id|>", "<|im_end|>", "<end_of_turn>", etc.
//
// TODO: convert scripts should provide this token through the KV metadata LLAMA_KV_TOKENIZER_EOT_ID
// for now, we apply this workaround to find the EOT token based on its text
@ -4351,7 +4351,7 @@ static void llm_load_vocab(
// need to fix convert script
//vocab.id_to_token[t.second].type == LLAMA_TOKEN_TYPE_CONTROL &&
(t.first == "<|eot_id|>" ||
t.first == "<|im_emd|>" ||
t.first == "<|im_end|>" ||
t.first == "<end_of_turn>"
)
) {