alex/nova-betterchat
1
0
Fork 0
mirror of https://github.com/NovaOSS/nova-betterchat.git synced 2024-11-25 19:24:00 +01:00
Code Issues Packages Projects Releases Wiki Activity

only load cl100k tokeniser

Browse source 
fix #109, #13
This commit is contained in:
Jing Hua 2023-03-25 22:49:16 +08:00
parent 8ff5079266
commit 6a6d2fe819
1 changed files with 12 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

18
src/utils/messageUtils.ts
View file

@ -1,6 +1,7 @@
import { MessageInterface, ModelOptions } from '@type/chat'; import { MessageInterface, ModelOptions } from '@type/chat';
import { encoding_for_model } from '@dqbd/tiktoken'; import { Tiktoken } from '@dqbd/tiktoken/lite';
const cl100k_base = await import('@dqbd/tiktoken/encoders/cl100k_base.json');
// https://github.com/dqbd/tiktoken/issues/23#issuecomment-1483317174 // https://github.com/dqbd/tiktoken/issues/23#issuecomment-1483317174
export const getChatGPTEncoding = ( export const getChatGPTEncoding = (
@ -9,11 +10,16 @@ export const getChatGPTEncoding = (
) => { ) => {
const isGpt3 = model === 'gpt-3.5-turbo'; const isGpt3 = model === 'gpt-3.5-turbo';
const encoder = encoding_for_model(model, { const encoder = new Tiktoken(
'<|im_start|>': 100264, cl100k_base.bpe_ranks,
'<|im_end|>': 100265, {
'<|im_sep|>': 100266, ...cl100k_base.special_tokens,
}); '<|im_start|>': 100264,
'<|im_end|>': 100265,
'<|im_sep|>': 100266,
},
cl100k_base.pat_str
);
const msgSep = isGpt3 ? '\n' : ''; const msgSep = isGpt3 ? '\n' : '';
const roleSep = isGpt3 ? '\n' : '<|im_sep|>'; const roleSep = isGpt3 ? '\n' : '<|im_sep|>';