From 0672cd8f4268c1ccef22fdb7558d327ad213f88b Mon Sep 17 00:00:00 2001 From: Joan Martinez Date: Thu, 2 May 2024 15:31:00 +0200 Subject: [PATCH] use conver ids to tokens --- convert-hf-to-gguf.py | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/convert-hf-to-gguf.py b/convert-hf-to-gguf.py index 28bf20e99..555ef8fa1 100755 --- a/convert-hf-to-gguf.py +++ b/convert-hf-to-gguf.py @@ -271,10 +271,12 @@ class Model(ABC): chktxt = '\n \n\n \n\n\n \t \t\t \t\n \n \n \n \n🚀 (normal) 😶\u200d🌫️ (multiple emojis concatenated) ✅ 🦙🦙 3 33 333 3333 33333 333333 3333333 33333333 3.3 3..3 3...3 កាន់តែពិសេសអាច😁 ?我想在apple工作1314151天～ ------======= нещо на Български \'\'\'\'\'\'```````""""......!!!!!!?????? I\'ve been \'told he\'s there, \'RE you sure? \'M not sure I\'ll make it, \'D you like some tea? We\'Ve a\'lL' - chktok = tokenizer.decode(tokenizer.encode(chktxt)) - chkhsh = sha256(str(chktok).encode()).hexdigest() + token_ids = tokenizer.encode(chktxt) + token_list = tokenizer.convert_ids_to_tokens(token_ids) + chkhsh = sha256(str(token_list).encode()).hexdigest() - print(f"chktok: {chktok}") + print(f"token_ids: {token_ids}") + print(f"token_list: {token_list}") print(f"chkhsh: {chkhsh}") res = None