From 6b6d5b5024faaf82019d08cde5e8a9d69c6ca316 Mon Sep 17 00:00:00 2001 From: Qingyou Meng Date: Tue, 21 Mar 2023 03:33:10 +0800 Subject: [PATCH] Fixed tokenizer.model not found error when model dir is symlink (#325) --- convert-pth-to-ggml.py | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/convert-pth-to-ggml.py b/convert-pth-to-ggml.py index 42f537769..108eb1fcc 100644 --- a/convert-pth-to-ggml.py +++ b/convert-pth-to-ggml.py @@ -17,6 +17,7 @@ # and vocabulary. # import argparse +import os import sys import json import struct @@ -44,8 +45,14 @@ def get_n_parts(dim): def load_hparams_and_tokenizer(dir_model): + # `dir_model` is something like `models/7B` or `models/7B/`. + # "tokenizer.model" is expected under model's parent dir. + # When `dir_model` is a symlink, f"{dir_model}/../tokenizer.model" would not be found. + # Let's use the model's parent dir directly. + model_parent_dir = os.path.dirname(os.path.normpath(dir_model)) + fname_hparams = f"{dir_model}/params.json" - fname_tokenizer = f"{dir_model}/../tokenizer.model" + fname_tokenizer = f"{model_parent_dir}/tokenizer.model" with open(fname_hparams, "r") as f: hparams = json.load(f)