zhangyiss/mlx-examples
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx-examples.git synced 2025-08-28 00:30:09 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

fix prompt cache with no chat template

Browse Source
This commit is contained in:
Awni Hannun 2025-02-05 06:37:31 -08:00
parent 6e6ba07b54
commit 087adcfacb
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
llms/mlx_lm/cache_prompt.py
View File

@ -152,7 +152,7 @@ def main():
print("Saving...")
metadata = {}
metadata["model"] = args.model
metadata["chat_template"] = tokenizer.chat_template
metadata["chat_template"] = json.dumps(tokenizer.chat_template)
metadata["tokenizer_config"] = json.dumps(tokenizer_config)
save_prompt_cache(args.prompt_cache_file, cache, metadata)

2
llms/mlx_lm/generate.py
View File

@ -199,7 +199,7 @@ def main():
if tokenizer.chat_template is None:
tokenizer.chat_template = tokenizer.default_chat_template
elif using_cache:
tokenizer.chat_template = metadata["chat_template"]
tokenizer.chat_template = json.loads(metadata["chat_template"])
prompt = args.prompt.replace("\\n", "\n").replace("\\t", "\t")
prompt = sys.stdin.read() if prompt == "-" else prompt