mirror of
https://github.com/ml-explore/mlx-examples.git
synced 2025-09-01 12:49:50 +08:00
Fix prompt cache for models without chat template (#1250)
* fix deepseek sharding (#1242) * fix prompt cache with no chat template
This commit is contained in:
@@ -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)
|
||||
|
||||
|
Reference in New Issue
Block a user