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:
Awni Hannun
2025-02-06 11:10:58 -08:00
committed by GitHub
parent 747c08e202
commit 52c41b5b5a
3 changed files with 7 additions and 7 deletions

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)