From d841e1dc0dffb27a242b918446fa010d20ababcf Mon Sep 17 00:00:00 2001 From: Ruonan Wang Date: Wed, 25 Dec 2024 19:23:04 -0800 Subject: [PATCH] [NPU] update convert script based on latest usage (#12617) --- .../NPU/HF-Transformers-AutoModels/LLM/CPP_Examples/convert.py | 2 -- 1 file changed, 2 deletions(-) diff --git a/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/CPP_Examples/convert.py b/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/CPP_Examples/convert.py index e236433cafe..e5e28472728 100644 --- a/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/CPP_Examples/convert.py +++ b/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/CPP_Examples/convert.py @@ -60,7 +60,6 @@ t0 = time.perf_counter() model = AutoModelForCausalLM.from_pretrained(model_path, optimize_model=True, - pipeline=True, load_in_low_bit=args.low_bit, max_context_len=args.max_context_len, max_prompt_len=args.max_prompt_len, @@ -69,7 +68,6 @@ attn_implementation="eager", transpose_value_cache=not args.disable_transpose_value_cache, trust_remote_code=True, - convert_model=True, save_directory=save_dir) t1 = time.perf_counter()