ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

Update qwen2-7b example script (#11961)

Browse source
This commit is contained in:
binbin Deng 2024-08-29 18:25:17 +08:00 committed by GitHub
parent 7abe17d6f7
commit 14b2c8dc32
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 3 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
python/llm/example/NPU/HF-Transformers-AutoModels/LLM/README.md
View file

@ -104,7 +104,7 @@ python llama.py --repo-id-or-model-path meta-llama/Meta-Llama-3-8B-Instruct
python qwen2.py python qwen2.py
# to run Qwen2-7B-Instruct # to run Qwen2-7B-Instruct
python qwen2.py --repo-id-or-model-path Qwen/Qwen2-7B-Instruct --inter-pp 4 python qwen2.py --repo-id-or-model-path Qwen/Qwen2-7B-Instruct
# to run MiniCPM-1B-sft-bf16 # to run MiniCPM-1B-sft-bf16
python minicpm.py python minicpm.py

4
python/llm/example/NPU/HF-Transformers-AutoModels/LLM/qwen2.py
View file

@ -43,8 +43,8 @@ if __name__ == "__main__":
parser.add_argument("--max-output-len", type=int, default=1024) parser.add_argument("--max-output-len", type=int, default=1024)
parser.add_argument("--max-prompt-len", type=int, default=512) parser.add_argument("--max-prompt-len", type=int, default=512)
parser.add_argument("--disable-transpose-value-cache", action="store_true", default=False) parser.add_argument("--disable-transpose-value-cache", action="store_true", default=False)
parser.add_argument("--intra-pp", type=int, default=2) parser.add_argument("--intra-pp", type=int, default=None)
parser.add_argument("--inter-pp", type=int, default=1) parser.add_argument("--inter-pp", type=int, default=None)
args = parser.parse_args() args = parser.parse_args()
model_path = args.repo_id_or_model_path model_path = args.repo_id_or_model_path