starlight-apk/Qwen
1
0
Fork 0
mirror of https://github.com/QwenLM/Qwen.git synced 2026-05-20 16:35:47 +08:00
Code Issues Packages Projects Releases Wiki Activity

add 72B and 1.8B Qwen models, add Ascend 910 and Hygon DCU support, add docker support

Browse Source
This commit is contained in:
yangapku
2023-11-30 15:29:13 +08:00
parent 981c89b2a9
commit e8e15962d8
52 changed files with 6139 additions and 1435 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
dcu-support/qwen2flm.py Normal file
View File

@@ -0,0 +1,13 @@
import sys
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation import GenerationConfig
from fastllm_pytools import torch2flm
if __name__ == "__main__":
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-7B-Chat", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="cpu", trust_remote_code=True, fp32=True).eval()
model.generation_config = GenerationConfig.from_pretrained("Qwen/Qwen-7B-Chat", trust_remote_code=True) # 可指定不同的生成长度、top_p等相关超参
dtype = sys.argv[2] if len(sys.argv) >= 3 else "float16"
exportPath = sys.argv[1] if len(sys.argv) >= 2 else "qwen-7b-" + dtype + ".flm"
torch2flm.tofile(exportPath, model, tokenizer, dtype = dtype)