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

Update README.md

Browse Source
This commit is contained in:
Yang An
2023-08-03 23:05:22 +08:00
committed by GitHub
parent 4e1b09dde1
commit 5c4d509df1
1 changed files with 10 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
README.md
View File

@@ -83,6 +83,11 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation import GenerationConfig
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-7B-Chat", trust_remote_code=True)
## use bf16
# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="auto", trust_remote_code=True, use_bf16=True).eval()
## use fp16
# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="auto", trust_remote_code=True, use_fp16=True).eval()
# use fp32
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="auto", trust_remote_code=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
@@ -117,6 +122,11 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation import GenerationConfig
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-7B", trust_remote_code=True)
## use bf16
# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B", device_map="auto", trust_remote_code=True, use_bf16=True).eval()
## use fp16
# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B", device_map="auto", trust_remote_code=True, use_fp16=True).eval()
# use fp32
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B", device_map="auto", trust_remote_code=True).eval()
model.generation_config = GenerationConfig.from_pretrained("Qwen/Qwen-7B", trust_remote_code=True) # 可指定不同的生成长度、top_p等相关超参