starlight-apk/Qwen
1
0
Fork 0
mirror of https://github.com/QwenLM/Qwen.git synced 2026-05-21 00:45:48 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update README_CN.md

Browse Source
This commit is contained in:
Wang Peng
2023-08-03 23:48:58 +08:00
committed by GitHub
parent 67adc5d029
commit 71ad2822e0
1 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
README_CN.md
View File

@@ -82,9 +82,9 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation import GenerationConfig from transformers.generation import GenerationConfig
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-7B-Chat", trust_remote_code=True) tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-7B-Chat", trust_remote_code=True)
## 使用bf16精度 ## 打开bf16精度，A100、H100、RTX3060、RTX3070等显卡建议启用以节省显存
# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="auto", trust_remote_code=True, bf16=True).eval() # model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="auto", trust_remote_code=True, bf16=True).eval()
## 使用fp16精度 ## 打开fp16精度，V100、P100、T4等显卡建议启用以节省显存
# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="auto", trust_remote_code=True, fp16=True).eval() # model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="auto", trust_remote_code=True, fp16=True).eval()
# 默认使用fp32精度 # 默认使用fp32精度
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="auto", trust_remote_code=True).eval() model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="auto", trust_remote_code=True).eval()
@@ -120,9 +120,9 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation import GenerationConfig from transformers.generation import GenerationConfig
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-7B", trust_remote_code=True) tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-7B", trust_remote_code=True)
## 使用bf16精度 ## 打开bf16精度，A100、H100、RTX3060、RTX3070等显卡建议启用以节省显存
# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B", device_map="auto", trust_remote_code=True, bf16=True).eval() # model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B", device_map="auto", trust_remote_code=True, bf16=True).eval()
## 使用fp16精度 ## 打开fp16精度，V100、P100、T4等显卡建议启用以节省显存
# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B", device_map="auto", trust_remote_code=True, fp16=True).eval() # model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B", device_map="auto", trust_remote_code=True, fp16=True).eval()
# 默认使用fp32精度 # 默认使用fp32精度
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B", device_map="auto", trust_remote_code=True).eval() model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B", device_map="auto", trust_remote_code=True).eval()