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
2023-08-04 15:58:12 +08:00
committed by GitHub
parent 71e2229d8b
commit 756a0db14b
1 changed files with 6 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
README.md
View File

@@ -85,11 +85,14 @@ from transformers.generation import GenerationConfig
# To remove the strategy, you can add `allowed_special`, which accepts the string "all" or a `set` of special tokens.
# For example: tokens = tokenizer(text, allowed_special="all")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-7B-Chat", trust_remote_code=True)
## use bf16
# We recommend checking the support of BF16 first. Run the command below:
# import torch
# torch.cuda.is_bf16_supported()
# use bf16
# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="auto", trust_remote_code=True, bf16=True).eval()
## use fp16
# use fp16
# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="auto", trust_remote_code=True, fp16=True).eval()
## use cpu only
# use cpu only
# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="cpu", trust_remote_code=True).eval()
# use fp32
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="auto", trust_remote_code=True).eval()