haoranxu commited on
Commit
f0a3613
•
1 Parent(s): ef79141

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -1
README.md CHANGED
@@ -12,6 +12,16 @@ license: mit
12
  primaryClass={cs.CL}
13
  }
14
  ```
 
 
 
 
 
 
 
 
 
 
15
  # Download ALMA(-R) Models and Dataset 🚀
16
 
17
  We release six translation models presented in the paper:
@@ -60,4 +70,6 @@ with torch.no_grad():
60
  generated_ids = model.generate(input_ids=input_ids, num_beams=5, max_new_tokens=20, do_sample=True, temperature=0.6, top_p=0.9)
61
  outputs = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
62
  print(outputs)
63
- ```
 
 
 
12
  primaryClass={cs.CL}
13
  }
14
  ```
15
+ ```
16
+ @misc{xu2023paradigm,
17
+ title={A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models},
18
+ author={Haoran Xu and Young Jin Kim and Amr Sharaf and Hany Hassan Awadalla},
19
+ year={2023},
20
+ eprint={2309.11674},
21
+ archivePrefix={arXiv},
22
+ primaryClass={cs.CL}
23
+ }
24
+ ```
25
  # Download ALMA(-R) Models and Dataset 🚀
26
 
27
  We release six translation models presented in the paper:
 
70
  generated_ids = model.generate(input_ids=input_ids, num_beams=5, max_new_tokens=20, do_sample=True, temperature=0.6, top_p=0.9)
71
  outputs = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
72
  print(outputs)
73
+ ```
74
+
75
+ Please find more details in our [GitHub repository](https://github.com/fe1ixxu/ALMA)