Translation
Safetensors
mistral
elonreevemusk009 commited on
Commit
4a6b055
·
verified ·
1 Parent(s): aea75de

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -41
README.md CHANGED
@@ -1,15 +1,12 @@
1
  ---
2
- license: other
3
  license_name: openmdw
4
  license_link: LICENSE
5
- ---
6
- # Seed-X-Instruct-7B
7
- <a href="https://github.com/ByteDance-Seed/Seed-X-7B/blob/main/Technical_Report.pdf">
8
- <img src="https://img.shields.io/badge/Seed--X-Report-blue"></a>
9
- <a href="https://huggingface.co/ByteDance-Seed/Seed-X-Instruct-7B">
10
- <img src="https://img.shields.io/badge/Seed--X-Hugging Face-brightgreen"></a>
11
- <a href="https://github.com/ByteDance-Seed/Seed-X-7B/blob/main/LICENSE.openmdw">
12
- <img src="https://img.shields.io/badge/License-OpenMDW-yellow"></a>
13
 
14
  ## Introduction
15
  We are excited to introduce **Seed-X**, a powerful series of open-source multilingual translation language models, including an instruction model, a reinforcement learning model, and a reward model. It pushes the boundaries of translation capabilities within 7 billion parameters.
@@ -45,9 +42,6 @@ This repo contains the **Seed-X-Instruct** model, with the following features:
45
  Here is a simple example demonstrating how to load the model and perform translation using ```vllm```
46
  ```python
47
  from vllm import LLM, SamplingParams
48
-
49
- model_path = "./ByteDance-Seed/Seed-X-Instruct-7B"
50
-
51
  model = LLM(model=model_path,
52
  max_num_seqs=512,
53
  tensor_parallel_size=8,
@@ -55,17 +49,10 @@ model = LLM(model=model_path,
55
  gpu_memory_utilization=0.95)
56
 
57
  messages = [
58
- "Translate the following English sentence into Chinese:\nMay the force be with you <zh>", # without CoT
59
- "Translate the following English sentence into Chinese and explain it in detail:\nMay the force be with you <zh>" # with CoT
60
  ]
61
 
62
- # Sampling
63
- decoding_params = SamplingParams(temperature=0,
64
- max_tokens=512,
65
- skip_special_tokens=True)
66
- # Beam Search
67
- decoding_params = BeamSearchParams(beam_width=4,
68
- max_tokens=512)
69
 
70
  results = model.generate(messages, decoding_params)
71
  responses = [res.outputs[0].text.strip() for res in results]
@@ -73,23 +60,4 @@ responses = [res.outputs[0].text.strip() for res in results]
73
  print(responses)
74
  ```
75
  ## Evaluation
76
- We evaluated Seed-X on a diverse set of translation benchmarks, including FLORES-200, WMT-25, and a publicly released [challenge set](https://github.com/ByteDance-Seed/Seed-X-7B/tree/main/challenge_set) accompanied by human evaluations.
77
- ![humen_eval](imgs/humen_eval.png)
78
- For detailed benchmark results and analysis, please refer to our [Technical Report](https://github.com/ByteDance-Seed/Seed-X-7B/blob/main/Technical_Report.pdf).
79
-
80
- ## License
81
- This project is licensed under OpenMDW. See the [LICENSE](https://github.com/ByteDance-Seed/Seed-X-7B/blob/main/LICENSE.openmdw) file for details.
82
-
83
- ## Citation
84
- <!--If you find Seed-X useful for your research and applications, feel free to give us a star ⭐ or cite us using:
85
- ```bibtex
86
- @Article{XXX,
87
- title={XXXXXXXXXXX},
88
- author={XXX,XXX,XXX,XXX},
89
- year={2025},
90
- eprint={XXXX.XXXXX},
91
- archivePrefix={arXiv},
92
- primaryClass={cs.XX}
93
- }
94
- ```-->
95
- We will soon publish our technical report on Arxiv.
 
1
  ---
 
2
  license_name: openmdw
3
  license_link: LICENSE
4
+ datasets:
5
+ - fka/awesome
6
+ metrics:
7
+ - accuracy
8
+ - character
9
+ pipeline_tag: text-classification
 
 
10
 
11
  ## Introduction
12
  We are excited to introduce **Seed-X**, a powerful series of open-source multilingual translation language models, including an instruction model, a reinforcement learning model, and a reward model. It pushes the boundaries of translation capabilities within 7 billion parameters.
 
42
  Here is a simple example demonstrating how to load the model and perform translation using ```vllm```
43
  ```python
44
  from vllm import LLM, SamplingParams
 
 
 
45
  model = LLM(model=model_path,
46
  max_num_seqs=512,
47
  tensor_parallel_size=8,
 
49
  gpu_memory_utilization=0.95)
50
 
51
  messages = [
52
+ "Translate the following English sentence :\nMay the force be with you <zh>", # without CoT
53
+ "Translate the following English sentence and explain it in detail:\nMay the force be with you <zh>" # with CoT
54
  ]
55
 
 
 
 
 
 
 
 
56
 
57
  results = model.generate(messages, decoding_params)
58
  responses = [res.outputs[0].text.strip() for res in results]
 
60
  print(responses)
61
  ```
62
  ## Evaluation
63
+ We evaluated Seed-X on a diverse set