Update README.md
Browse files
README.md
CHANGED
|
@@ -1,4 +1,8 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
language:
|
| 3 |
- en
|
| 4 |
- zh
|
|
@@ -24,7 +28,7 @@ language:
|
|
| 24 |
- hu
|
| 25 |
- id
|
| 26 |
- ko
|
| 27 |
-
-
|
| 28 |
- ro
|
| 29 |
- sk
|
| 30 |
- sv
|
|
@@ -60,15 +64,12 @@ language:
|
|
| 60 |
- ur
|
| 61 |
- uz
|
| 62 |
- yue
|
|
|
|
| 63 |
metrics:
|
| 64 |
- bleu
|
| 65 |
- comet
|
| 66 |
-
datasets:
|
| 67 |
-
- NiuTrans/LMT-60-sft-data
|
| 68 |
-
base_model:
|
| 69 |
-
- NiuTrans/LMT-60-4B-Base
|
| 70 |
-
license: apache-2.0
|
| 71 |
pipeline_tag: translation
|
|
|
|
| 72 |
---
|
| 73 |
|
| 74 |
## LMT
|
|
@@ -100,7 +101,9 @@ model_name = "NiuTrans/LMT-60-8B"
|
|
| 100 |
tokenizer = AutoTokenizer.from_pretrained(model_name, padding_side='left')
|
| 101 |
model = AutoModelForCausalLM.from_pretrained(model_name)
|
| 102 |
|
| 103 |
-
prompt = "Translate the following text from English into Chinese.
|
|
|
|
|
|
|
| 104 |
messages = [{"role": "user", "content": prompt}]
|
| 105 |
text = tokenizer.apply_chat_template(
|
| 106 |
messages,
|
|
@@ -122,7 +125,7 @@ print("response:", outputs)
|
|
| 122 |
| Resource Tier | Languages |
|
| 123 |
| :---- | :---- |
|
| 124 |
| High-resource Languages (13) | Arabic(ar), English(en), Spanish(es), German(de), French(fr), Italian(it), Japanese(ja), Dutch(nl), Polish(pl), Portuguese(pt), Russian(ru), Turkish(tr), Chinese(zh) |
|
| 125 |
-
| Medium-resource Languages (18) | Bulgarian(bg), Bengali(bn), Czech(cs), Danish(da), Modern Greek(el), Persian(fa), Finnish(fi), Hindi(hi), Hungarian(hu), Indonesian(id), Korean(ko), Norwegian(
|
| 126 |
| Low-resouce Languages (29) | Amharic(am), Azerbaijani(az), Tibetan(bo), Modern Hebrew(he), Croatian(hr), Armenian(hy), Icelandic(is), Javanese(jv), Georgian(ka), Kazakh(kk), Central Khmer(km), Kirghiz(ky), Lao(lo), Chinese Mongolian(mn_cn), Marathi(mr), Malay(ms), Burmese(my), Nepali(ne), Pashto(ps), Sinhala(si), Swahili(sw), Tamil(ta), Telugu(te), Tajik(tg), Tagalog(tl), Uighur(ug), Urdu(ur), Uzbek(uz), Yue Chinese(yue) |
|
| 127 |
|
| 128 |
## Citation
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model:
|
| 3 |
+
- NiuTrans/LMT-60-8B-Base
|
| 4 |
+
datasets:
|
| 5 |
+
- NiuTrans/LMT-60-sft-data
|
| 6 |
language:
|
| 7 |
- en
|
| 8 |
- zh
|
|
|
|
| 28 |
- hu
|
| 29 |
- id
|
| 30 |
- ko
|
| 31 |
+
- nb
|
| 32 |
- ro
|
| 33 |
- sk
|
| 34 |
- sv
|
|
|
|
| 64 |
- ur
|
| 65 |
- uz
|
| 66 |
- yue
|
| 67 |
+
license: apache-2.0
|
| 68 |
metrics:
|
| 69 |
- bleu
|
| 70 |
- comet
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 71 |
pipeline_tag: translation
|
| 72 |
+
library_name: transformers
|
| 73 |
---
|
| 74 |
|
| 75 |
## LMT
|
|
|
|
| 101 |
tokenizer = AutoTokenizer.from_pretrained(model_name, padding_side='left')
|
| 102 |
model = AutoModelForCausalLM.from_pretrained(model_name)
|
| 103 |
|
| 104 |
+
prompt = "Translate the following text from English into Chinese.
|
| 105 |
+
English: The concept came from China where plum blossoms were the flower of choice.
|
| 106 |
+
Chinese: "
|
| 107 |
messages = [{"role": "user", "content": prompt}]
|
| 108 |
text = tokenizer.apply_chat_template(
|
| 109 |
messages,
|
|
|
|
| 125 |
| Resource Tier | Languages |
|
| 126 |
| :---- | :---- |
|
| 127 |
| High-resource Languages (13) | Arabic(ar), English(en), Spanish(es), German(de), French(fr), Italian(it), Japanese(ja), Dutch(nl), Polish(pl), Portuguese(pt), Russian(ru), Turkish(tr), Chinese(zh) |
|
| 128 |
+
| Medium-resource Languages (18) | Bulgarian(bg), Bengali(bn), Czech(cs), Danish(da), Modern Greek(el), Persian(fa), Finnish(fi), Hindi(hi), Hungarian(hu), Indonesian(id), Korean(ko), Norwegian(nb), Romanian(ro), Slovak(sk), Swedish(sv), Thai(th), Ukrainian(uk), Vietnamese(vi) |
|
| 129 |
| Low-resouce Languages (29) | Amharic(am), Azerbaijani(az), Tibetan(bo), Modern Hebrew(he), Croatian(hr), Armenian(hy), Icelandic(is), Javanese(jv), Georgian(ka), Kazakh(kk), Central Khmer(km), Kirghiz(ky), Lao(lo), Chinese Mongolian(mn_cn), Marathi(mr), Malay(ms), Burmese(my), Nepali(ne), Pashto(ps), Sinhala(si), Swahili(sw), Tamil(ta), Telugu(te), Tajik(tg), Tagalog(tl), Uighur(ug), Urdu(ur), Uzbek(uz), Yue Chinese(yue) |
|
| 130 |
|
| 131 |
## Citation
|