huangzixian
commited on
Commit
•
8924ae7
1
Parent(s):
35ace76
update readme
Browse files
README.md
CHANGED
@@ -1,10 +1,10 @@
|
|
1 |
### Model Sources
|
2 |
|
3 |
-
Paper
|
4 |
|
5 |
-
Link
|
6 |
|
7 |
-
Repository
|
8 |
|
9 |
### Model Description
|
10 |
|
@@ -17,7 +17,7 @@ We collected extensive training sets in 102 languages for continued pre-training
|
|
17 |
LLaMAX supports translation between more than 100 languages, surpassing the performance of similarly scaled LLMs.
|
18 |
|
19 |
```angular2html
|
20 |
-
def
|
21 |
instruction = f'Translate the following sentences from {src_language} to {trg_language}.'
|
22 |
prompt = (
|
23 |
'Below is an instruction that describes a task, paired with an input that provides further context. '
|
@@ -46,21 +46,20 @@ tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokeniza
|
|
46 |
|
47 |
|
48 |
### 🔥 Excellent Translation Performance
|
|
|
49 |
|
50 |
-
|
51 |
-
|
52 |
-
|
|
53 |
-
|
54 |
-
|
|
55 |
-
| LLaMA2-Alpaca | 13B | 57.16 | 11.85 | 53.93 | 6.25 | 54.70 | 9.42 | 51.47 | 3.11 | 50.73 | 5.23 | 50.68 | 2.74 | 47.86 | 4.96 |
|
56 |
-
| LLaMAX2-Alpaca| 7B | 76.66 | 23.17 | 73.54 | 14.17 | 73.82 | 18.96 | 74.64 | 14.49 | 72.00 | 15.82 | 70.91 | 11.34 | 68.67 | 15.53 |
|
57 |
|
58 |
|
59 |
| System | Size | X-en (COMET) | X-en (BLEU) | X-zh (COMET)| X-zh (BLEU) | X-de (COMET) | X-de (BLEU) | X-ne (COMET) | X-ne (BLEU) |X-ar (COMET) | X-ar (BLEU) | X-az (COMET) | X-az (BLEU) | X-ceb (COMET) | X-ceb (BLEU) |
|
60 |
|---------------|------|----------------|-------------| ----| ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- |--------------|
|
61 |
-
|
|
62 |
-
|
|
63 |
-
| LLaMAX2-Alpaca| 7B | 80.55 | 30.63 | 75.52 | 13.53 | 74.47 | 19.26 | 67.36 | 15.47 | 75.40 | 15.32 | 72.03 | 10.27 | 65.05| 16.11|
|
64 |
|
65 |
|
66 |
### 🔥 Effective Base Model for Multilingual Task
|
@@ -68,11 +67,11 @@ LLaMAX2-Alpaca achieves an average spBLEU score improvement of over **10 points*
|
|
68 |
LLaMAX preserves its efficacy in general tasks and improves the performance on multilingual tasks.
|
69 |
We fine-tuned LLaMAX using only the English training set of downstream task, which also shows significant improvements in non-English. We provide fine-tuning LLaMAX models for the following three tasks:
|
70 |
|
71 |
-
Math Reasoning
|
72 |
|
73 |
-
Commonsense Reasoning
|
74 |
|
75 |
-
Natural Language Inference
|
76 |
|
77 |
### Supported Languages
|
78 |
Akrikaans (af), Amharic (am), Arabic (ar), Armenian (hy), Assamese (as), Asturian (ast), Azerbaijani (az), Belarusian (be), Bengali (bn), Bosnian (bs), Bulgarian (bg), Burmese (my), Catalan (ca), Cebuano (ceb), Chinese Simpl (zho), Chinese Trad (zho), Croatian (hr), Czech (cs), Danish (da), Dutch (nl), English (en), Estonian (et), Filipino (tl), Finnish (fi), French (fr), Fulah (ff), Galician (gl), Ganda (lg), Georgian (ka), German (de), Greek (el), Gujarati (gu), Hausa (ha), Hebrew (he), Hindi (hi), Hungarian (hu), Icelandic (is), Igbo (ig), Indonesian (id), Irish (ga), Italian (it), Japanese (ja), Javanese (jv), Kabuverdianu (kea), Kamba (kam), Kannada (kn), Kazakh (kk), Khmer (km), Korean (ko), Kyrgyz (ky), Lao (lo), Latvian (lv), Lingala (ln), Lithuanian (lt), Luo (luo), Luxembourgish (lb), Macedonian (mk), Malay (ms), Malayalam (ml), Maltese (mt), Maori (mi), Marathi (mr), Mongolian (mn), Nepali (ne), Northern Sotho (ns), Norwegian (no), Nyanja (ny), Occitan (oc), Oriya (or), Oromo (om), Pashto (ps), Persian (fa), Polish (pl), Portuguese (pt), Punjabi (pa), Romanian (ro), Russian (ru), Serbian (sr), Shona (sn), Sindhi (sd), Slovak (sk), Slovenian (sl), Somali (so), Sorani Kurdish (ku), Spanish (es), Swahili (sw), Swedish (sv), Tajik (tg), Tamil (ta), Telugu (te), Thai (th), Turkish (tr), Ukrainian (uk), Umbundu (umb), Urdu (ur), Uzbek (uz), Vietnamese (vi), Welsh (cy), Wolof (wo), Xhosa (xh), Yoruba (yo), Zulu (zu)
|
|
|
1 |
### Model Sources
|
2 |
|
3 |
+
- **Paper**: "LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages"
|
4 |
|
5 |
+
- **Link**:
|
6 |
|
7 |
+
- **Repository**: https://github.com/CONE-MT/LLaMAX/
|
8 |
|
9 |
### Model Description
|
10 |
|
|
|
17 |
LLaMAX supports translation between more than 100 languages, surpassing the performance of similarly scaled LLMs.
|
18 |
|
19 |
```angular2html
|
20 |
+
def Prompt_template(query, src_language, trg_language):
|
21 |
instruction = f'Translate the following sentences from {src_language} to {trg_language}.'
|
22 |
prompt = (
|
23 |
'Below is an instruction that describes a task, paired with an input that provides further context. '
|
|
|
46 |
|
47 |
|
48 |
### 🔥 Excellent Translation Performance
|
49 |
+
LLaMAX achieves an average spBLEU score improvement of over **10 points** compared to the LLaMA2-Alpaca model on the Flores-101 dataset.
|
50 |
|
51 |
+
| System | Size | en-X (COMET) | en-X (BLEU) | zh-X (COMET)| zh-X (BLEU) | de-X (COMET) | de-X (BLEU) | ne-X (COMET) | ne-X (BLEU) |ar-X (COMET) | ar-X (BLEU) | az-X (COMET) | az-X (BLEU) | ceb-X (COMET) | ceb-X (BLEU)|
|
52 |
+
|--------------------|------|--------------------|-------------| ----| ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- |
|
53 |
+
| LLaMAX2-7B-Alpaca | 7B | 52.83 | 9.44 | 51.29 | 3.80 | 51.47 | 6.82 | 46.59 | 1.31 | 46.76 | 2.84 | 48.63 | 1.36 | 41.02 | 2.69 |
|
54 |
+
| LLaMAX2-7B-Alpaca | 13B | 57.16 | 11.85 | 53.93 | 6.25 | 54.70 | 9.42 | 51.47 | 3.11 | 50.73 | 5.23 | 50.68 | 2.74 | 47.86 | 4.96 |
|
55 |
+
| LLaMAX2-7B-Alpaca | 7B | 76.66 | 23.17 | 73.54 | 14.17 | 73.82 | 18.96 | 74.64 | 14.49 | 72.00 | 15.82 | 70.91 | 11.34 | 68.67 | 15.53 |
|
|
|
|
|
56 |
|
57 |
|
58 |
| System | Size | X-en (COMET) | X-en (BLEU) | X-zh (COMET)| X-zh (BLEU) | X-de (COMET) | X-de (BLEU) | X-ne (COMET) | X-ne (BLEU) |X-ar (COMET) | X-ar (BLEU) | X-az (COMET) | X-az (BLEU) | X-ceb (COMET) | X-ceb (BLEU) |
|
59 |
|---------------|------|----------------|-------------| ----| ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- |--------------|
|
60 |
+
| LLaMAX2-7B-Alpaca | 7B |65.85| 16.44 | 56.53 | 4.46 | 56.76 | 9.01 | 34.96 | 1.03 | 44.10 | 2.18 | 40.67 | 0.63 | 45.69 | 1.73 |
|
61 |
+
| LLaMAX2-7B-Alpaca | 13B | 68.72| 19.69 | 64.46| 8.80| 62.86| 12.57| 38.88| 2.16| 52.08| 4.48| 41.18| 0.87| 48.47| 2.51|
|
62 |
+
| LLaMAX2-7B-Alpaca| 7B | 80.55 | 30.63 | 75.52 | 13.53 | 74.47 | 19.26 | 67.36 | 15.47 | 75.40 | 15.32 | 72.03 | 10.27 | 65.05| 16.11|
|
63 |
|
64 |
|
65 |
### 🔥 Effective Base Model for Multilingual Task
|
|
|
67 |
LLaMAX preserves its efficacy in general tasks and improves the performance on multilingual tasks.
|
68 |
We fine-tuned LLaMAX using only the English training set of downstream task, which also shows significant improvements in non-English. We provide fine-tuning LLaMAX models for the following three tasks:
|
69 |
|
70 |
+
- **Math Reasoning**: https://huggingface.co/LLaMAX/LLaMAX2-7B-MetaMath
|
71 |
|
72 |
+
- **Commonsense Reasoning**: https://huggingface.co/LLaMAX/LLaMAX2-7B-X-CSQA
|
73 |
|
74 |
+
- **Natural Language Inference**: https://huggingface.co/LLaMAX/LLaMAX2-7B-XNLI
|
75 |
|
76 |
### Supported Languages
|
77 |
Akrikaans (af), Amharic (am), Arabic (ar), Armenian (hy), Assamese (as), Asturian (ast), Azerbaijani (az), Belarusian (be), Bengali (bn), Bosnian (bs), Bulgarian (bg), Burmese (my), Catalan (ca), Cebuano (ceb), Chinese Simpl (zho), Chinese Trad (zho), Croatian (hr), Czech (cs), Danish (da), Dutch (nl), English (en), Estonian (et), Filipino (tl), Finnish (fi), French (fr), Fulah (ff), Galician (gl), Ganda (lg), Georgian (ka), German (de), Greek (el), Gujarati (gu), Hausa (ha), Hebrew (he), Hindi (hi), Hungarian (hu), Icelandic (is), Igbo (ig), Indonesian (id), Irish (ga), Italian (it), Japanese (ja), Javanese (jv), Kabuverdianu (kea), Kamba (kam), Kannada (kn), Kazakh (kk), Khmer (km), Korean (ko), Kyrgyz (ky), Lao (lo), Latvian (lv), Lingala (ln), Lithuanian (lt), Luo (luo), Luxembourgish (lb), Macedonian (mk), Malay (ms), Malayalam (ml), Maltese (mt), Maori (mi), Marathi (mr), Mongolian (mn), Nepali (ne), Northern Sotho (ns), Norwegian (no), Nyanja (ny), Occitan (oc), Oriya (or), Oromo (om), Pashto (ps), Persian (fa), Polish (pl), Portuguese (pt), Punjabi (pa), Romanian (ro), Russian (ru), Serbian (sr), Shona (sn), Sindhi (sd), Slovak (sk), Slovenian (sl), Somali (so), Sorani Kurdish (ku), Spanish (es), Swahili (sw), Swedish (sv), Tajik (tg), Tamil (ta), Telugu (te), Thai (th), Turkish (tr), Ukrainian (uk), Umbundu (umb), Urdu (ur), Uzbek (uz), Vietnamese (vi), Welsh (cy), Wolof (wo), Xhosa (xh), Yoruba (yo), Zulu (zu)
|