Hugging Face's logo

sultan
/
ArabicT5-17GB-small

Text2Text Generation
Transformers
PyTorch
t5
text-generation-inference
Inference Endpoints
Model card Files Community
3
sultan commited on
Commit
f772556
•
1 Parent(s): 0d6a90a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -12,7 +12,7 @@ This model adapt T5 on Arabic Language by pre-training T5 on ArabicWikipedia, Ma
12
  | AraT5-Base | 768 | 12 | 12 | 110K |TPUv3-8 | 1M | 128 | 1.0x |248GB 29B tokens (MSA + Tweets) | 69.16/82.82 |
13
  | AraT5-Base-MSA | 768 | 12 | 12 | 110K |TPUv3-8 | 1M | 128 | 1.0x |70GB (MSA) | 68.51/82.66 |
14
  | AraT5-Base-Tweets| 768 | 12 | 12 | 110K |TPUv3-8 | 1M | 128 | 1.0x |178GB (Tweets) | 64.39/78.22 |
15
- | mT5-Base | 768 | 12 | 12 | 250K |TPUv3-32 | 1M | 1024 | 8.0x |6.3T tokens (mC4)| 71.55/83.78 |
16
  | **ArabicT5-Base** | **512** | **8** | **20** | **32K** |**TPUv3-32** | **256K** | **256** | **0.5x** |**17GB (MSA)** | **72.75/85.49** |
17
  | ArabicT5-Large | 768 | 12 | 16 | 32K |TPUv3-128 | 500K | 512 | 2.0x |17GB (MSA) | 74.27/86.37 |
18
  | ArabicT5-xLarge | 768 | 12 | 36 | 32K |TPUv3-128 | 500K | 512 | 2.0x |17GB (MSA) | 74.38/86.60 |
 
12
  | AraT5-Base | 768 | 12 | 12 | 110K |TPUv3-8 | 1M | 128 | 1.0x |248GB 29B tokens (MSA + Tweets) | 69.16/82.82 |
13
  | AraT5-Base-MSA | 768 | 12 | 12 | 110K |TPUv3-8 | 1M | 128 | 1.0x |70GB (MSA) | 68.51/82.66 |
14
  | AraT5-Base-Tweets| 768 | 12 | 12 | 110K |TPUv3-8 | 1M | 128 | 1.0x |178GB (Tweets) | 64.39/78.22 |
15
+ | mT5-Base | 768 | 12 | 12 | 250K |TPUv3-32 | 1M | 1024 | 8.0x |6.3T tokens (mC4)| 72.53/85.04 |
16
  | **ArabicT5-Base** | **512** | **8** | **20** | **32K** |**TPUv3-32** | **256K** | **256** | **0.5x** |**17GB (MSA)** | **72.75/85.49** |
17
  | ArabicT5-Large | 768 | 12 | 16 | 32K |TPUv3-128 | 500K | 512 | 2.0x |17GB (MSA) | 74.27/86.37 |
18
  | ArabicT5-xLarge | 768 | 12 | 36 | 32K |TPUv3-128 | 500K | 512 | 2.0x |17GB (MSA) | 74.38/86.60 |