yhavinga commited on
Commit
74babbc
1 Parent(s): b75b9a2

Update model card

Browse files
Files changed (1) hide show
  1. README.md +19 -7
README.md CHANGED
@@ -1,8 +1,10 @@
1
  ---
2
  language: nl
3
  widget:
4
- - text: "Een zalig kerstfeest en "
5
- - text: "Na een lange reeks vertragingen zal eind volgende week de James Webb Space Telescope (JWST) de aarde verlaten. Met een vergulde spiegel van "
 
 
6
  tags:
7
  - gpt2-medium
8
  - gpt2
@@ -12,13 +14,23 @@ datasets:
12
  ---
13
  # GPT2-Medium pre-trained on cleaned Dutch mC4 🇳🇱
14
 
 
 
 
 
 
 
 
 
 
 
15
  Training details:
16
 
17
- * trained for 240k steps (29 dec 2021)
18
- * block size: 512
19
- * optimizer: adam, lr 8e-4, beta1 0.9, beta2 0.98
20
- * warmup 5000 steps
21
- * weight decay 0.01
22
 
23
  Work in progress. Dec 2021.
24
 
 
1
  ---
2
  language: nl
3
  widget:
4
+ - text: "In het jaar 2030 zullen we"
5
+ - text: "Toen ik gisteren volledig in de ban was van"
6
+ - text: "Studenten en leraren van de Bogazici Universiteit in de Turkse stad Istanbul"
7
+ - text: "In Israël was een strenge lockdown"
8
  tags:
9
  - gpt2-medium
10
  - gpt2
 
14
  ---
15
  # GPT2-Medium pre-trained on cleaned Dutch mC4 🇳🇱
16
 
17
+ Dataset:
18
+
19
+ * [mC4 NL Cleaned](https://huggingface.co/datasets/yhavinga/mc4_nl_cleaned)
20
+ * dataset split: full (33B tokens)
21
+
22
+ Tokenizer:
23
+
24
+ * New tokenizer trained on mC4 with the scripts from the Huggingface
25
+ Transformers [Flax examples](https://github.com/huggingface/transformers/tree/master/examples/flax/language-modeling)
26
+
27
  Training details:
28
 
29
+ * Trained for 240k steps (29 dec 2021)
30
+ * Block size: 512
31
+ * Optimizer: adam, lr 8e-4, beta1 0.9, beta2 0.98
32
+ * Warmup steps: 5000
33
+ * Weight decay: 0.01
34
 
35
  Work in progress. Dec 2021.
36