Hugging Face's logo

catherinearnett
/
B-GPT_en_pl_sequential

Text Generation
Transformers
Safetensors
English
Polish
gpt2
text-generation-inference
Model card Files Community
catherinearnett commited on
Commit
c8f5d0d
·
verified ·
1 Parent(s): 9a5d482

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +1 -3
README.md CHANGED
@@ -23,14 +23,12 @@ Details for this model specifically:
23
  * Architecture: gpt2
24
  * Parameters: 124770816
25
  * Maximum sequence length: 512 tokens
26
- * Training text data (raw): [XXXX]
27
  * Training tokens: 12B
28
  * Vocabulary size: 50000
29
  * Compute cost: ~9 NVIDIA A6000 GPU hours
30
  * CO2 Emission: 1.17 kg
31
 
32
- Training datasets:
33
- * 100%: [OSCAR 2021/09](https://huggingface.co/datasets/oscar-corpus/OSCAR-2109)
34
 
35
  Checkpoints are taken at training steps: 0, 10000, 20000, 30000, 40000, 50000, 64000, 64010, 64020, 64030, 64040, 64050, 64060, 64070, 64080, 64090, 64100, 64110, 64120, 64130, 64140, 64150, 64160, 64170, 64180, 64190, 64200, 64300, 64400, 64500, 64600, 64700, 64800, 64900, 65000, 66000, 67000, 68000, 69000, 70000, 80000, 90000, 100000, 110000, 120000, 128000.
36
 
 
23
  * Architecture: gpt2
24
  * Parameters: 124770816
25
  * Maximum sequence length: 512 tokens
 
26
  * Training tokens: 12B
27
  * Vocabulary size: 50000
28
  * Compute cost: ~9 NVIDIA A6000 GPU hours
29
  * CO2 Emission: 1.17 kg
30
 
31
+ Training dataset: [OSCAR 2021/09](https://huggingface.co/datasets/oscar-corpus/OSCAR-2109)
 
32
 
33
  Checkpoints are taken at training steps: 0, 10000, 20000, 30000, 40000, 50000, 64000, 64010, 64020, 64030, 64040, 64050, 64060, 64070, 64080, 64090, 64100, 64110, 64120, 64130, 64140, 64150, 64160, 64170, 64180, 64190, 64200, 64300, 64400, 64500, 64600, 64700, 64800, 64900, 65000, 66000, 67000, 68000, 69000, 70000, 80000, 90000, 100000, 110000, 120000, 128000.
34