Downloads · 30 days
5
1% of all-time downloads
gpt2-pretrained-for-coq-pt-custom-train
Andrusyshyn/gpt2-pretrained-for-coq-pt-custom-train
gpt2-pretrained-for-coq-pt-custom-train is a text generation model from Andrusyshyn. Use it when you need the model to write or continue text. It is set up for transformers.
Our trained models are contained by the following branches: - main - contains n12 model - v30a95lrcos8em4 - contains n12 model - v30a95lrcos8em4mod10l10h640e - contains n10 model - v30a95lrcos8em4mod8l8h512e - contain…
All-time downloads
402
Public
Parameters
109M
265 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors436 MB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- gpt2
- Access
- Public
- Created
- Feb 4, 2024
- Updated
- Apr 29, 2024
- SHA
- 2e78acf3
Try a prompt
Model card
From the Hugging Face model README
Our trained models are contained by the following branches:
- main -> contains n12 model
- v30_a95_lrcos8em4 -> contains n12 model
- v30_a95_lrcos8em4_mod10l10h640e -> contains n10 model
- v30_a95_lrcos8em4_mod8l8h512e -> contains n08 model
- v30_a95_lrcos8em4_mod6l6h384e -> contains n06 model
- v30_a95_lrcos8em4_mod4l4h256e -> contains n04 model
- v30_a95_lrcos8em4_mod2l2h128e -> contains n02 model
| Characteristic | n02 | n04 | n06 | n08 | n10 | n12 |
|---|---|---|---|---|---|---|
| number of heads | 2 | 4 | 6 | 8 | 10 | 12 |
| size of embeddings | 128 | 256 | 384 | 512 | 640 | 768 |
| total trainable params | 4,367,872 | 11,101,696 | 22,560,768 | 41,104,384 | 69,091,840 | 108,882,432 |
| non-embedding params | 396,800 | 3,159,552 | 10,647,552 | 25,220,096 | 49,236,480 | 85,056,000 |
- Task
- Text Generation
- Library
- transformers
- Type
- gpt2
- Created
- Feb 4, 2024
- Updated
- Apr 29, 2024