Update README.md
Browse files
README.md
CHANGED
@@ -9,10 +9,13 @@ pipeline_tag: text-generation
|
|
9 |
|
10 |
<!-- Provide a quick summary of what the model is/does. -->
|
11 |
|
12 |
-
This model is pre-trained with the causal language modelling objective on
|
|
|
|
|
13 |
|
14 |
## Model Details
|
15 |
|
|
|
16 |
### Model Description
|
17 |
|
18 |
<!-- Provide a longer summary of what this model is. -->
|
@@ -20,9 +23,9 @@ This model is pre-trained with the causal language modelling objective on the we
|
|
20 |
|
21 |
|
22 |
- **Developed by:** [Iva Marinova](https://huggingface.co/usmiva)
|
23 |
-
- **Shared by [optional]:**
|
24 |
- **Model type:** GPT-2
|
25 |
-
- **Language(s) (NLP):**
|
26 |
- **License:** [More Information Needed]
|
27 |
- **Finetuned from model [optional]:** [More Information Needed]
|
28 |
|
@@ -31,7 +34,7 @@ This model is pre-trained with the causal language modelling objective on the we
|
|
31 |
<!-- Provide the basic links for the model. -->
|
32 |
|
33 |
- **Repository:** [More Information Needed]
|
34 |
-
- **Paper [optional]:**
|
35 |
- **Demo [optional]:** [More Information Needed]
|
36 |
|
37 |
## Uses
|
|
|
9 |
|
10 |
<!-- Provide a quick summary of what the model is/does. -->
|
11 |
|
12 |
+
This model is pre-trained with the causal language modelling objective on a private web scraped dataset created at the Bulgarian Academy of Sciences under the [ClaDa-BG Project](https://clada-bg.eu/en/).
|
13 |
+
|
14 |
+
The dataset is cleaned and balanced with a specialized procedure to avoid cultural, political, racial and other biases. The procedure is described in the paper dedicated to this model- coming soon!
|
15 |
|
16 |
## Model Details
|
17 |
|
18 |
+
|
19 |
### Model Description
|
20 |
|
21 |
<!-- Provide a longer summary of what this model is. -->
|
|
|
23 |
|
24 |
|
25 |
- **Developed by:** [Iva Marinova](https://huggingface.co/usmiva)
|
26 |
+
- **Shared by [optional]:** ClaDa-BG, : National Interdisciplinary Research E-Infrastructure for Bulgarian Language and Cultural Heritage Resources and Technologies integrated within European CLARIN and DARIAH infrastructures
|
27 |
- **Model type:** GPT-2
|
28 |
+
- **Language(s) (NLP):** Bulgarian
|
29 |
- **License:** [More Information Needed]
|
30 |
- **Finetuned from model [optional]:** [More Information Needed]
|
31 |
|
|
|
34 |
<!-- Provide the basic links for the model. -->
|
35 |
|
36 |
- **Repository:** [More Information Needed]
|
37 |
+
- **Paper [optional]:** Marinova et. al. 2023 - link to be added
|
38 |
- **Demo [optional]:** [More Information Needed]
|
39 |
|
40 |
## Uses
|