Update README.md
Browse files
README.md
CHANGED
|
@@ -3,4 +3,6 @@ license: apache-2.0
|
|
| 3 |
---
|
| 4 |
openllama_v2 3B second stage pre-trained on russian part of OSCAR with 4k sequence length. Model has seen about 5B tokens for now, weights will be updated as the training goes on.
|
| 5 |
Achieves 3.8 perplexity on the evaluation dataset. Will we further pre-trained on wiki dataset with 16K context length.
|
| 6 |
-
Free inference works, feel free to experiement in Russian :). Should be the natural continuation of the prompt
|
|
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
openllama_v2 3B second stage pre-trained on russian part of OSCAR with 4k sequence length. Model has seen about 5B tokens for now, weights will be updated as the training goes on.
|
| 5 |
Achieves 3.8 perplexity on the evaluation dataset. Will we further pre-trained on wiki dataset with 16K context length.
|
| 6 |
+
Free inference works, feel free to experiement in Russian :). Should be the natural continuation of the prompt. Example:
|
| 7 |
+
Prompt: "Собака пришла домой и начала вопрошать", output: "... что делать.
|
| 8 |
+
Подруга хозяина сказала, что нужно сделать, чтобы понять, как правильно поступить."
|