Update README.md
Browse files
README.md
CHANGED
|
@@ -29,7 +29,8 @@ The fine-tuning process utilized the [Continued Pretraining](https://docs.unslot
|
|
| 29 |
- **Base Model**: [Gemma2-2b-it](https://huggingface.co/google/gemma-2b-it)
|
| 30 |
- **Languages Supported**: English and Russian
|
| 31 |
- **Training Method**: [Continued Pretraining](https://docs.unsloth.ai/basics/continued-pretraining)
|
| 32 |
-
- **Epochs**: 10
|
|
|
|
| 33 |
**License:** This model is distributed under the [Gemma Terms of Use](https://ai.google.dev/gemma/terms)
|
| 34 |
### Quantization Options
|
| 35 |
|
|
@@ -195,7 +196,8 @@ For issues, questions, or suggestions, feel free to open an issue in the reposit
|
|
| 195 |
- **Базовая модель**: [Gemma2-2b-it](https://huggingface.co/google/gemma-2b-it)
|
| 196 |
- **Поддерживаемые языки**: Русский и английский
|
| 197 |
- **Метод обучения**: [Continued Pretraining](https://docs.unsloth.ai/basics/continued-pretraining)
|
| 198 |
-
- **Количество эпох**: 10
|
|
|
|
| 199 |
**Лицензия:** Модель распространяетчя по лицензии Google [Gemma Terms of Use](https://ai.google.dev/gemma/terms)
|
| 200 |
### Варианты квантизации
|
| 201 |
|
|
|
|
| 29 |
- **Base Model**: [Gemma2-2b-it](https://huggingface.co/google/gemma-2b-it)
|
| 30 |
- **Languages Supported**: English and Russian
|
| 31 |
- **Training Method**: [Continued Pretraining](https://docs.unsloth.ai/basics/continued-pretraining)
|
| 32 |
+
- **Epochs**: 10
|
| 33 |
+
- **Resources**: 1 RTX A5000 24Gb vRAM for approximately 3 days. The cost of finetuning is about $54.
|
| 34 |
**License:** This model is distributed under the [Gemma Terms of Use](https://ai.google.dev/gemma/terms)
|
| 35 |
### Quantization Options
|
| 36 |
|
|
|
|
| 196 |
- **Базовая модель**: [Gemma2-2b-it](https://huggingface.co/google/gemma-2b-it)
|
| 197 |
- **Поддерживаемые языки**: Русский и английский
|
| 198 |
- **Метод обучения**: [Continued Pretraining](https://docs.unsloth.ai/basics/continued-pretraining)
|
| 199 |
+
- **Количество эпох**: 10
|
| 200 |
+
- **Оборужование**: 1 RTX A5000 24Gb vRAM приблизительно в течение 3-х дней. Общие затраты на файнтюнинг около $54.
|
| 201 |
**Лицензия:** Модель распространяетчя по лицензии Google [Gemma Terms of Use](https://ai.google.dev/gemma/terms)
|
| 202 |
### Варианты квантизации
|
| 203 |
|