Update README.md
Browse files
README.md
CHANGED
|
@@ -1,15 +1,33 @@
|
|
| 1 |
---
|
|
|
|
| 2 |
datasets:
|
| 3 |
- Mykes/rus_med_dialogues
|
| 4 |
language:
|
| 5 |
- ru
|
|
|
|
| 6 |
pipeline_tag: question-answering
|
| 7 |
tags:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
- biology
|
| 9 |
- chemistry
|
| 10 |
- medical
|
| 11 |
---
|
| 12 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
## Supervised Fine-tuning of gemma-7b
|
| 14 |
I used unsloth lib, unsloth/gemma-7b-bnb-4bit, rus_med_dialogues dataset
|
| 15 |
10 epochs, 2560 training steps on 1 x RTX 4090
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: unsloth/gemma-7b-bnb-4bit
|
| 3 |
datasets:
|
| 4 |
- Mykes/rus_med_dialogues
|
| 5 |
language:
|
| 6 |
- ru
|
| 7 |
+
license: apache-2.0
|
| 8 |
pipeline_tag: question-answering
|
| 9 |
tags:
|
| 10 |
+
- text-generation-inference
|
| 11 |
+
- transformers
|
| 12 |
+
- unsloth
|
| 13 |
+
- gemma
|
| 14 |
+
- trl
|
| 15 |
+
- sft
|
| 16 |
- biology
|
| 17 |
- chemistry
|
| 18 |
- medical
|
| 19 |
---
|
| 20 |
|
| 21 |
+
# Uploaded model
|
| 22 |
+
|
| 23 |
+
- **Developed by:** Mykes
|
| 24 |
+
- **License:** apache-2.0
|
| 25 |
+
- **Finetuned from model :** unsloth/gemma-7b-bnb-4bit
|
| 26 |
+
|
| 27 |
+
This gemma model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
| 28 |
+
|
| 29 |
+
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
| 30 |
+
|
| 31 |
## Supervised Fine-tuning of gemma-7b
|
| 32 |
I used unsloth lib, unsloth/gemma-7b-bnb-4bit, rus_med_dialogues dataset
|
| 33 |
10 epochs, 2560 training steps on 1 x RTX 4090
|