77 lines
2.1 KiB
Markdown
77 lines
2.1 KiB
Markdown
---
|
|
license: cc-by-sa-4.0
|
|
---
|
|
|
|
# **Synatra-7B-v0.3-Translation🐧**
|
|
|
|
|
|
## Support Me
|
|
시나트라는 개인 프로젝트로, 1인의 자원으로 개발되고 있습니다. 모델이 마음에 드셨다면 약간의 연구비 지원은 어떨까요?
|
|
[<img src="https://cdn.buymeacoffee.com/buttons/default-orange.png" alt="Buy me a Coffee" width="217" height="50">](https://www.buymeacoffee.com/mwell)
|
|
|
|
Wanna be a sponser? (Please) Contact me on Telegram **AlzarTakkarsen**
|
|
|
|
# **Model Details**
|
|
**Base Model**
|
|
[mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1)
|
|
|
|
**Datasets**
|
|
[sharegpt_deepl_ko_translation](https://huggingface.co/datasets/squarelike/sharegpt_deepl_ko_translation)
|
|
|
|
Filtered version of above dataset included.
|
|
|
|
**Trained On**
|
|
A100 80GB * 1
|
|
|
|
**Instruction format**
|
|
|
|
It follows [ChatML](https://github.com/openai/openai-python/blob/main/chatml.md) format and **Alpaca(No-Input)** format.
|
|
|
|
```python
|
|
<|im_start|>system
|
|
주어진 문장을 한국어로 번역해라.<|im_end|>
|
|
<|im_start|>user
|
|
{instruction}<|im_end|>
|
|
<|im_start|>assistant
|
|
|
|
```
|
|
```python
|
|
<|im_start|>system
|
|
주어진 문장을 영어로 번역해라.<|im_end|>
|
|
<|im_start|>user
|
|
{instruction}<|im_end|>
|
|
<|im_start|>assistant
|
|
|
|
```
|
|
|
|
|
|
## Ko-LLM-Leaderboard
|
|
|
|
On Benchmarking...
|
|
|
|
# **Implementation Code**
|
|
|
|
Since, chat_template already contains insturction format above.
|
|
You can use the code below.
|
|
|
|
```python
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
|
|
device = "cuda" # the device to load the model onto
|
|
|
|
model = AutoModelForCausalLM.from_pretrained("maywell/Synatra-7B-v0.3-Translation")
|
|
tokenizer = AutoTokenizer.from_pretrained("maywell/Synatra-7B-v0.3-Translation")
|
|
|
|
messages = [
|
|
{"role": "user", "content": "바나나는 원래 하얀색이야?"},
|
|
]
|
|
|
|
encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
|
|
|
|
model_inputs = encodeds.to(device)
|
|
model.to(device)
|
|
|
|
generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
|
|
decoded = tokenizer.batch_decode(generated_ids)
|
|
print(decoded[0])
|
|
``` |