README.md

metadata

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?

Wanna be a sponser? (Please) Contact me on Telegram AlzarTakkarsen

Model Details

Base Model
mistralai/Mistral-7B-Instruct-v0.1

Datasets sharegpt_deepl_ko_translation

Filtered version of above dataset included.

Trained On
A100 80GB * 1

Instruction format

It follows ChatML format and Alpaca(No-Input) format.

<|im_start|>system
주어진 문장을 한국어로 번역해라.<|im_end|>
<|im_start|>user
{instruction}<|im_end|>
<|im_start|>assistant

<|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.

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])