IHaBiS/Synatra-7B-v0.3-dpo-exl2

Exl2 version of maywell/Synatra-7B-v0.3-dpo

branch

main : 8bpw h8
b6h8 : 6bpw h8
b4h8 : 4bpw h8

below this line is original readme

Synatra-7B-v0.3-dpo🐧

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

License

This model is strictly non-commercial (cc-by-sa-4.0) use, Under 5K MAU The "Model" is completely free (ie. base model, derivates, merges/mixes) to use for non-commercial purposes as long as the the included cc-by-sa-4.0 license in any parent repository, and the non-commercial use statute remains, regardless of other models' licences. If your service has over 5K MAU contact me for license approval.

Model Details

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

Trained On
A100 80GB * 1

Instruction format

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

Model Benchmark

KOBEST_BOOLQ, SENTINEG, WIC - ZERO_SHOT

EleutherAI/lm-evaluation-harness를 사용하여 BoolQ, SentiNeg, Wic을 측정했습니다.

Model	COPA	HellaSwag	BoolQ	SentiNeg
EleutherAI/polyglot-ko-12.8b	0.7937	0.5954	0.4818	0.9117
Synatra-7B-v0.3-base	0.6344	0.5140	0.5226	NaN
Synatra-7B-v0.3-dpo	0.6380	0.4780	0.8058	0.8942

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-dpo")
tokenizer = AutoTokenizer.from_pretrained("maywell/Synatra-7B-v0.3-dpo")

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])