Synatra-7B-Instruct-v0.2
Made by StableFluffy
Contact (Do not Contact for personal things.) Discord : is.maywell Telegram : AlzarTakkarsen
License
This model is strictly non-commercial (cc-by-nc-4.0) use only. 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-nc-4.0 license in any parent repository, and the non-commercial use statute remains, regardless of other models' licences. The licence can be changed after new model released. If you are to use this model for commercial purpose, Contact me.
Model Details
Base Model
mistralai/Mistral-7B-Instruct-v0.1
Trained On
A6000 48GB * 8
TODO
- RP 기반 튜닝 모델 제작
- 데이터셋 정제
- 언어 이해능력 개선
- 상식 보완
- 토크나이저 변경
Instruction format
In order to leverage instruction fine-tuning, your prompt should be surrounded by [INST] and [/INST] tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id.
E.g.
text = "<s>[INST] 아이작 뉴턴의 업적을 알려줘. [/INST]"
Model Benchmark
Ko-LLM-Leaderboard
| Model | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 | Avg |
|---|---|---|---|---|---|---|
| kyujinpy/KoT-platypus2-13B(No.1 at 2023/10/12) | 43.69 | 53.05 | 42.29 | 43.34 | 65.38 | 49.55 |
| Synatra-V0.1-7B-Instruct | 41.72 | 49.28 | 43.27 | 43.75 | 39.32 | 43.47 |
| Synatra-7B-Instruct-v0.2 | 41.81 | 49.35 | 43.99 | 45.77 | 42.96 | 44.78 |
MMLU에서는 우세하나 Ko-CommonGen V2 에서 크게 약한 모습을 보임.
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-V0.1-7B")
tokenizer = AutoTokenizer.from_pretrained("maywell/Synatra-V0.1-7B")
messages = [
{"role": "user", "content": "What is your favourite condiment?"},
]
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])
If you run it on oobabooga your prompt would look like this.
[INST] 링컨에 대해서 알려줘. [/INST]
Readme format: beomi/llama-2-ko-7b