DataVortexM-7B-Instruct-v0.1
Our Team
| Research & Engineering | Product Management |
|---|---|
| Kwangseok Yang | Seunghyun Choi |
| Jeongwon Choi | Hyoseok Choi |
Model Details
Base Model
mistralai/Mistral-7B-Instruct-v0.2
Trained On
- OS: Ubuntu 20.04
- GPU: H100 80GB 4ea
- transformers: v4.36.2
Dataset
Instruction format
It follows Alpaca format.
E.g.
text = """\
당신은 사람들이 정보를 찾을 수 있도록 도와주는 인공지능 비서입니다.
### Instruction:
대한민국의 수도는 어디야?
### Response:
대한민국의 수도는 서울입니다.
### Instruction:
서울 인구는 총 몇 명이야?
"""
Model Benchmark
Ko LM Eval Harness
On Benchmarking ...
| Task | 0-shot | 5-shot | 10-shot | 50-shot |
|---|---|---|---|---|
| kobest_boolq | 0.0 | 0.0 | 0.0 | 0.0 |
| kobest_copa | 0.0 | 0.0 | 0.0 | 0.0 |
| kobest_hellaswag | 0.0 | 0.0 | 0.0 | 0.0 |
| kobest_sentineg | 0.0 | 0.0 | 0.0 | 0.0 |
Ko-LLM-Leaderboard
| Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
|---|---|---|---|---|---|
| 39.81 | 34.13 | 42.35 | 38.73 | 45.46 | 38.37 |
Implementation Code
This model contains the chat_template instruction format.
You can use the code below.
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained("Edentns/DataVortexM-7B-Instruct-v0.1")
tokenizer = AutoTokenizer.from_pretrained("Edentns/DataVortexM-7B-Instruct-v0.1")
messages = [
{"role": "system", "content": "당신은 사람들이 정보를 찾을 수 있도록 도와주는 인공지능 비서입니다."},
{"role": "user", "content": "대한민국의 수도는 어디야?"},
{"role": "assistant", "content": "대한민국의 수도는 서울입니다."},
{"role": "user", "content": "서울 인구는 총 몇 명이야?"}
]
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])
License
The model is licensed under the cc-by-nc-sa-4.0 license, which allows others to copy, modify, and share the work non-commercially, as long as they give appropriate credit and distribute any derivative works under the same license.