README.md

metadata

tags:
  - text-generation
license: cc-by-nc-4.0
language:
  - ko
base_model: upstage/SOLAR-10.7B-Instruct-v1.0
pipeline_tag: text-generation

DataVortexS-10.7B-dpo-v1.1

Model Details

Base Model

upstage/SOLAR-10.7B-Instruct-v1.0

Trained On

• OS: Ubuntu 22.04
• GPU: H100 80GB 4ea
• transformers: v4.36.2

Instruction format

It follows Alpaca (Chat) format.

E.g.

text = """\
### System:
당신은 사람들이 정보를 찾을 수 있도록 도와주는 인공지능 비서입니다.

### User:
대한민국의 수도는 어디야?

### Assistant:
대한민국의 수도는 서울입니다.

### User:
서울 인구는 총 몇 명이야?
"""

Model Benchmark

Ko LM Eval Harness

Task	0-shot	5-shot	10-shot	50-shot
kobest_boolq	0.375807	0.822623	0.828582	0.822529
kobest_copa	0.539993	0.665979	0.67998	0.694997
kobest_hellaswag	0.405785	0.401975	0.438219	0.402962
kobest_sentineg	0.794083	0.85276	0.883509	0.880932
Average	0.528917	0.68583425	0.7075725	0.700355

Ko-LLM-Leaderboard

On Benchmarking ...

Average	Ko-ARC	Ko-HellaSwag	Ko-MMLU	Ko-TruthfulQA	Ko-CommonGen V2
0	0	0	0	0	0

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/DataVortexS-10.7B-dpo-v1.1")
tokenizer = AutoTokenizer.from_pretrained("Edentns/DataVortexS-10.7B-dpo-v1.1")

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

This model is licensed under the upstage/SOLAR-10.7B-Instruct-v1.0 license, with the cc-by-nc-4.0 license granted. Under this license, others are allowed to copy, modify, and share the work, as long as it is not used for commercial purposes. They must provide appropriate credit and distribute any derivative works under the same license. For more details, please refer to the cc-by-nc-4.0 license.