DataVortexS-10.7B-dpo-v1.7

DataVortex

Our Team

Research & Engineering Product Management
Kwangseok Yang Seunghyun Choi
Jeongwon Choi Hyoseok Choi

Model Details

Base Model

beomi/OPEN-SOLAR-KO-10.7B

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:
๋‹น์‹ ์€ ์‚ฌ๋žŒ๋“ค์ด ์ •๋ณด๋ฅผ ์ฐพ์„ ์ˆ˜ ์žˆ๋„๋ก ๋„์™€์ฃผ๋Š” ์ธ๊ณต์ง€๋Šฅ ๋น„์„œ์ž…๋‹ˆ๋‹ค.

### User:
๋Œ€ํ•œ๋ฏผ๊ตญ์˜ ์ˆ˜๋„๋Š” ์–ด๋””์•ผ?

### Assistant:
๋Œ€ํ•œ๋ฏผ๊ตญ์˜ ์ˆ˜๋„๋Š” ์„œ์šธ์ž…๋‹ˆ๋‹ค.

### User:
์„œ์šธ ์ธ๊ตฌ๋Š” ์ด ๋ช‡ ๋ช…์ด์•ผ?
"""

Model Benchmark

Ko LM Eval Harness

Task 0-shot 5-shot 10-shot 50-shot
kobest_boolq 0.886844 0.917351 0.921621 0.919476
kobest_copa 0.805514 0.856782 0.864773 0.87793
kobest_hellaswag 0.505714 0.512116 0.50608 0.512187
kobest_sentineg 0.357169 0.974811 0.987404 0.979848
Average 0.63881 0.815265 0.81997 0.82236

Ko-LLM-Leaderboard

Average Ko-ARC Ko-HellaSwag Ko-MMLU Ko-TruthfulQA Ko-CommonGen V2
55.81 55.55 63.39 51.57 48.23 60.33

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-v1.7")
tokenizer = AutoTokenizer.from_pretrained("Edentns/DataVortexS-10.7B-dpo-v1.7")

messages = [
    {"role": "system", "content": "๋‹น์‹ ์€ ์‚ฌ๋žŒ๋“ค์ด ์ •๋ณด๋ฅผ ์ฐพ์„ ์ˆ˜ ์žˆ๋„๋ก ๋„์™€์ฃผ๋Š” ์ธ๊ณต์ง€๋Šฅ ๋น„์„œ์ž…๋‹ˆ๋‹ค."},
    {"role": "user", "content": "๋Œ€ํ•œ๋ฏผ๊ตญ์˜ ์ˆ˜๋„๋Š” ์–ด๋””์•ผ?"},
    {"role": "assistant", "content": "๋Œ€ํ•œ๋ฏผ๊ตญ์˜ ์ˆ˜๋„๋Š” ์„œ์šธ์ž…๋‹ˆ๋‹ค."},
    {"role": "user", "content": "์„œ์šธ ์ธ๊ตฌ๋Š” ์ด ๋ช‡ ๋ช…์ด์•ผ?"}
]

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 cc-by-nc-4.0. which allows others to share and adapt the model for non-commercial purposes.

Downloads last month
7
Safetensors
Model size
11B params
Tensor type
F16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for Edentns/DataVortexS-10.7B-dpo-v1.7

Finetuned
(5)
this model
Quantizations
3 models

Space using Edentns/DataVortexS-10.7B-dpo-v1.7 1

Collection including Edentns/DataVortexS-10.7B-dpo-v1.7