DataVortex Models
Collection
21 items
β’
Updated
Research & Engineering | Product Management |
---|---|
Kwangseok Yang | Seunghyun Choi |
Jeongwon Choi | Hyoseok Choi |
It follows ChatML format.
E.g.
text = """\
<|im_start|>system
λΉμ μ μ¬λλ€μ΄ μ 보λ₯Ό μ°Ύμ μ μλλ‘ λμμ£Όλ μΈκ³΅μ§λ₯ λΉμμ
λλ€.<|im_end|>
<|im_start|>user
λνλ―Όκ΅μ μλλ μ΄λμΌ?<|im_end|>
<|im_start|>assistant
λνλ―Όκ΅μ μλλ μμΈμ
λλ€.<|im_end|>
<|im_start|>user
μμΈ μΈκ΅¬λ μ΄ λͺ λͺ
μ΄μΌ?<|im_end|>
<|im_start|>assistant
"""
Task | 0-shot | 5-shot | 10-shot | 50-shot |
---|---|---|---|---|
kobest_boolq | 0.91154 | 0.927338 | 0.92373 | 0.653224 |
kobest_copa | 0.747317 | 0.826961 | 0.842943 | 0.860989 |
kobest_hellaswag | 0.445855 | 0.459065 | 0.462306 | 0.4721 |
kobest_sentineg | 0.483219 | 0.95466 | 0.964734 | 0.972292 |
Average | 0.646983 | 0.792006 | 0.798428 | 0.739651 |
Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
---|---|---|---|---|---|
57.65 | 52.99 | 64.8 | 54.86 | 53.87 | 61.75 |
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-v1.3")
tokenizer = AutoTokenizer.from_pretrained("Edentns/DataVortexS-10.7B-dpo-v1.3")
messages = [
{"role": "system", "content": "λΉμ μ μ¬λλ€μ΄ μ 보λ₯Ό μ°Ύμ μ μλλ‘ λμμ£Όλ μΈκ³΅μ§λ₯ λΉμμ
λλ€."},
{"role": "user", "content": "λνλ―Όκ΅μ μλλ μ΄λμΌ?"},
{"role": "assistant", "content": "λνλ―Όκ΅μ μλλ μμΈμ
λλ€."},
{"role": "user", "content": "μμΈ μΈκ΅¬λ μ΄ λͺ λͺ
μ΄μΌ?"}
]
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])
This model is licensed under the cc-by-nc-4.0. which allows others to share and adapt the model for non-commercial purposes.