metadata
tags:
- text-generation
license: cc-by-nc-sa-4.0
language:
- ko
base_model: megastudy/M-SOLAR-10.7B-v1.3
pipeline_tag: text-generation
DataVortexS-10.7B-dpo-v1.8
![DataVortex](/Edentns/DataVortexS-10.7B-dpo-v1.8/resolve/main/DataVortex.png)
Our Team
Research & Engineering | Product Management |
---|---|
Kwangseok Yang | Seunghyun Choi |
Jeongwon Choi | Hyoseok Choi |
Model Details
Base Model
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:
λΉμ μ μ¬λλ€μ΄ μ 보λ₯Ό μ°Ύμ μ μλλ‘ λμμ£Όλ μΈκ³΅μ§λ₯ λΉμμ
λλ€.
### User:
λνλ―Όκ΅μ μλλ μ΄λμΌ?
### Assistant:
λνλ―Όκ΅μ μλλ μμΈμ
λλ€.
### User:
μμΈ μΈκ΅¬λ μ΄ λͺ λͺ
μ΄μΌ?
"""
Model Benchmark
Ko LM Eval Harness
Task | 0-shot | 5-shot | 10-shot | 50-shot |
---|---|---|---|---|
kobest_boolq | 0.903441 | 0.922987 | 0.919466 | 0.923032 |
kobest_copa | 0.734711 | 0.778697 | 0.773796 | 0.796829 |
kobest_hellaswag | 0.473673 | 0.480091 | 0.491471 | 0.488234 |
kobest_sentineg | 0.536605 | 0.93185 | 0.952136 | 0.949596 |
Average | 0.662107 | 0.778406 | 0.784217 | 0.789423 |
Ko-LLM-Leaderboard
Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
---|---|---|---|---|---|
58.15 | 52.56 | 66.68 | 51.21 | 59.27 | 61.04 |
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-v1.8")
tokenizer = AutoTokenizer.from_pretrained("Edentns/DataVortexS-10.7B-dpo-v1.8")
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])
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.