JeongwonChoi's picture
Update README.md
91c4b18 verified
|
raw
history blame
3.59 kB
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

Our Team

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

Model Details

Base Model

megastudy/M-SOLAR-10.7B-v1.3

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 μ‚¬λžŒλ“€μ΄ 정보λ₯Ό 찾을 수 μžˆλ„λ‘ λ„μ™€μ£ΌλŠ” 인곡지λŠ₯ λΉ„μ„œμž…λ‹ˆλ‹€.

### User:
λŒ€ν•œλ―Όκ΅­μ˜ μˆ˜λ„λŠ” μ–΄λ””μ•Ό?

### Assistant:
λŒ€ν•œλ―Όκ΅­μ˜ μˆ˜λ„λŠ” μ„œμšΈμž…λ‹ˆλ‹€.

### User:
μ„œμšΈ μΈκ΅¬λŠ” 총 λͺ‡ λͺ…이야?
"""

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

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-v1.8")
tokenizer = AutoTokenizer.from_pretrained("Edentns/DataVortexS-10.7B-dpo-v1.8")

messages = [
    {"role": "system", "content": "당신은 μ‚¬λžŒλ“€μ΄ 정보λ₯Ό 찾을 수 μžˆλ„λ‘ λ„μ™€μ£ΌλŠ” 인곡지λŠ₯ λΉ„μ„œμž…λ‹ˆλ‹€."},
    {"role": "user", "content": "λŒ€ν•œλ―Όκ΅­μ˜ μˆ˜λ„λŠ” μ–΄λ””μ•Ό?"},
    {"role": "assistant", "content": "λŒ€ν•œλ―Όκ΅­μ˜ μˆ˜λ„λŠ” μ„œμšΈμž…λ‹ˆλ‹€."},
    {"role": "user", "content": "μ„œμšΈ μΈκ΅¬λŠ” 총 λͺ‡ λͺ…이야?"}
]

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.