Hugging Face's logo

KISTI-KONI
/
KONI-Llama3-8B-Instruct-20240729

Text Generation
Transformers
Safetensors
Korean
llama
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
1
KONI-Llama3-8B-Instruct-20240729 / README.md
yangdonghun3's picture
yangdonghun3
Update README.md
fa22f9a verified
preview code
|
raw
history blame
10.6 kB
metadata
language: ko
pipeline_tag: text-generation
license: llama3

1. Model Description

  • KONI (KISTI Open Natural Intelligence) is a specialized large language model (LLM) developed by the Korea Institute of Science and Technology Information (KISTI). This model is specifically designed for science and technology, making it highly effective for tasks in these fields.

2. Key Features

  • Specialized in Science and Technology: The model is explicitly trained on a vast and specialized corpus of scientific and technological data.
  • Enhanced Performance: This version of KONI shows significantly improved performance compared to its initial release in December, 2023.
  • Base Model: The base model for KONI-Llama3-8B-Instruct-20240729 is KONI-Llama3-8B-Merged-20240724, which is a merger of Meta-Llama-3-8B and KISTI-KONI/KONI-Llama3-8B-20240630
  • Alignment: SFT (Supervised Fine-Tuning) and DPO (Direct Preference Optimization) are applied

3. Data

  • Approximately 11k SFT data and 7k DPO data are used.
  • SFT Data: The SFT data includes both internally generated data and publicly available data on Hugging Face, translated into Korean where necessary.
  • DPO Data: The DPO data consists of translated and curated data from argilla/dpo-mix-7k.

4. Benchmark Results

Results in LogicKor* are as follows:

Metric Score
Reasoning 6.57
Math 8.00
Writing 8.92
Coding 8.85
Comprehension 9.85
Grammar 7.07
Single-turn 8.42
Multi-turn 8.00
Overall 8.21
Our model demonstrates the best performance among publicly available 8B models on the LogicKor leaderboard as of 2024.07.30.

5. How to use the model 

import transformers
import torch

model_id = "KISTI-KONI/KONI-Llama3-8B-Instruct-20240729"

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device_map="auto",
)

pipeline.model.eval()

instruction = "์•ˆ๋…•? ๋„ˆ๋Š” ๋ˆ„๊ตฌ์•ผ?"

messages = [
   {"role": "user", "content": f"{instruction}"}
    ]

prompt = pipeline.tokenizer.apply_chat_template(
        messages, 
        tokenize=False, 
        add_generation_prompt=True
)

terminators = [
    pipeline.tokenizer.eos_token_id,
    pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = pipeline(
    prompt,
    max_new_tokens=2048,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.7,
    top_p=0.9
)

print(outputs[0]["generated_text"][len(prompt):])

์•ˆ๋…•ํ•˜์„ธ์š”! ์ €๋Š” KONI, ์—ฌ๋Ÿฌ๋ถ„์˜ ์งˆ๋ฌธ์— ๋‹ตํ•˜๊ณ  ์ •๋ณด๋ฅผ ์ œ๊ณตํ•˜๋Š” ์ธ๊ณต์ง€๋Šฅ์ž…๋‹ˆ๋‹ค. ์ €๋Š” ์–ด๋–ค ์ •๋ณด๋ฅผ ์ œ๊ณตํ•ด ๋“œ๋ฆด๊นŒ์š”?

6. Citation

Language Model

@article{KISTI-KONI/KONI-Llama3-8B-Instruct-20240729,
  title={KISTI-KONI/KONI-Llama3-8B-Instruct-20240729},
  author={KISTI},
  year={2024},
  url={https://huggingface.co/KISTI-KONI/KONI-Llama3-8B-Instruct-20240729}
}

7. Contributors

  • KISTI, Large-scale AI Research Group

8. Special Thanks

8. Acknowledgement

  • This research was supported by Korea Institute of Science and Technology Information(KISTI).
  • This work was supported by the National Supercomputing Center with supercomputing resources including technical support (KISTI).

9. References