Quantization made by Richard Erkhov.

DataVortexS-10.7B-dpo-v1.0 - GGUF

Model creator: https://huggingface.co/Edentns/
Original model: https://huggingface.co/Edentns/DataVortexS-10.7B-dpo-v1.0/

Name	Quant method	Size
DataVortexS-10.7B-dpo-v1.0.Q2_K.gguf	Q2_K	3.73GB
DataVortexS-10.7B-dpo-v1.0.IQ3_XS.gguf	IQ3_XS	4.14GB
DataVortexS-10.7B-dpo-v1.0.IQ3_S.gguf	IQ3_S	4.37GB
DataVortexS-10.7B-dpo-v1.0.Q3_K_S.gguf	Q3_K_S	4.34GB
DataVortexS-10.7B-dpo-v1.0.IQ3_M.gguf	IQ3_M	4.51GB
DataVortexS-10.7B-dpo-v1.0.Q3_K.gguf	Q3_K	4.84GB
DataVortexS-10.7B-dpo-v1.0.Q3_K_M.gguf	Q3_K_M	4.84GB
DataVortexS-10.7B-dpo-v1.0.Q3_K_L.gguf	Q3_K_L	5.26GB
DataVortexS-10.7B-dpo-v1.0.IQ4_XS.gguf	IQ4_XS	5.43GB
DataVortexS-10.7B-dpo-v1.0.Q4_0.gguf	Q4_0	5.66GB
DataVortexS-10.7B-dpo-v1.0.IQ4_NL.gguf	IQ4_NL	5.72GB
DataVortexS-10.7B-dpo-v1.0.Q4_K_S.gguf	Q4_K_S	5.7GB
DataVortexS-10.7B-dpo-v1.0.Q4_K.gguf	Q4_K	6.02GB
DataVortexS-10.7B-dpo-v1.0.Q4_K_M.gguf	Q4_K_M	6.02GB
DataVortexS-10.7B-dpo-v1.0.Q4_1.gguf	Q4_1	6.27GB
DataVortexS-10.7B-dpo-v1.0.Q5_0.gguf	Q5_0	6.89GB
DataVortexS-10.7B-dpo-v1.0.Q5_K_S.gguf	Q5_K_S	6.89GB
DataVortexS-10.7B-dpo-v1.0.Q5_K.gguf	Q5_K	7.08GB
DataVortexS-10.7B-dpo-v1.0.Q5_K_M.gguf	Q5_K_M	7.08GB
DataVortexS-10.7B-dpo-v1.0.Q5_1.gguf	Q5_1	7.51GB
DataVortexS-10.7B-dpo-v1.0.Q6_K.gguf	Q6_K	8.2GB
DataVortexS-10.7B-dpo-v1.0.Q8_0.gguf	Q8_0	10.62GB

Original model description:

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-v1.0

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 사람들이 정보를 찾을 수 있도록 도와주는 인공지능 비서입니다.

### User:
대한민국의 수도는 어디야?

### Assistant:
대한민국의 수도는 서울입니다.

### User:
서울 인구는 총 몇 명이야?
"""

Model Benchmark

Ko LM Eval Harness

Task	0-shot	5-shot	10-shot	50-shot
kobest_boolq	0.867265	0.930834	0.938736	0.938023
kobest_copa	0.722438	0.792716	0.782842	0.805869
kobest_hellaswag	0.484781	0.480055	0.496734	0.501488
kobest_sentineg	0.759887	0.964735	0.964735	0.972291
Average	0.70859275	0.792085	0.79576175	0.80441775

Ko-LLM-Leaderboard

Average	Ko-ARC	Ko-HellaSwag	Ko-MMLU	Ko-TruthfulQA	Ko-CommonGen V2
57.92	56.91	65.81	53.81	58.77	54.31

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-v1.0")
tokenizer = AutoTokenizer.from_pretrained("Edentns/DataVortexS-10.7B-dpo-v1.0")

messages = [
    {"role": "system", "content": "당신은 사람들이 정보를 찾을 수 있도록 도와주는 인공지능 비서입니다."},
    {"role": "user", "content": "대한민국의 수도는 어디야?"},
    {"role": "assistant", "content": "대한민국의 수도는 서울입니다."},
    {"role": "user", "content": "서울 인구는 총 몇 명이야?"}
]

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.