Instructions to use dddsaty/SOLAR-Instruct-ko-Adapter-Attach with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dddsaty/SOLAR-Instruct-ko-Adapter-Attach with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="dddsaty/SOLAR-Instruct-ko-Adapter-Attach")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dddsaty/SOLAR-Instruct-ko-Adapter-Attach")
model = AutoModelForCausalLM.from_pretrained("dddsaty/SOLAR-Instruct-ko-Adapter-Attach")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use dddsaty/SOLAR-Instruct-ko-Adapter-Attach with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dddsaty/SOLAR-Instruct-ko-Adapter-Attach"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dddsaty/SOLAR-Instruct-ko-Adapter-Attach",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dddsaty/SOLAR-Instruct-ko-Adapter-Attach

SGLang

How to use dddsaty/SOLAR-Instruct-ko-Adapter-Attach with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "dddsaty/SOLAR-Instruct-ko-Adapter-Attach" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dddsaty/SOLAR-Instruct-ko-Adapter-Attach",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "dddsaty/SOLAR-Instruct-ko-Adapter-Attach" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dddsaty/SOLAR-Instruct-ko-Adapter-Attach",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dddsaty/SOLAR-Instruct-ko-Adapter-Attach with Docker Model Runner:
```
docker model run hf.co/dddsaty/SOLAR-Instruct-ko-Adapter-Attach
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Explanation

With the base model, attached the saved DPO applied adapter

Base Model

upstage/SOLAR-10.7B-Instruct-v1.0

Adapter Base Model

beomi/OPEN-SOLAR-KO-10.7B

Adapter Used Corpus

maywell/ko_Ultrafeedback_binarized

Score

Average	ARC	HellaSwag	MMLU	TruthfulQA	Winogrande	GSM8K
74.11	71.08	88.2	66.09	71.51	83.5	64.29

Log

2024.01.29: Initial version Upload
2024.02.10: Readme update

LICENSE
Following the upstage/SOLAR-10.7B-Instruct-v1.0 License

cc-by-nc-4.0

Citation

beomi/OPEN-SOLAR-KO-10.7B

@misc {solar_ko_junbum_2023,
    author       = { {L. Junbum} },
    title        = { Solar-Ko-10.7b },
    year         = 2024,
    url          = { https://huggingface.co/beomi/SOLAR-KO-10.7B },
    publisher    = { Hugging Face }
}

upstage/SOLAR-10.7B-Instruct-v1.0

@misc{kim2023solar,
      title={SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling}, 
      author={Dahyun Kim and Chanjun Park and Sanghoon Kim and Wonsung Lee and Wonho Song and Yunsu Kim and Hyeonwoo Kim and Yungi Kim and Hyeonju Lee and Jihoo Kim and Changbae Ahn and Seonghoon Yang and Sukyung Lee and Hyunbyung Park and Gyoungjin Gim and Mikyoung Cha and Hwalsuk Lee and Sunghun Kim},
      year={2023},
      eprint={2312.15166},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

Downloads last month: 85

Safetensors

Model size

11B params

Tensor type

F16

Model tree for dddsaty/SOLAR-Instruct-ko-Adapter-Attach

Quantizations

1 model

Spaces using dddsaty/SOLAR-Instruct-ko-Adapter-Attach 9

Paper for dddsaty/SOLAR-Instruct-ko-Adapter-Attach

SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling

Paper • 2312.15166 • Published Dec 23, 2023 • 61