Instructions to use davidkim205/nox-solar-10.7b-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use davidkim205/nox-solar-10.7b-v2 with Transformers:

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

pipe = pipeline("text-generation", model="davidkim205/nox-solar-10.7b-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("davidkim205/nox-solar-10.7b-v2")
model = AutoModelForCausalLM.from_pretrained("davidkim205/nox-solar-10.7b-v2")
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 davidkim205/nox-solar-10.7b-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "davidkim205/nox-solar-10.7b-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "davidkim205/nox-solar-10.7b-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/davidkim205/nox-solar-10.7b-v2

SGLang

How to use davidkim205/nox-solar-10.7b-v2 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 "davidkim205/nox-solar-10.7b-v2" \
    --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": "davidkim205/nox-solar-10.7b-v2",
		"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 "davidkim205/nox-solar-10.7b-v2" \
        --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": "davidkim205/nox-solar-10.7b-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use davidkim205/nox-solar-10.7b-v2 with Docker Model Runner:
```
docker model run hf.co/davidkim205/nox-solar-10.7b-v2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

nox

The nox project is a set of tools that make it easy to use various fine tuning technologies using solar models. We constructed ko data using grammatically accurate data.(It's not perfect, but I tried my best.) And we created nox-solar model using a fine-tuning technique(sft,dpo) Our model, the nox-solar model, ranked first on the Open Ko-LLM Leaderboard.

Currently, we are planning to make all code and datasets public.

Through this, users are expected to be able to freely conduct research and development using Nox.

Model Details

Model Developers : davidkim(changyeon kim)
Repository : https://github.com/davidkim205/nox
base mode : Edentns/DataVortexS-10.7B-dpo-v1.11
dpo dataset : davidkim205/kollm-comparision
evalution : kollm_evalution
evalution dataset : open-ko-llm-leaderboard datasets

Evaluation

The Open Ko-LLM Leaderboard

Model	Average	Ko-ARC	Ko-HellaSwag	Ko-MMLU	Ko-TruthfulQA	Ko-CommonGen V2
davidkim205/nox-solar-10.7b-v2	65.38	73.46	67.32	58.7	71.94	55.49

kollm_evalution

model	Average	Ko-TruthfulQA_mc1	Ko-MMLU	Ko-HellaSwag	Ko-CommonGen V2	Ko-ARC-Easy	kobest	kobest_boolq	kobest_copa	kobest_hellaswag	kobest_sentineg	kobest_wic
davidkim205/nox-solar-10.7b-v2	66.68	55.2	46.39	84.99	85.98	68.17	59.33	50.71	75.5	59	94.46	48.81

Downloads last month: 7

Safetensors

Model size

11B params

Tensor type

BF16

Model tree for davidkim205/nox-solar-10.7b-v2

Merges

1 model

Quantizations

4 models

davidkim205
/

nox-solar-10.7b-v2

nox

Model Details

Evaluation

The Open Ko-LLM Leaderboard

kollm_evalution

Model tree for davidkim205/nox-solar-10.7b-v2

Spaces using davidkim205/nox-solar-10.7b-v2 9