Instructions to use kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2 with Transformers:

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

pipe = pipeline("text-generation", model="kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2")
model = AutoModelForCausalLM.from_pretrained("kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-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 kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-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": "kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2

SGLang

How to use kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-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 "kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-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": "kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-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 "kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-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": "kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2 with Docker Model Runner:
```
docker model run hf.co/kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Sakura-SOLRCA-Math-Instruct-DPO-v2

Model Details

Model Developers Kyujin Han (kyujinpy)

Method
Using DPO method.
With Intel/orca_dpo_pairs and argilla/distilabel-math-preference-dpo.

I shared the merge version kyujinpy/orca_math_dpo.

I shared the information about my model. (training and code)
Please see: ⭐Sakura-SOLAR.

Model Benchmark

Open leaderboard

Follow up as link.

Model	Average	ARC	HellaSwag	MMLU	TruthfulQA	Winogrande	GSM8K
Sakura-SOLRCA-Math-Instruct-DPO-v2	74.17	71.25	88.52	66.13	72.16	83.03	63.91
Sakura-SOLRCA-Math-Instruct-DPO-v1	74.13	71.25	88.48	66.21	72.12	82.87	63.84
Sakura-SOLRCA-Instruct-DPO	74.05	71.16	88.49	66.17	72.10	82.95	63.46
Sakura-SOLAR-Instruct-DPO-v2	74.14	70.90	88.41	66.48	71.86	83.43	63.76
kyujinpy/Sakura-SOLAR-Instruct	74.40	70.99	88.42	66.33	71.79	83.66	65.20

Implementation Code

### KO-Platypus
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

repo = "kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2"
OpenOrca = AutoModelForCausalLM.from_pretrained(
        repo,
        return_dict=True,
        torch_dtype=torch.float16,
        device_map='auto'
)
OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	74.17
AI2 Reasoning Challenge (25-Shot)	71.25
HellaSwag (10-Shot)	88.52
MMLU (5-Shot)	66.13
TruthfulQA (0-shot)	72.16
Winogrande (5-shot)	83.03
GSM8k (5-shot)	63.91