Instructions to use chihoonlee10/T3Q-ko-solar-dpo-v6.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chihoonlee10/T3Q-ko-solar-dpo-v6.0 with Transformers:

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

pipe = pipeline("text-generation", model="chihoonlee10/T3Q-ko-solar-dpo-v6.0")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("chihoonlee10/T3Q-ko-solar-dpo-v6.0")
model = AutoModelForMultimodalLM.from_pretrained("chihoonlee10/T3Q-ko-solar-dpo-v6.0")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use chihoonlee10/T3Q-ko-solar-dpo-v6.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "chihoonlee10/T3Q-ko-solar-dpo-v6.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "chihoonlee10/T3Q-ko-solar-dpo-v6.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/chihoonlee10/T3Q-ko-solar-dpo-v6.0

SGLang

How to use chihoonlee10/T3Q-ko-solar-dpo-v6.0 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 "chihoonlee10/T3Q-ko-solar-dpo-v6.0" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "chihoonlee10/T3Q-ko-solar-dpo-v6.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "chihoonlee10/T3Q-ko-solar-dpo-v6.0" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "chihoonlee10/T3Q-ko-solar-dpo-v6.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use chihoonlee10/T3Q-ko-solar-dpo-v6.0 with Docker Model Runner:
```
docker model run hf.co/chihoonlee10/T3Q-ko-solar-dpo-v6.0
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

T3Q-ko-solar-dpo-v6.0

This model is a version of T3Q-ko-solar-dpo-v5.0 that has been fine-tuned with DPO.

Model Developers Chihoon Lee(chihoonlee10), T3Q

hf (pretrained=chihoonlee10/T3Q-ko-solar-dpo-v6.0), limit: None, provide_description: False, num_fewshot: 0, batch_size: None

Task	Version	Metric	Value		Stderr
kobest_boolq	0	acc	0.5028	±	0.0133
		macro_f1	0.3396	±	0.0067
kobest_copa	0	acc	0.8020	±	0.0126
		macro_f1	0.8018	±	0.0126
kobest_hellaswag	0	acc	0.5340	±	0.0223
		acc_norm	0.5720	±	0.0221
		macro_f1	0.5322	±	0.0224
kobest_sentineg	0	acc	0.7985	±	0.0202
		macro_f1	0.7956	±	0.0205

Downloads last month: 7

Safetensors

Model size

11B params

Tensor type

F16

Model tree for chihoonlee10/T3Q-ko-solar-dpo-v6.0

Merges

2 models

Quantizations

5 models

chihoonlee10
/

T3Q-ko-solar-dpo-v6.0

T3Q-ko-solar-dpo-v6.0

This model is a version of T3Q-ko-solar-dpo-v5.0 that has been fine-tuned with DPO.

Model Developers Chihoon Lee(chihoonlee10), T3Q

Model tree for chihoonlee10/T3Q-ko-solar-dpo-v6.0

Spaces using chihoonlee10/T3Q-ko-solar-dpo-v6.0 9