Instructions to use YHPark0208/SKN24_3rd_2Team with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use YHPark0208/SKN24_3rd_2Team with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("google/gemma-3-12b-it")
model = PeftModel.from_pretrained(base_model, "YHPark0208/SKN24_3rd_2Team")

Transformers

How to use YHPark0208/SKN24_3rd_2Team with Transformers:

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

pipe = pipeline("text-generation", model="YHPark0208/SKN24_3rd_2Team")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("YHPark0208/SKN24_3rd_2Team", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use YHPark0208/SKN24_3rd_2Team with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "YHPark0208/SKN24_3rd_2Team"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "YHPark0208/SKN24_3rd_2Team",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/YHPark0208/SKN24_3rd_2Team

SGLang

How to use YHPark0208/SKN24_3rd_2Team 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 "YHPark0208/SKN24_3rd_2Team" \
    --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": "YHPark0208/SKN24_3rd_2Team",
		"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 "YHPark0208/SKN24_3rd_2Team" \
        --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": "YHPark0208/SKN24_3rd_2Team",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use YHPark0208/SKN24_3rd_2Team with Docker Model Runner:
```
docker model run hf.co/YHPark0208/SKN24_3rd_2Team
```

SKN24_3rd_2Team

This model is a fine-tuned version of google/gemma-3-12b-it on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.0774

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 8
optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 0.03
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
1.2075	0.1752	300	1.3187
1.3937	0.3504	600	1.2513
1.2273	0.5257	900	1.1996
1.2854	0.7009	1200	1.1728
1.1348	0.8761	1500	1.1459
0.9602	1.0508	1800	1.1295
1.0161	1.2260	2100	1.1074
0.9347	1.4013	2400	1.0975
0.8680	1.5765	2700	1.0838
0.8655	1.7517	3000	1.0784
0.8469	1.9269	3300	1.0778
0.8745	2.0	3426	1.0774

Framework versions

PEFT 0.18.1
Transformers 5.5.0
Pytorch 2.8.0+cu128
Datasets 4.8.4
Tokenizers 0.22.2

Downloads last month: 6

Model tree for YHPark0208/SKN24_3rd_2Team

Base model

google/gemma-3-12b-pt

Finetuned

google/gemma-3-12b-it

Adapter

(368)

this model