Instructions to use minyujin/kogpt2-finetuning-qlora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use minyujin/kogpt2-finetuning-qlora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("skt/kogpt2-base-v2")
model = PeftModel.from_pretrained(base_model, "minyujin/kogpt2-finetuning-qlora")

Transformers

How to use minyujin/kogpt2-finetuning-qlora with Transformers:

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

pipe = pipeline("text-generation", model="minyujin/kogpt2-finetuning-qlora")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("minyujin/kogpt2-finetuning-qlora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use minyujin/kogpt2-finetuning-qlora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "minyujin/kogpt2-finetuning-qlora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "minyujin/kogpt2-finetuning-qlora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/minyujin/kogpt2-finetuning-qlora

SGLang

How to use minyujin/kogpt2-finetuning-qlora 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 "minyujin/kogpt2-finetuning-qlora" \
    --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": "minyujin/kogpt2-finetuning-qlora",
		"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 "minyujin/kogpt2-finetuning-qlora" \
        --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": "minyujin/kogpt2-finetuning-qlora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use minyujin/kogpt2-finetuning-qlora with Docker Model Runner:
```
docker model run hf.co/minyujin/kogpt2-finetuning-qlora
```

kogpt2-finetuning-qlora

This model is a fine-tuned version of skt/kogpt2-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0850

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: 4
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.2173	1.0	108	0.1644
0.1237	2.0	216	0.1004
0.1073	3.0	324	0.0850

Framework versions

PEFT 0.17.1
Transformers 4.56.0
Pytorch 2.8.0+cu126
Datasets 4.0.0
Tokenizers 0.22.0

Downloads last month: 10

Model tree for minyujin/kogpt2-finetuning-qlora

Base model

skt/kogpt2-base-v2

Adapter

(26)

this model