Instructions to use idah4/byteetm-korean-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use idah4/byteetm-korean-tiny with Transformers:

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

pipe = pipeline("text-generation", model="idah4/byteetm-korean-tiny", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("idah4/byteetm-korean-tiny", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use idah4/byteetm-korean-tiny with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "idah4/byteetm-korean-tiny"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "idah4/byteetm-korean-tiny",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/idah4/byteetm-korean-tiny

SGLang

How to use idah4/byteetm-korean-tiny 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 "idah4/byteetm-korean-tiny" \
    --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": "idah4/byteetm-korean-tiny",
		"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 "idah4/byteetm-korean-tiny" \
        --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": "idah4/byteetm-korean-tiny",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use idah4/byteetm-korean-tiny with Docker Model Runner:
```
docker model run hf.co/idah4/byteetm-korean-tiny
```

idah4 commited on Nov 4, 2025

Commit

70eb4d4

verified ·

1 Parent(s): 55d5258

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -2

README.md CHANGED Viewed

@@ -18,7 +18,6 @@ inference_providers:
 - t4
 - a10g
 library_name: transformers
-pipeline_tag: text-generation
 widget:
   - text: "오늘은 날씨가"
 ---
@@ -26,7 +25,7 @@ widget:
 소형 바이트-레벨 텍스트 디코더 LM
 - 133 MB byte-level causal LM trained on Korean web text.
 - 학습 데이터: roneneldan/TinyStories, HAERAE-HUB/KOREAN-WEBTEXT 일부
-- 학습 step 예시 val ppl ≈ 3.7
 ## Example
 ```python

 - t4
 - a10g
 library_name: transformers
 widget:
   - text: "오늘은 날씨가"
 ---
 소형 바이트-레벨 텍스트 디코더 LM
 - 133 MB byte-level causal LM trained on Korean web text.
 - 학습 데이터: roneneldan/TinyStories, HAERAE-HUB/KOREAN-WEBTEXT 일부
+- 학습 step 예시 val ppl ≈ 3.4
 ## Example
 ```python