Instructions to use minpeter/tiny-ko-124m-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use minpeter/tiny-ko-124m-base with Transformers:

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

pipe = pipeline("text-generation", model="minpeter/tiny-ko-124m-base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("minpeter/tiny-ko-124m-base")
model = AutoModelForCausalLM.from_pretrained("minpeter/tiny-ko-124m-base")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use minpeter/tiny-ko-124m-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "minpeter/tiny-ko-124m-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "minpeter/tiny-ko-124m-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/minpeter/tiny-ko-124m-base

SGLang

How to use minpeter/tiny-ko-124m-base 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 "minpeter/tiny-ko-124m-base" \
    --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": "minpeter/tiny-ko-124m-base",
		"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 "minpeter/tiny-ko-124m-base" \
        --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": "minpeter/tiny-ko-124m-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use minpeter/tiny-ko-124m-base with Docker Model Runner:
```
docker model run hf.co/minpeter/tiny-ko-124m-base
```

minpeter commited on Jun 26, 2025

Commit

7e6e0d9

verified ·

1 Parent(s): b0fc6a2

Training in progress, step 313

Browse files

Files changed (3) hide show

config.json +30 -0
model.safetensors +3 -0
training_args.bin +3 -0

config.json ADDED Viewed

	@@ -0,0 +1,30 @@

+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32001,
+  "head_dim": 80,
+  "hidden_act": "silu",
+  "hidden_size": 480,
+  "initializer_range": 0.02,
+  "intermediate_size": 1920,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 6,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 2,
+  "pad_token_id": 32003,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 32018
+}

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:fa15f41aab0e829521b7706d88127c5e6c32c9ff22d3f2728d2348986846fb77
+size 247100976

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:66c0c129c8ee2279cfbeef7b6fd841635aae3c433303e4c1147f2c6b22076c71
+size 5777