Instructions to use minpeter/tiny-ko-20m-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use minpeter/tiny-ko-20m-base with Transformers:

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

pipe = pipeline("text-generation", model="minpeter/tiny-ko-20m-base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("minpeter/tiny-ko-20m-base")
model = AutoModelForCausalLM.from_pretrained("minpeter/tiny-ko-20m-base")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use minpeter/tiny-ko-20m-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-20m-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-20m-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/minpeter/tiny-ko-20m-base

SGLang

How to use minpeter/tiny-ko-20m-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-20m-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-20m-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-20m-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-20m-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use minpeter/tiny-ko-20m-base with Docker Model Runner:
```
docker model run hf.co/minpeter/tiny-ko-20m-base
```

tiny-ko-20m-base / tokenizer_config.json

minpeter

Update tokenizer_config.json

083b441 verified about 1 year ago

Raw

History Blame Contribute Delete

3.61 kB

	{
	"added_tokens_decoder": {
	"32000": {
	"content": "<\|im_start\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32001": {
	"content": "<\|im_end\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32002": {
	"content": "<\|unk_token\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32003": {
	"content": "<\|pad_token\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32004": {
	"content": "<tool_call>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"32005": {
	"content": "</tool_call>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"32006": {
	"content": "<think>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"32007": {
	"content": "</think>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": false
	},
	"32008": {
	"content": "<\|unused_special_token_0\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32009": {
	"content": "<\|unused_special_token_1\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32010": {
	"content": "<\|unused_special_token_2\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32011": {
	"content": "<\|unused_special_token_3\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32012": {
	"content": "<\|unused_special_token_4\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32013": {
	"content": "<\|unused_special_token_5\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32014": {
	"content": "<\|unused_special_token_6\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32015": {
	"content": "<\|unused_special_token_7\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32016": {
	"content": "<\|unused_special_token_8\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"32017": {
	"content": "<\|unused_special_token_9\|>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	}
	},
	"clean_up_tokenization_spaces": false,
	"eos_token": "<\|im_end\|>",
	"extra_special_tokens": {},
	"model_max_length": 8192,
	"pad_token": "<\|pad_token\|>",
	"tokenizer_class": "PreTrainedTokenizer",
	"unk_token": "<\|unk_token\|>"
	}