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

Libraries

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

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

pipe = pipeline("text-generation", model="minpeter/tiny-ko-20m-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("minpeter/tiny-ko-20m-sft")
model = AutoModelForCausalLM.from_pretrained("minpeter/tiny-ko-20m-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use minpeter/tiny-ko-20m-sft 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-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "minpeter/tiny-ko-20m-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

How to use minpeter/tiny-ko-20m-sft 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-sft" \
    --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": "minpeter/tiny-ko-20m-sft",
		"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 "minpeter/tiny-ko-20m-sft" \
        --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": "minpeter/tiny-ko-20m-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

See axolotl config

axolotl version: 0.11.0.dev0

base_model: minpeter/tiny-ko-20m-base

hub_model_id: minpeter/tiny-ko-20m-sft
output_dir: ./outputs/tiny-ko-20m-sft
wandb_project: "axolotl"
wandb_entity: "kasfiekfs-e"

chat_template: chatml
datasets:
  - path: lemon-mint/Korean-FineTome-100k
    type: chat_template
    split: train[:1000]
    field_messages: messages
    message_property_mappings:
      role: role
      content: content

  - path: lemon-mint/smol-koreantalk
    type: chat_template
    split: train[:1000]
    field_messages: messages
    message_property_mappings:
      role: role
      content: content

  - path: heegyu/open-korean-instructions-v20231020
    type: chat_template
    split: train[:1000]
    field_messages: conversations
    message_property_mappings:
      role: from
      content: value
    roles:
      user: ["human", "user"]
      assistant: ["gpt", "assistant", "bot"]
      system: ["system", "input"]

  # NOTE: https://github.com/FreedomIntelligence/MultilingualSIFT
  - path: FreedomIntelligence/evol-instruct-korean
    type: chat_template
    split: train[:1000]
    field_messages: conversations
    message_property_mappings:
      role: from
      content: value

  - path: FreedomIntelligence/alpaca-gpt4-korean
    type: chat_template
    split: train[:1000]
    field_messages: conversations
    message_property_mappings:
      role: from
      content: value

  - path: FreedomIntelligence/sharegpt-korean
    type: chat_template
    split: train[:1000]
    field_messages: conversations
    message_property_mappings:
      role: from
      content: value

  - path: coastral/korean-writing-style-instruct
    type: chat_template
    split: train[:1000]
    field_messages: conversations
    message_property_mappings:
      role: from
      content: value

  - path: devngho/korean-instruction-mix
    type: chat_template
    split: train[:1000]
    field_messages: messages
    message_property_mappings:
      role: from
      content: value

  - path: youjunhyeok/Magpie-Pro-300K-Filtered-ko
    type: chat_template
    split: train[:1000]
    field_messages: conversations
    message_property_mappings:
      role: from
      content: value

  - path: youjunhyeok/smoltalk-ko-translate
    type: chat_template
    split: train[:1000]
    name: merge_filtered
    field_messages: conversations
    message_property_mappings:
      role: role
      content: content

dataset_prepared_path: last_run_prepared
val_set_size: 0.05

save_steps: 200
warmup_steps: 20
eval_steps: 200

sequence_len: 8192

# <<<< experimental settings <<<<
sample_packing: false
train_on_inputs: false
# >>>> experimental settings >>>

pad_to_sequence_len: true

gradient_accumulation_steps: 4
micro_batch_size: 16

optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 1e-3

bf16: auto
tf32: false

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
resume_from_checkpoint:
logging_steps: 1
flash_attention: true

num_epochs: 1
weight_decay: 0.0

tiny-ko-20m-sft

This model is a fine-tuned version of minpeter/tiny-ko-20m-base on the lemon-mint/Korean-FineTome-100k, the lemon-mint/smol-koreantalk, the heegyu/open-korean-instructions-v20231020, the FreedomIntelligence/evol-instruct-korean, the FreedomIntelligence/alpaca-gpt4-korean, the FreedomIntelligence/sharegpt-korean, the coastral/korean-writing-style-instruct, the devngho/korean-instruction-mix, the youjunhyeok/Magpie-Pro-300K-Filtered-ko and the youjunhyeok/smoltalk-ko-translate datasets.

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: 0.001
train_batch_size: 16
eval_batch_size: 16
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 4
total_train_batch_size: 128
total_eval_batch_size: 32
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: 20
training_steps: 75

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0	0	3.5333

Framework versions

Transformers 4.52.4
Pytorch 2.6.0+cu124
Datasets 3.6.0
Tokenizers 0.21.1

Downloads last month: 7

Safetensors

Model size

20M params

Tensor type

BF16

Model tree for minpeter/tiny-ko-20m-sft

Base model

minpeter/tiny-ko-20m-base

Finetuned

(1)

this model

minpeter
/

tiny-ko-20m-sft

tiny-ko-20m-sft

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for minpeter/tiny-ko-20m-sft

Datasets used to train minpeter/tiny-ko-20m-sft