Instructions to use halcyon-llm/SmolLM2-360M-japanese_patch-11393 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use halcyon-llm/SmolLM2-360M-japanese_patch-11393 with Transformers:

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

pipe = pipeline("text-generation", model="halcyon-llm/SmolLM2-360M-japanese_patch-11393")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("halcyon-llm/SmolLM2-360M-japanese_patch-11393")
model = AutoModelForCausalLM.from_pretrained("halcyon-llm/SmolLM2-360M-japanese_patch-11393", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use halcyon-llm/SmolLM2-360M-japanese_patch-11393 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "halcyon-llm/SmolLM2-360M-japanese_patch-11393"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "halcyon-llm/SmolLM2-360M-japanese_patch-11393",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/halcyon-llm/SmolLM2-360M-japanese_patch-11393

SGLang

How to use halcyon-llm/SmolLM2-360M-japanese_patch-11393 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 "halcyon-llm/SmolLM2-360M-japanese_patch-11393" \
    --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": "halcyon-llm/SmolLM2-360M-japanese_patch-11393",
		"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 "halcyon-llm/SmolLM2-360M-japanese_patch-11393" \
        --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": "halcyon-llm/SmolLM2-360M-japanese_patch-11393",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use halcyon-llm/SmolLM2-360M-japanese_patch-11393 with Docker Model Runner:
```
docker model run hf.co/halcyon-llm/SmolLM2-360M-japanese_patch-11393
```

results

This model is a fine-tuned version of HuggingFaceTB/SmolLM2-360M on the kajuma/training_01-09_patch dataset. It achieves the following results on the evaluation set:

Loss: 0.1002

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: 0.003
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 32
total_train_batch_size: 256
optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine_with_min_lr
lr_scheduler_warmup_steps: 1000
num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
3.584	0.0878	1000	0.1139
3.4937	0.1755	2000	0.1080
3.3486	0.2633	3000	0.1059
3.4019	0.3511	4000	0.1044
3.2915	0.4388	5000	0.1033
3.2729	0.5266	6000	0.1023
3.2451	0.6144	7000	0.1015
3.2339	0.7022	8000	0.1009
3.2383	0.7899	9000	0.1005
3.2441	0.8777	10000	0.1003
3.2744	0.9655	11000	0.1002

Framework versions

Transformers 4.48.0.dev0
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0

Downloads last month: 52

Safetensors

Model size

0.4B params

Tensor type

BF16

Model tree for halcyon-llm/SmolLM2-360M-japanese_patch-11393

Base model

HuggingFaceTB/SmolLM2-360M

Finetuned

(122)

this model

Dataset used to train halcyon-llm/SmolLM2-360M-japanese_patch-11393

Collection including halcyon-llm/SmolLM2-360M-japanese_patch-11393

SmolLM2-360M-japanese_patch-checkpoints

Collection

12 items • Updated Feb 7, 2025