Instructions to use Huyle2501/SmolLM2-NewGen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Huyle2501/SmolLM2-NewGen with Transformers:

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

pipe = pipeline("text-generation", model="Huyle2501/SmolLM2-NewGen")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Huyle2501/SmolLM2-NewGen")
model = AutoModelForCausalLM.from_pretrained("Huyle2501/SmolLM2-NewGen", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Huyle2501/SmolLM2-NewGen with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Huyle2501/SmolLM2-NewGen"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Huyle2501/SmolLM2-NewGen",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Huyle2501/SmolLM2-NewGen

SGLang

How to use Huyle2501/SmolLM2-NewGen 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 "Huyle2501/SmolLM2-NewGen" \
    --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": "Huyle2501/SmolLM2-NewGen",
		"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 "Huyle2501/SmolLM2-NewGen" \
        --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": "Huyle2501/SmolLM2-NewGen",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Huyle2501/SmolLM2-NewGen with Docker Model Runner:
```
docker model run hf.co/Huyle2501/SmolLM2-NewGen
```

SmolLM2-testing

This model is a fine-tuned version of HuggingFaceTB/SmolLM2-135M on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.8183

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: 3e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
3.3244	0.1066	100	3.1575
2.9347	0.2132	200	3.0467
2.8302	0.3198	300	2.9874
2.8362	0.4264	400	2.9479
2.7913	0.5330	500	2.9120
2.7092	0.6397	600	2.8882
2.6953	0.7463	700	2.8684
2.6043	0.8529	800	2.8508
2.5504	0.9595	900	2.8356
2.4937	1.0661	1000	2.8345
2.3495	1.1727	1100	2.8333
2.3568	1.2793	1200	2.8295
2.3536	1.3859	1300	2.8278
2.3287	1.4925	1400	2.8236
2.3339	1.5991	1500	2.8211
2.3566	1.7058	1600	2.8193
2.3626	1.8124	1700	2.8185
2.3146	1.9190	1800	2.8183

Framework versions

Transformers 4.56.1
Pytorch 2.8.0+cu126
Datasets 4.0.0
Tokenizers 0.22.0

Downloads last month: 6

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for Huyle2501/SmolLM2-NewGen

Base model

HuggingFaceTB/SmolLM2-135M

Finetuned

(931)

this model