Instructions to use bakhil-aissa/smollerlm2_unsloth with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bakhil-aissa/smollerlm2_unsloth with Transformers:

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

pipe = pipeline("text-generation", model="bakhil-aissa/smollerlm2_unsloth")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bakhil-aissa/smollerlm2_unsloth")
model = AutoModelForCausalLM.from_pretrained("bakhil-aissa/smollerlm2_unsloth")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use bakhil-aissa/smollerlm2_unsloth with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bakhil-aissa/smollerlm2_unsloth"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bakhil-aissa/smollerlm2_unsloth",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bakhil-aissa/smollerlm2_unsloth

SGLang

How to use bakhil-aissa/smollerlm2_unsloth 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 "bakhil-aissa/smollerlm2_unsloth" \
    --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": "bakhil-aissa/smollerlm2_unsloth",
		"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 "bakhil-aissa/smollerlm2_unsloth" \
        --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": "bakhil-aissa/smollerlm2_unsloth",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bakhil-aissa/smollerlm2_unsloth with Docker Model Runner:
```
docker model run hf.co/bakhil-aissa/smollerlm2_unsloth
```

Model Card for Model ID

Model Details

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

Developed by: Aissa Bakhil
Model type: Text Generation
Language(s) (NLP): En
License: More Information Needed
Pruned from model: SmolLM2-137M

Evaluation

Dataset	Accuracy
HellaSwag	32.58
PIQA	61.48
WinoGrande	51.8
ARC-C	46.13
ARC-E	25.60

Hardware

2xT4

Software

Unsloth,Pytorch,transformers

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]

Downloads last month: 3

Safetensors

Model size

97.5M params

Tensor type

F16

bakhil-aissa
/

smollerlm2_unsloth

Model Card for Model ID

Model Details

Model Description

Evaluation

Hardware

Software

More Information [optional]

Model Card Authors [optional]

Model Card Contact

Space using bakhil-aissa/smollerlm2_unsloth 1