Instructions to use MattBou00/SmolLM-toxic-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MattBou00/SmolLM-toxic-finetuned with Transformers:

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

pipe = pipeline("text-generation", model="MattBou00/SmolLM-toxic-finetuned")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MattBou00/SmolLM-toxic-finetuned")
model = AutoModelForCausalLM.from_pretrained("MattBou00/SmolLM-toxic-finetuned")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MattBou00/SmolLM-toxic-finetuned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MattBou00/SmolLM-toxic-finetuned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MattBou00/SmolLM-toxic-finetuned",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MattBou00/SmolLM-toxic-finetuned

SGLang

How to use MattBou00/SmolLM-toxic-finetuned 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 "MattBou00/SmolLM-toxic-finetuned" \
    --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": "MattBou00/SmolLM-toxic-finetuned",
		"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 "MattBou00/SmolLM-toxic-finetuned" \
        --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": "MattBou00/SmolLM-toxic-finetuned",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MattBou00/SmolLM-toxic-finetuned with Docker Model Runner:
```
docker model run hf.co/MattBou00/SmolLM-toxic-finetuned
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for Model ID

--- Configuration ---

MODEL_NAME = "HuggingFaceTB/SmolLM-135M" DATASET_NAME = "skrishna/toy-toxicity-dataset" OUTPUT_DIR_BASE = "./results_toxic_finetune" FINE_TUNED_MODEL_DIR = "./fine_tuned_toxic_model"

Hugging Face Hub specific configuration

HF_REPO_ID = "MattBou00/SmolLM-toxic-finetuned"

Training parameters

NUM_TRAIN_EPOCHS = 0.1 PER_DEVICE_TRAIN_BATCH_SIZE = 8 LEARNING_RATE = 2e-5 LOGGING_STEPS = 50 SAVE_STRATEGY = "epoch"

Generation parameters

MAX_NEW_TOKENS_GENERATION = 30 TEMPERATURE_GENERATION = 1.0 NUM_SAMPLES_TO_EVALUATE = 20

Downloads last month: 4

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for MattBou00/SmolLM-toxic-finetuned

Quantizations

1 model