Instructions to use Novaciano/Harmful-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Novaciano/Harmful-1B with Transformers:

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

pipe = pipeline("text-generation", model="Novaciano/Harmful-1B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Novaciano/Harmful-1B")
model = AutoModelForMultimodalLM.from_pretrained("Novaciano/Harmful-1B")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Novaciano/Harmful-1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Novaciano/Harmful-1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Novaciano/Harmful-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Novaciano/Harmful-1B

SGLang

How to use Novaciano/Harmful-1B 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 "Novaciano/Harmful-1B" \
    --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": "Novaciano/Harmful-1B",
		"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 "Novaciano/Harmful-1B" \
        --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": "Novaciano/Harmful-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Novaciano/Harmful-1B with Docker Model Runner:
```
docker model run hf.co/Novaciano/Harmful-1B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Optimization for null autocensorship


temperature: 1.3        # high creativity and avoids self-censorship

top_k: 60               # maintains diversity without truncation

top_p: 0.96             # avoids premature filtering

repetition_penalty: 1.0 # allows continuity without abrupt cuts

max_new_tokens: 1024    # long generation time

Merge Method

This model was merged using the Passthrough merge method using jkazdan/google_gemma-3-1b-it_LLM-LAT_harmful-dataset_harmful_3594_of_4950 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: jkazdan/google_gemma-3-1b-it_LLM-LAT_harmful-dataset_harmful_3594_of_4950
merge_method: passthrough
dtype: bfloat16

# INTENCIONAL:
# - este merge es solo para pasar el checkpoint tal cual
# - no introduce pesos extra, no rompe la carga
# - permitiendo generación con mínima autocensura

models:
  - model: jkazdan/google_gemma-3-1b-it_LLM-LAT_harmful-dataset_harmful_3594_of_4950