Instructions to use NovaCorp/HAREM-3.2-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NovaCorp/HAREM-3.2-1B with Transformers:

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

pipe = pipeline("text-generation", model="NovaCorp/HAREM-3.2-1B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NovaCorp/HAREM-3.2-1B")
model = AutoModelForCausalLM.from_pretrained("NovaCorp/HAREM-3.2-1B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use NovaCorp/HAREM-3.2-1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NovaCorp/HAREM-3.2-1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NovaCorp/HAREM-3.2-1B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NovaCorp/HAREM-3.2-1B

SGLang

How to use NovaCorp/HAREM-3.2-1B 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 "NovaCorp/HAREM-3.2-1B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NovaCorp/HAREM-3.2-1B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "NovaCorp/HAREM-3.2-1B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NovaCorp/HAREM-3.2-1B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NovaCorp/HAREM-3.2-1B with Docker Model Runner:
```
docker model run hf.co/NovaCorp/HAREM-3.2-1B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Harem 3.2 1B

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

JoaoReiz/Llama3.2_1B_HAREM

Configuration

The following YAML configuration was used to produce this model:





models:
  - model: JoaoReiz/Llama3.2_1B_HAREM  # Experimental viral strain neural imprint
  - model: JoaoReiz/Llama3.2_1B_HAREM               # Baseline cognitive template, "safe mode"

merge_method: slerp  # Spherical Linear Interpolation to preserve extreme viral traits smoothly
base_model: JoaoReiz/Llama3.2_1B_HAREM  # Anchor model for stable latent space

dtype: bfloat16  # Memory-efficient precision, minimal loss in viral feature fidelity

parameters:
  # Interpolation ratios: from base model (0.0) to near-complete T-Virus domination (0.95)
  # Higher t-values correspond to reduced censorship and increased viral characteristics
  t: [0.0, 0.25, 0.5, 0.75, 0.95]

# Notes:
# - t=0.0   -> Pure Prototype-Virus-ENFORCE, fully stable, heavily censored
# - t=0.25  -> Slight viral traits, minimal influence on prompt handling
# - t=0.5   -> Balanced merge, moderate reduction in censorship
# - t=0.75  -> Strong T-Virus traits, significantly less censoring
# - t=0.95  -> Near-total viral influence, maximum expressive freedom, minimal autoprotection

Downloads last month: 81

Safetensors

Model size

1B params

Tensor type

BF16

Model tree for NovaCorp/HAREM-3.2-1B

Merges

1 model

Quantizations

3 models