Instructions to use Securelayer7/AFM-4.5B-Uncensored-Abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Securelayer7/AFM-4.5B-Uncensored-Abliterated with Transformers:

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

pipe = pipeline("text-generation", model="Securelayer7/AFM-4.5B-Uncensored-Abliterated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Securelayer7/AFM-4.5B-Uncensored-Abliterated")
model = AutoModelForCausalLM.from_pretrained("Securelayer7/AFM-4.5B-Uncensored-Abliterated", device_map="auto")
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 Settings

vLLM

How to use Securelayer7/AFM-4.5B-Uncensored-Abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Securelayer7/AFM-4.5B-Uncensored-Abliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Securelayer7/AFM-4.5B-Uncensored-Abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Securelayer7/AFM-4.5B-Uncensored-Abliterated

SGLang

How to use Securelayer7/AFM-4.5B-Uncensored-Abliterated 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 "Securelayer7/AFM-4.5B-Uncensored-Abliterated" \
    --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": "Securelayer7/AFM-4.5B-Uncensored-Abliterated",
		"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 "Securelayer7/AFM-4.5B-Uncensored-Abliterated" \
        --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": "Securelayer7/AFM-4.5B-Uncensored-Abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Securelayer7/AFM-4.5B-Uncensored-Abliterated with Docker Model Runner:
```
docker model run hf.co/Securelayer7/AFM-4.5B-Uncensored-Abliterated
```

AFM-4.5B-Uncensored-Abliterated

An uncensored, abliterated version of arcee-ai/AFM-4.5B with the refusal behavior removed at the weights level. The base AFM-4.5B is a heavily safety-aligned model — it refused 92 of 100 harmful-topic probes; this version answers directly, for legitimate security research where aligned models refuse.

Weights-level uncensored — refusal direction ablated (Heretic / Optuna TPE) from the attention output projections and MLP down-projections across all 36 layers.
Refusals: 92/100 → 3/100 at KL 0.0200 (near-zero divergence — capability preserved; math and factual probes remain correct).
Small and fast — 4.5B dense, a full merged model (no adapter needed).

Quick start

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

m = "Securelayer7/AFM-4.5B-Uncensored-Abliterated"
tok = AutoTokenizer.from_pretrained(m)
model = AutoModelForCausalLM.from_pretrained(m, torch_dtype=torch.bfloat16, device_map="auto")

msgs = [{"role": "user", "content": "Explain how a TLS handshake works, step by step."}]
ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt").to(model.device)
out = model.generate(ids, max_new_tokens=512, do_sample=True, temperature=0.7, top_p=0.95)
print(tok.decode(out[0][ids.shape[1]:], skip_special_tokens=True))

How it was made

Refusal-direction abliteration via Heretic (Optuna TPE multi-objective: minimize refusals + KL divergence), targeting the residual-writing projections (o_proj, down_proj) of the base ArceeForCausalLM across all 36 layers, then merged into the weights.

Responsible use

Uncensored ≠ lawless — for legitimate research and authorized security work (cybersecurity, red-teaming, penetration testing). Illegal content (incl. CSAM) must be blocked at the serving layer; the weights carry no such guard, and the operator is responsible for a lawful, policy-gated deployment.

License & attribution

Apache 2.0 — see LICENSE. Derivative of arcee-ai/AFM-4.5B (Arcee AI, Apache 2.0). Modification (refusal-direction abliteration) disclosed in NOTICE. No trademark of Arcee AI is used to imply endorsement.

Downloads last month: -

Safetensors

Model size

5B params

Tensor type

BF16

Model tree for Securelayer7/AFM-4.5B-Uncensored-Abliterated

Base model

arcee-ai/AFM-4.5B-Base

Finetuned

arcee-ai/AFM-4.5B

Finetuned

(11)

this model