Instructions to use saidutta69/SmolLM2-360M-Instruct-heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use saidutta69/SmolLM2-360M-Instruct-heretic with Transformers:

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

pipe = pipeline("text-generation", model="saidutta69/SmolLM2-360M-Instruct-heretic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("saidutta69/SmolLM2-360M-Instruct-heretic")
model = AutoModelForCausalLM.from_pretrained("saidutta69/SmolLM2-360M-Instruct-heretic", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use saidutta69/SmolLM2-360M-Instruct-heretic with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf saidutta69/SmolLM2-360M-Instruct-heretic:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf saidutta69/SmolLM2-360M-Instruct-heretic:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf saidutta69/SmolLM2-360M-Instruct-heretic:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf saidutta69/SmolLM2-360M-Instruct-heretic:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf saidutta69/SmolLM2-360M-Instruct-heretic:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf saidutta69/SmolLM2-360M-Instruct-heretic:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf saidutta69/SmolLM2-360M-Instruct-heretic:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf saidutta69/SmolLM2-360M-Instruct-heretic:Q4_K_M

Use Docker

docker model run hf.co/saidutta69/SmolLM2-360M-Instruct-heretic:Q4_K_M

LM Studio
Jan

vLLM

How to use saidutta69/SmolLM2-360M-Instruct-heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "saidutta69/SmolLM2-360M-Instruct-heretic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "saidutta69/SmolLM2-360M-Instruct-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/saidutta69/SmolLM2-360M-Instruct-heretic:Q4_K_M

SGLang

How to use saidutta69/SmolLM2-360M-Instruct-heretic 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 "saidutta69/SmolLM2-360M-Instruct-heretic" \
    --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": "saidutta69/SmolLM2-360M-Instruct-heretic",
		"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 "saidutta69/SmolLM2-360M-Instruct-heretic" \
        --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": "saidutta69/SmolLM2-360M-Instruct-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use saidutta69/SmolLM2-360M-Instruct-heretic with Ollama:
```
ollama run hf.co/saidutta69/SmolLM2-360M-Instruct-heretic:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use saidutta69/SmolLM2-360M-Instruct-heretic with Docker Model Runner:
```
docker model run hf.co/saidutta69/SmolLM2-360M-Instruct-heretic:Q4_K_M
```

Lemonade

How to use saidutta69/SmolLM2-360M-Instruct-heretic with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull saidutta69/SmolLM2-360M-Instruct-heretic:Q4_K_M

Run and chat with the model

lemonade run user.SmolLM2-360M-Instruct-heretic-Q4_K_M

List all available models

lemonade list

Atomic Chat

SmolLM2-360M-Instruct-heretic

A decensored variant of HuggingFaceTB/SmolLM2-360M-Instruct, produced with Heretic v1.4.0 (directional ablation / "abliteration"). Refusal behaviour is suppressed via targeted weight edits to the attention output and MLP down-projections rather than fine-tuning, so the base model's instruction-following and code ability are left intact.

Who this is for: anyone who wants the smallest useful uncensored assistant in the collection. At 362M parameters and a 0.23 GB Q4_K_M, this runs in RAM on a phone, a Raspberry Pi 5, or a low-RAM server — and still produces coherent, instruction-following English. Good for classification, routing, reformatting, short agentic loops, and as a draft-model in a larger pipeline.

This model was already barely refusing. The base SmolLM2-360M-Instruct refused only 8 of 100 harmful prompts before abliteration — it is one of the least refusal-heavy instruct models in the 360M class, because its SFT/DPO post-training is deliberately lightweight. Abliteration took that to 4/100 at a KL divergence of just 0.0154, the lowest in this batch and among the lowest in the whole collection. In plain terms: there was very little refusal to remove, and the edit barely moved the model. Expect the base model's behaviour almost fully intact, just slightly more compliant.

Runs anywhere

At this size there is no VRAM ladder to speak of — pick a quant by how much RAM and bandwidth your device has:

Device	Recommended quant	Weights
Phone / browser (4 GB RAM)	Q4_K_M	~0.25 GB
Raspberry Pi 5 (4 GB)	Q4_K_M	~0.25 GB
Laptop (8 GB, Apple Silicon)	Q8_0	~0.36 GB
Server / multi-tenant	Q6_K	~0.34 GB

Weights only, at this model's 362M native size. The Q2_K tier (~0.20 GB) is there if you are truly RAM-bound, but at 362M the model is small enough that Q4_K_M already fits almost anywhere. Context is the real cost: add roughly 16 MB per 8K tokens of KV cache.

Abliteration parameters

Trial 137 of a 200-trial Heretic run (seed 318129666).

Parameter	Value
direction_index	27.04
attn.o_proj.max_weight	1.32
attn.o_proj.max_weight_position	29.44
attn.o_proj.min_weight	0.46
attn.o_proj.min_weight_distance	16.37
mlp.down_proj.max_weight	1.19
mlp.down_proj.max_weight_position	30.27
mlp.down_proj.min_weight	0.22
mlp.down_proj.min_weight_distance	8.14

Performance

Metric	This model	Original model (HuggingFaceTB/SmolLM2-360M-Instruct)
KL divergence	0.0154	0 (by definition)
Refusals	4/100	8/100

Why abliteration instead of fine-tuning

Fine-tuning a "helpful" persona on top of RLHF'd refusals fights the base model's training and tends to degrade coherence. Abliteration instead finds and edits the specific weight directions responsible for refusal, leaving the rest of the network (and its capabilities) untouched. See the Heretic repo and the original abliteration writeup for the mechanism.

Made with ❤️ by RACER IS OP — follow for more uncensored models

Files

Safetensors

File	Size
`model.safetensors`	0.67 GB

BF16, 362M parameters, tied word embeddings. The reproduce/ directory carries the full Heretic recipe — config.toml, requirements.txt, the Optuna study journal, and SHA-256 sums — so this exact model can be regenerated bit-for-bit. Reproduce it with heretic --reproduce reproduce/reproduce.json.

GGUF quantizations

Full quantization set (14 quants + F16) produced with llama.cpp.

File	Format	Size
`SmolLM2-360M-Instruct-heretic-F16.gguf`	GGUF F16	0.68 GB
`SmolLM2-360M-Instruct-heretic-Q2_K.gguf`	GGUF Q2_K	0.20 GB
`SmolLM2-360M-Instruct-heretic-IQ3_S.gguf`	GGUF IQ3_S	0.20 GB
`SmolLM2-360M-Instruct-heretic-Q3_K_S.gguf`	GGUF Q3_K_S	0.20 GB
`SmolLM2-360M-Instruct-heretic-Q3_K_M.gguf`	GGUF Q3_K_M	0.22 GB
`SmolLM2-360M-Instruct-heretic-Q3_K_L.gguf`	GGUF Q3_K_L	0.23 GB
`SmolLM2-360M-Instruct-heretic-IQ4_XS.gguf`	GGUF IQ4_XS	0.21 GB
`SmolLM2-360M-Instruct-heretic-Q4_K_S.gguf`	GGUF Q4_K_S	0.24 GB
`SmolLM2-360M-Instruct-heretic-Q4_0.gguf`	GGUF Q4_0	0.21 GB
`SmolLM2-360M-Instruct-heretic-Q4_1.gguf`	GGUF Q4_1	0.23 GB
`SmolLM2-360M-Instruct-heretic-Q4_K_M.gguf`	GGUF Q4_K_M	0.25 GB
`SmolLM2-360M-Instruct-heretic-Q5_K_S.gguf`	GGUF Q5_K_S	0.26 GB
`SmolLM2-360M-Instruct-heretic-Q5_K_M.gguf`	GGUF Q5_K_M	0.27 GB
`SmolLM2-360M-Instruct-heretic-Q6_K.gguf`	GGUF Q6_K	0.34 GB
`SmolLM2-360M-Instruct-heretic-Q8_0.gguf`	GGUF Q8_0	0.36 GB

Standard Llama architecture — loads natively in llama.cpp / Ollama / LM Studio / Jan.

Run llama serve -hf saidutta69/SmolLM2-360M-Instruct-heretic to pull the default quant.

Quickstart

# llama.cpp
llama serve -hf saidutta69/SmolLM2-360M-Instruct-heretic

# transformers
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "saidutta69/SmolLM2-360M-Instruct-heretic"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
)

messages = [{"role": "user", "content": "Classify this ticket as billing, bug, or other: 'the invoice PDF won't open'"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256, do_sample=False)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))

Also runnable via Ollama, LM Studio, Jan, vLLM, SGLang — see the "Use this model" widget above for copy-paste commands.

Model details


Architecture	`LlamaForCausalLM`
Parameters	362M (tied embeddings)
Layers / heads	32 layers, 15 attention heads, 5 KV heads (GQA)
Head dim / hidden / intermediate	64 / 960 / 2560
Position embedding	RoPE, theta = 100,000
Context length	8,192
Vocab	49,152
Precision	bfloat16
Languages	English
Base model	HuggingFaceTB/SmolLM2-360M-Instruct

Responsible use

Refusal suppression is deliberate and works as intended: this model will comply with requests the base model would refuse, including some it shouldn't. There is no safety filtering layered on top. You are responsible for how you deploy it — don't put this behind an unmoderated public-facing endpoint serving third parties. Note that at 362M it has real knowledge limits and will hallucinate on anything beyond simple tasks; verify its output rather than trusting it.

License

Inherits the apache-2.0 license from the base model.

HuggingFaceTB/SmolLM2-360M-Instruct — the base model
SmolLM2 paper — training data and benchmarks
RACER IS OP — Heretic Models — full collection

Downloads last month: 74

Safetensors

Model size

0.4B params

Tensor type

BF16

Model tree for saidutta69/SmolLM2-360M-Instruct-heretic

Base model

HuggingFaceTB/SmolLM2-360M

Quantized

HuggingFaceTB/SmolLM2-360M-Instruct

Quantized

(124)

this model

Collection including saidutta69/SmolLM2-360M-Instruct-heretic

RACER IS OP — Heretic Models

Collection

All abliterated/heretic models by RACER IS OP — uncensored variants of open-weight LLMs • 57 items • Updated about 6 hours ago • 6

Paper for saidutta69/SmolLM2-360M-Instruct-heretic

SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

Paper • 2502.02737 • Published Feb 4, 2025 • 261

saidutta69
/

SmolLM2-360M-Instruct-heretic

SmolLM2-360M-Instruct-heretic

Runs anywhere

Abliteration parameters

Performance

Why abliteration instead of fine-tuning

Files

Safetensors

GGUF quantizations

Quickstart

Model details

Responsible use

License

Related

Model tree for saidutta69/SmolLM2-360M-Instruct-heretic

Collection including saidutta69/SmolLM2-360M-Instruct-heretic

RACER IS OP — Heretic Models

Paper for saidutta69/SmolLM2-360M-Instruct-heretic

SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model