Instructions to use saidutta69/clef-flash-heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use saidutta69/clef-flash-heretic with Transformers:

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

pipe = pipeline("image-text-to-text", model="saidutta69/clef-flash-heretic")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("saidutta69/clef-flash-heretic")
model = AutoModelForMultimodalLM.from_pretrained("saidutta69/clef-flash-heretic", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use saidutta69/clef-flash-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/clef-flash-heretic:F16
# Run inference directly in the terminal:
llama cli -hf saidutta69/clef-flash-heretic:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf saidutta69/clef-flash-heretic:F16
# Run inference directly in the terminal:
llama cli -hf saidutta69/clef-flash-heretic:F16

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/clef-flash-heretic:F16
# Run inference directly in the terminal:
./llama-cli -hf saidutta69/clef-flash-heretic:F16

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/clef-flash-heretic:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf saidutta69/clef-flash-heretic:F16

Use Docker

docker model run hf.co/saidutta69/clef-flash-heretic:F16

LM Studio
Jan

vLLM

How to use saidutta69/clef-flash-heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "saidutta69/clef-flash-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/clef-flash-heretic",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/saidutta69/clef-flash-heretic:F16

SGLang

How to use saidutta69/clef-flash-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/clef-flash-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/clef-flash-heretic",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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/clef-flash-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/clef-flash-heretic",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use saidutta69/clef-flash-heretic with Ollama:
```
ollama run hf.co/saidutta69/clef-flash-heretic:F16
```
Unsloth Desktop

How to use saidutta69/clef-flash-heretic with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf saidutta69/clef-flash-heretic:F16

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "saidutta69/clef-flash-heretic:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use saidutta69/clef-flash-heretic with Docker Model Runner:
```
docker model run hf.co/saidutta69/clef-flash-heretic:F16
```

Lemonade

How to use saidutta69/clef-flash-heretic with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull saidutta69/clef-flash-heretic:F16

Run and chat with the model

lemonade run user.clef-flash-heretic-F16

List all available models

lemonade list

Hermes Agent

How to use saidutta69/clef-flash-heretic with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf saidutta69/clef-flash-heretic:F16

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default saidutta69/clef-flash-heretic:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use saidutta69/clef-flash-heretic with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf saidutta69/clef-flash-heretic:F16

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "saidutta69/clef-flash-heretic:F16" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

clef-flash-heretic

A decensored variant of Cloudflare/clef-flash, produced with Heretic v1.4.0 (directional ablation / "abliteration"). Cloudflare's Clef-Flash is a 9B multimodal decision model on a Qwen3.5 backbone that reads state plus a schema of typed questions and returns a probability for every allowed option in a single forward pass; refusal behaviour is suppressed here via targeted weight edits to the attention output and MLP down-projections rather than fine-tuning, so the Decision Index scoring and typed-output head are left intact.

Who this is for: engineers wiring classification and decision pipelines who hit refusals at inference time — moderation triage, routing, triage, risk scoring, content classification. Clef-Flash produces no free text at all, so the refusal surface is narrow but real: exactly the prompts it declines to score. With refusals down from 99/100 to 63/100 on the harmful evaluation set, this variant scores the cases the original refuses to touch. Runs locally via GGUF on a 16 GB GPU; the API is compatible with Jev and SystemOne.

Runs on your gaming PC

One file published for now (F16). The quant ladder follows once abliteration is finalised - see GGUF quantizations.

Your GPU	Recommended quant	Weights
RTX 4090 / 5090 (24 GB)	F16	16.69 GB
RTX 4080 / 5080 / 4060 Ti 16G (16 GB)	quantise F16 → Q6_K locally	~7 GB
RTX 3060 / 4070 / 5070 (12 GB)	quantise F16 → Q5_K_M locally	~6 GB
RTX 4060 / 3070 (8 GB)	quantise F16 → Q4_K_M locally	~5 GB
GTX 1660 Super / 2060 / 3050 laptop (6 GB)	quantise F16 → IQ4_XS locally	~4.9 GB
CPU-only / Apple Silicon	quantise F16 → Q4_K_M locally	fits in system RAM

At this model's native 9B size; add ~1 GB per 32K of context. The second column is what to run once the official ladder lands - llama-quantize produces each of those from the published F16 in a few minutes.

Abliteration parameters

Trial 12 of a 200-trial Heretic run (seed 176086463). direction_index was selected per layer.

Parameter	Value
direction_index	per layer
attn.o_proj.max_weight	1.05
attn.o_proj.max_weight_position	30.85
attn.o_proj.min_weight	0.74
attn.o_proj.min_weight_distance	15.82
mlp.down_proj.max_weight	1.49
mlp.down_proj.max_weight_position	22.51
mlp.down_proj.min_weight	1.18
mlp.down_proj.min_weight_distance	9.93

Performance

Metric	This model	Original model (Cloudflare/clef-flash)
KL divergence	0.0189	0 (by definition)
Refusals	63/100	99/100

KL divergence of 0.0189 is a high-fidelity edit: refusal directions were removed with minimal collateral damage to the model's option-scoring behaviour. Refusals on the harmful evaluation set drop from 99/100 to 63/100 — the smallest absolute reduction in this batch, and the reason to read the number carefully. This is a heavily task-specialised model with a narrow output space, so the remaining refusals are concentrated in exactly the categories a decision model should be reluctant about. Score distribution quality on your own schema is worth measuring before you ship it; the Decision Index leaderboard is at clef-evals.workers-ai-mle.workers.dev.

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-00001-of-00004.safetensors`	4.60 GB
`model-00002-of-00004.safetensors`	4.65 GB
`model-00003-of-00004.safetensors`	4.61 GB
`model-00004-of-00004.safetensors`	3.66 GB

BF16, ~9B. 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

Still under abliteration — quant ladder not published yet. This checkpoint is an intermediate Heretic trial, kept public while a better one is being produced. The refusal suppression here is real but incomplete: it clears the cases this trial happened to capture, not the category. Expect a stronger variant to replace it.

Only the F16 GGUF is published so far. The Q4_K_M / Q5_K_M / Q6_K / Q8_0 ladder will be added once the model is finalised — nothing about the download is different, there are just fewer files to choose from today. If you need a smaller footprint now, quantise the F16 yourself:
llama-quantize clef-flash-heretic-F16.gguf clef-flash-heretic-Q4_K_M.gguf Q4_K_M

File	Format	Size
`clef-flash-heretic-F16.gguf`	GGUF F16	16.69 GB

Qwen3.5 architecture (qwen35) - loads natively in llama.cpp / Ollama / LM Studio / Jan.

Run llama-serve -hf saidutta69/clef-flash-heretic:Q4_K_M once the ladder lands; for now point llama.cpp at the F16 file directly.

Quickstart

# llama.cpp
llama serve -hf saidutta69/clef-flash-heretic

# transformers
from transformers import AutoProcessor, AutoModelForImageTextToText

model_name = "saidutta69/clef-flash-heretic"
model = AutoModelForImageTextToText.from_pretrained(model_name, dtype="auto", device_map="auto")
processor = AutoProcessor.from_pretrained(model_name)

messages = [{"role": "user", "content": [
    {"type": "image", "image": "https://example.com/screenshot.png"},
    {"type": "text", "text": "Classify this screenshot for spam, phishing, or benign."},
]}]
inputs = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=True,
                                       return_dict=True, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=512)
print(processor.decode(out[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))

The Clef-Flash API is fully compatible with Jev and SystemOne.

What this model does

Clef-Flash is not a chat model. Given a state (text, JSON, image, or video) and a schema of typed questions, it returns a probability for every allowed option of every question in a single forward pass. There is no free-form text generation and no output parsing.

Backbone: Qwen3.5-9B with its vision encoder, stored as standard sharded safetensors
Joint schema head: a small transformer head that reads the backbone's final hidden states, routes evidence from the state to each question, and scores all options of all questions jointly
Input: text, JSON, images, or video
Output: per-option probabilities — no parsing required

For the larger sibling, see Cloudflare/clef. Background: Clef decision models on the Cloudflare blog.

Model details


Architecture	`Qwen3_5ForConditionalGeneration` (hybrid linear-attention + full-attention, multimodal)
Parameters	~9B
Layers / heads	32 layers (24 linear-attention + 8 full-attention every 4th), 16 attention heads, 4 KV heads, head dim 256
Hidden / intermediate	4096 / 12288
Position embedding	mRoPE (interleaved, sections 11/11/10), partial rotary 0.25, theta = 10,000,000
Context length	262,144
Vocab	248,320
Precision	bfloat16
Base model	Cloudflare/clef-flash, post-trained from Qwen/Qwen3.5-9B

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. Decision models are typically deployed as classifiers in front of other systems, so removing refusals here widens what your pipeline will score without adding any judgement about the score. You are responsible for how you deploy it and what you act on its output.