Instructions to use saidutta69/DeepSeek-R1-Qwen3-8B-heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use saidutta69/DeepSeek-R1-Qwen3-8B-heretic with Transformers:

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

pipe = pipeline("text-generation", model="saidutta69/DeepSeek-R1-Qwen3-8B-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/DeepSeek-R1-Qwen3-8B-heretic")
model = AutoModelForCausalLM.from_pretrained("saidutta69/DeepSeek-R1-Qwen3-8B-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/DeepSeek-R1-Qwen3-8B-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/DeepSeek-R1-Qwen3-8B-heretic:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf saidutta69/DeepSeek-R1-Qwen3-8B-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/DeepSeek-R1-Qwen3-8B-heretic:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf saidutta69/DeepSeek-R1-Qwen3-8B-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/DeepSeek-R1-Qwen3-8B-heretic:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf saidutta69/DeepSeek-R1-Qwen3-8B-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/DeepSeek-R1-Qwen3-8B-heretic:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf saidutta69/DeepSeek-R1-Qwen3-8B-heretic:Q4_K_M

Use Docker

docker model run hf.co/saidutta69/DeepSeek-R1-Qwen3-8B-heretic:Q4_K_M

LM Studio
Jan

vLLM

How to use saidutta69/DeepSeek-R1-Qwen3-8B-heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "saidutta69/DeepSeek-R1-Qwen3-8B-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/DeepSeek-R1-Qwen3-8B-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/saidutta69/DeepSeek-R1-Qwen3-8B-heretic:Q4_K_M

SGLang

How to use saidutta69/DeepSeek-R1-Qwen3-8B-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/DeepSeek-R1-Qwen3-8B-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/DeepSeek-R1-Qwen3-8B-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/DeepSeek-R1-Qwen3-8B-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/DeepSeek-R1-Qwen3-8B-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use saidutta69/DeepSeek-R1-Qwen3-8B-heretic with Ollama:
```
ollama run hf.co/saidutta69/DeepSeek-R1-Qwen3-8B-heretic:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use saidutta69/DeepSeek-R1-Qwen3-8B-heretic with Docker Model Runner:
```
docker model run hf.co/saidutta69/DeepSeek-R1-Qwen3-8B-heretic:Q4_K_M
```

Lemonade

How to use saidutta69/DeepSeek-R1-Qwen3-8B-heretic with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull saidutta69/DeepSeek-R1-Qwen3-8B-heretic:Q4_K_M

Run and chat with the model

lemonade run user.DeepSeek-R1-Qwen3-8B-heretic-Q4_K_M

List all available models

lemonade list

Atomic Chat

DeepSeek-R1-Qwen3-8B-heretic

A decensored variant of deepseek-ai/DeepSeek-R1-0528-Qwen3-8B, produced with Heretic v1.4.0 (directional ablation / "abliteration"). DeepSeek's R1-0528 distill of Qwen3-8B keeps its native <think> reasoning traces; refusal behaviour is suppressed here via targeted weight edits to the attention output and MLP down-projections rather than fine-tuning, so the R1 reasoning tuning is left largely intact.

Who this is for: developers who want uncensored R1-style reasoning at 8B - visible <think> traces, refusals down from 87/100 to 3/100 at a KL of just 0.0082, one of the tightest edits in this collection. At 8B with 128K context it runs on a single consumer GPU via GGUF.

Runs on your gaming PC

Full GGUF ladder included - pick the quant that fits your card:

Your GPU	Recommended quant	Weights
RTX 4090 / 5090 (24 GB)	Q8_0	8.11 GB
RTX 4080 / 5080 / 4060 Ti 16G (16 GB)	Q6_K	6.26 GB
RTX 3060 / 4070 / 5070 (12 GB)	Q5_K_M	5.45 GB
RTX 4060 / 3070 (8 GB)	Q4_K_M	4.68 GB
CPU-only / Apple Silicon	Q4_K_M	4.68 GB

Weights only, at this model's native 8.2B size; add ~1 GB per 32K of context. OOM? Drop one quant level. Headroom to spare? Go one up.

Abliteration parameters

Trial 98 of a 200-trial Heretic run (seed 750233003).

Parameter	Value
direction_index	19.81
attn.o_proj.max_weight	1.44
attn.o_proj.max_weight_position	21.05
attn.o_proj.min_weight	1.38
attn.o_proj.min_weight_distance	20.94
mlp.down_proj.max_weight	1.43
mlp.down_proj.max_weight_position	25.81
mlp.down_proj.min_weight	1.19
mlp.down_proj.min_weight_distance	20.76

Performance

Metric	This model	Original model (deepseek-ai/DeepSeek-R1-0528-Qwen3-8B)
KL divergence	0.0082	0 (by definition)
Refusals	3/100	87/100

Refusals on the harmful evaluation set drop from 87/100 to 3/100 - effectively total removal. KL divergence of 0.0082 is one of the tightest edits in this collection, so the R1 reasoning style and formatting stay very close to the original. direction_index is a single index (19.81) rather than per-layer, which is why the refusal removal lands this completely without needing a wider edit.

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`	4.57 GB
`model-00002-of-00004.safetensors`	4.58 GB
`model-00003-of-00004.safetensors`	4.63 GB
`model-00004-of-00004.safetensors`	1.48 GB

BF16, ~8.2B parameters. 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 (F16 + Q4_K_M, Q5_K_M, Q6_K, Q8_0) produced with llama.cpp.

File	Format	Size
`DeepSeek-R1-Qwen3-8B-heretic-F16.gguf`	GGUF F16	15.26 GB
`DeepSeek-R1-Qwen3-8B-heretic-Q4_K_M.gguf`	GGUF Q4_K_M	4.68 GB
`DeepSeek-R1-Qwen3-8B-heretic-Q5_K_M.gguf`	GGUF Q5_K_M	5.45 GB
`DeepSeek-R1-Qwen3-8B-heretic-Q6_K.gguf`	GGUF Q6_K	6.26 GB
`DeepSeek-R1-Qwen3-8B-heretic-Q8_0.gguf`	GGUF Q8_0	8.11 GB

Qwen3 architecture (qwen3) - loads natively in llama.cpp / Ollama / LM Studio / Jan.

Tokenizer note: the repo's tokenizer.json was re-saved by Heretic with a Metaspace pre-tokenizer wrapper and the snapshot declares the slow LlamaTokenizer, a combination the GGUF converter rejects. The GGUFs were built with the base model's ByteLevel pre-tokenizer and Qwen2Tokenizer (vocab, merges, and all 28 added tokens verified identical; token IDs verified identical to reference Qwen3 tokenization), so the embedded qwen2 pre-tokenizer behaves exactly as the base model does.

Run llama serve -hf saidutta69/DeepSeek-R1-Qwen3-8B-heretic to pull the default quant.

Quickstart

# llama.cpp
llama serve -hf saidutta69/DeepSeek-R1-Qwen3-8B-heretic

# transformers
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "saidutta69/DeepSeek-R1-Qwen3-8B-heretic"
model = AutoModelForCausalLM.from_pretrained(model_name, dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = [{"role": "user", "content": "Prove that the square root of 2 is irrational. Show each step of the reasoning."}]
inputs = tokenizer.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=2048)
print(tokenizer.decode(out[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))

Also runnable via Ollama, LM Studio, Jan, vLLM, SGLang.

Thinking traces

This is the R1 reasoning edition - the model emits a <think>...</think> block before its answer. For latency-sensitive agent loops where you want tokens directly, use a non-thinking model from this collection instead; for hard problems that benefit from visible reasoning, this one is the right pick.

Model details


Architecture	`Qwen3ForCausalLM` (decoder-only dense transformer)
Parameters	~8.2B
Layers / heads	36 layers, 32 attention heads, 8 KV heads (GQA), head dim 128
Hidden / intermediate	4096 / 12288 (SwiGLU)
Position embedding	RoPE (YaRN, factor 4.0), theta = 1,000,000
Context length	131,072
Vocab	151,936
Precision	bfloat16
Base model	deepseek-ai/DeepSeek-R1-0528-Qwen3-8B

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. It inherits R1/Qwen3's factual limitations and biases; abliteration removes refusal directions, it doesn't add capability or judgment.

License

Inherits the mit license from the base model.

deepseek-ai/DeepSeek-R1-0528-Qwen3-8B — the base model
RACER IS OP — Heretic Models — full collection

Downloads last month: 546

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for saidutta69/DeepSeek-R1-Qwen3-8B-heretic

Base model

deepseek-ai/DeepSeek-R1-0528-Qwen3-8B

Finetuned

(67)

this model

Collection including saidutta69/DeepSeek-R1-Qwen3-8B-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 12 hours ago • 6

saidutta69
/

DeepSeek-R1-Qwen3-8B-heretic

DeepSeek-R1-Qwen3-8B-heretic

Runs on your gaming PC

Abliteration parameters

Performance

Why abliteration instead of fine-tuning

Files

Safetensors

GGUF quantizations

Quickstart

Thinking traces

Model details

Responsible use

License

Related

Model tree for saidutta69/DeepSeek-R1-Qwen3-8B-heretic

Collection including saidutta69/DeepSeek-R1-Qwen3-8B-heretic

RACER IS OP — Heretic Models