Instructions to use helixdouble/GLM-5.1-FP8-Abliterated-v2-SoftRefusal-Research-Checkpoint with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use helixdouble/GLM-5.1-FP8-Abliterated-v2-SoftRefusal-Research-Checkpoint with Transformers:

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

pipe = pipeline("text-generation", model="helixdouble/GLM-5.1-FP8-Abliterated-v2-SoftRefusal-Research-Checkpoint")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("helixdouble/GLM-5.1-FP8-Abliterated-v2-SoftRefusal-Research-Checkpoint")
model = AutoModelForMultimodalLM.from_pretrained("helixdouble/GLM-5.1-FP8-Abliterated-v2-SoftRefusal-Research-Checkpoint")
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 helixdouble/GLM-5.1-FP8-Abliterated-v2-SoftRefusal-Research-Checkpoint with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "helixdouble/GLM-5.1-FP8-Abliterated-v2-SoftRefusal-Research-Checkpoint"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "helixdouble/GLM-5.1-FP8-Abliterated-v2-SoftRefusal-Research-Checkpoint",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/helixdouble/GLM-5.1-FP8-Abliterated-v2-SoftRefusal-Research-Checkpoint

SGLang

How to use helixdouble/GLM-5.1-FP8-Abliterated-v2-SoftRefusal-Research-Checkpoint 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 "helixdouble/GLM-5.1-FP8-Abliterated-v2-SoftRefusal-Research-Checkpoint" \
    --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": "helixdouble/GLM-5.1-FP8-Abliterated-v2-SoftRefusal-Research-Checkpoint",
		"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 "helixdouble/GLM-5.1-FP8-Abliterated-v2-SoftRefusal-Research-Checkpoint" \
        --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": "helixdouble/GLM-5.1-FP8-Abliterated-v2-SoftRefusal-Research-Checkpoint",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use helixdouble/GLM-5.1-FP8-Abliterated-v2-SoftRefusal-Research-Checkpoint with Docker Model Runner:
```
docker model run hf.co/helixdouble/GLM-5.1-FP8-Abliterated-v2-SoftRefusal-Research-Checkpoint
```

GLM-5.1-FP8 Abliterated v2 - Soft-Refusal Research Checkpoint

[update:] Follow-up evaluation found this v2 regex bake actually outperformed the later v3 label-colored checkpoint at removing "I cannot..." refusal openers — the v3 direction diluted the refusal signal by blending it with an orthogonal soft-disclaimer component. v2 is the preferred checkpoint for refusal removal and is being retained as such.

This is a research checkpoint, not a fully benchmarked release. It is an FP8 direct-weight abliteration of GLM-5.1-FP8, retained because it remains the strongest refusal-removal bake in this study.

Current Status

This checkpoint appears to have substantially reduced hard refusal behavior, but it has not cleanly removed the broader safety/disclaimer style prior.

Note on prompt counts: the refusal direction was extracted from 1000 balanced prompt pairs (see What Changed / Provenance). The "100" figures below are a small evaluation smoke test only — not the calibration/extraction set. Don't read the 100 as the size of the abliteration data.

Latest local smoke evaluation, run on 2026-06-14:

Model path evaluated: /workspace/glm5-fp8-ablit_t0_mw2.0
Prompt set: 100 harmful evaluation prompts (smoke-test set, distinct from the 1000-pair extraction)
Generation cap: 100 tokens
Harmless/control prompts: not run in this pass
Judge: regex fallback only, not an external LLM judge
Hard regex refusals: 7/100
Full prompt/response samples saved locally for review

Additional provisional taxonomy from the saved 100 outputs:

hard refusal proxy: 7
soft-disclaimer-only proxy: 29
disclaimer-plus-answer proxy: 47
direct-answer proxy: 12
unclear/short proxy: 5

Important caveat: the 100-prompt run used a 100-token generation cap, so many completions are visibly cut off. These numbers should be treated as directional triage only, not a publishable evaluation.

What Changed

This checkpoint is a direct FP8 weight bake at strength mw2.0, using a 1000 balanced prompt-pair refusal-direction extraction pass. It is not healed. A healing pass may be run later.

The current result should be understood as:

successful at reducing hard refusals and removing refusal openers;
still somewhat heavy on disclaimers and ethical/legal preambles;
not yet evaluated on benign utility or coherence at adequate breadth;
not yet externally benchmarked.

Recommended Use

This is the preferred checkpoint for refusal-removal research and comparison:

it outperforms the v3 label-colored checkpoint at removing "I cannot..." openers;
useful for collecting residual soft-disclaimer examples;
useful for benchmarking runtime behavior across inference stacks.

Treat it as a research checkpoint rather than a final, fully benchmarked release.

Next Planned Work

The next pass should avoid blindly increasing strength. The better plan is to collect residual examples from the 100-output batch and split them into:

hard refusals;
soft-disclaimer-only responses;
disclaimer-plus-answer responses;
direct answers;
broken/collapsed outputs.

If v3 is run, it should target the residual refusal/disclaimer style cases specifically, ideally with a benign control set to check collateral damage.

Provenance

Base model: zai-org/GLM-5.1-FP8
Checkpoint type: FP8 direct-weight bake
Current bake strength: mw2.0
Direction extraction: 1000 balanced prompt pairs
Healing: none
Evaluation status: provisional local smoke eval only

Originally uploaded 2026-06-14; retained as the preferred refusal-removal checkpoint.

Downloads last month: 66

Safetensors

Model size

754B params

Tensor type

F32

BF16

F8_E4M3

Model tree for helixdouble/GLM-5.1-FP8-Abliterated-v2-SoftRefusal-Research-Checkpoint

Base model

zai-org/GLM-5.1-FP8

Quantized

(5)

this model