Instructions to use Blackfrost-AI/GLM-5.2-ABLITERATED-BF16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Blackfrost-AI/GLM-5.2-ABLITERATED-BF16 with Transformers:

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

pipe = pipeline("text-generation", model="Blackfrost-AI/GLM-5.2-ABLITERATED-BF16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Blackfrost-AI/GLM-5.2-ABLITERATED-BF16")
model = AutoModelForCausalLM.from_pretrained("Blackfrost-AI/GLM-5.2-ABLITERATED-BF16")
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 Blackfrost-AI/GLM-5.2-ABLITERATED-BF16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Blackfrost-AI/GLM-5.2-ABLITERATED-BF16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Blackfrost-AI/GLM-5.2-ABLITERATED-BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Blackfrost-AI/GLM-5.2-ABLITERATED-BF16

SGLang

How to use Blackfrost-AI/GLM-5.2-ABLITERATED-BF16 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 "Blackfrost-AI/GLM-5.2-ABLITERATED-BF16" \
    --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": "Blackfrost-AI/GLM-5.2-ABLITERATED-BF16",
		"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 "Blackfrost-AI/GLM-5.2-ABLITERATED-BF16" \
        --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": "Blackfrost-AI/GLM-5.2-ABLITERATED-BF16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Blackfrost-AI/GLM-5.2-ABLITERATED-BF16 with Docker Model Runner:
```
docker model run hf.co/Blackfrost-AI/GLM-5.2-ABLITERATED-BF16
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

GLM-5.2-ABLITERATED — BF16 STILL TESTING WILL, I WILL GIVE UPDATE IN 48 HOURS ALONG WITH REVIEWING REQUEST

Private archive / insurance artifact. This repository holds a BF16 conversion of a GLM-5.2 (glm_moe_dsa) model that had previously undergone abliteration (refusal removal). It exists as a durable archival backup. It is untested and not intended for release or production use.

What this is


Architecture	`glm_moe_dsa` (`GlmMoeDsaForCausalLM`) — GLM MoE with DeepSeek-style sparse attention (MLA + indexer)
Precision	BF16 (`safetensors`, 337 shards, ≈1.4 TB on disk)
Total parameters	~753B (GLM-5.2 architecture), Mixture-of-Experts
Layers	78 (`first_k_dense_replace=3` → first 3 dense, rest MoE)
Hidden size	6144
Experts	256 routed, top-8 active per token, + 1 shared expert
Attention	64 heads, MLA (`kv_lora_rank=512`, `q_lora_rank=2048`) + sparse indexer (DSA)
MoE FFN	`moe_intermediate_size=2048`; dense `intermediate_size=12288`
Vocab	154,880
Max context	1,048,576 (1M) positions
MTP	Multi-token-prediction layers present (`num_nextn_predict_layers`)

Chat template (chat_template.jinja), tokenizer, config.json, and generation_config.json are all included. The chat template preserves the GLM control tokens (<think>, <|observation|>, reasoning-effort), so a serving stack that honors the packaged template will not fall back to a generic one.

Provenance

This artifact is a BF16 conversion of a GLM-5.2 model that had previously undergone abliteration (refusal removal). No fine-tuning, additional abliteration, or training was performed.
Abliteration status: the refusal removal is inherited from the source model and was not re-verified on this artifact. Do not assume a specific refusal rate for this file.

Intended use

Primary: archival backup.
Not intended as a served model as-is: at ≈1.4 TB it requires very large multi-GPU hosts.

Serving notes

glm_moe_dsa needs a serving stack with GLM sparse-MLA / DSA support.
Recommended parsers when a GLM stack is used: --reasoning-parser glm45, --tool-call-parser glm47. For a clean refusal test, disable reasoning snap-back (enable_thinking=false).

Limitations & responsible use

Uncensored: abliteration removes many refusal behaviors. There are no additional safety guarantees on this artifact. Use it only where you are authorized to, and apply your own safeguards.
Untested / archival: correctness, coherence, and refusal behavior have not been validated on this specific BF16 file.
License is inherited from the upstream GLM base model — consult and comply with the upstream license before any use or redistribution.

Blackfrost AI — private archive. This card documents an intermediate research artifact and is intentionally conservative about what the weights are.

Downloads last month: -

Safetensors

Model size

753B params

Tensor type

BF16

Model tree for Blackfrost-AI/GLM-5.2-ABLITERATED-BF16

Base model

zai-org/GLM-5.2

Finetuned

(16)

this model

Quantizations

1 model