Instructions to use INCModel2/GLM-5.2-MXFP4-Mixed-CT-AutoRound with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use INCModel2/GLM-5.2-MXFP4-Mixed-CT-AutoRound with Transformers:

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

pipe = pipeline("text-generation", model="INCModel2/GLM-5.2-MXFP4-Mixed-CT-AutoRound")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("INCModel2/GLM-5.2-MXFP4-Mixed-CT-AutoRound")
model = AutoModelForCausalLM.from_pretrained("INCModel2/GLM-5.2-MXFP4-Mixed-CT-AutoRound")
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 INCModel2/GLM-5.2-MXFP4-Mixed-CT-AutoRound with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "INCModel2/GLM-5.2-MXFP4-Mixed-CT-AutoRound"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "INCModel2/GLM-5.2-MXFP4-Mixed-CT-AutoRound",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/INCModel2/GLM-5.2-MXFP4-Mixed-CT-AutoRound

SGLang

How to use INCModel2/GLM-5.2-MXFP4-Mixed-CT-AutoRound 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 "INCModel2/GLM-5.2-MXFP4-Mixed-CT-AutoRound" \
    --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": "INCModel2/GLM-5.2-MXFP4-Mixed-CT-AutoRound",
		"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 "INCModel2/GLM-5.2-MXFP4-Mixed-CT-AutoRound" \
        --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": "INCModel2/GLM-5.2-MXFP4-Mixed-CT-AutoRound",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use INCModel2/GLM-5.2-MXFP4-Mixed-CT-AutoRound with Docker Model Runner:
```
docker model run hf.co/INCModel2/GLM-5.2-MXFP4-Mixed-CT-AutoRound
```

GLM-5.2-MXFP4-Mixed-CT-AutoRound / README.md

xinhe

Update README.md

e276e22 verified about 12 hours ago

preview code

Raw

History Blame Contribute Delete

3.4 kB

	---
	tags:
	- auto-round
	license: other
	license_name: mit
	library_name: transformers
	base_model:
	- zai-org/GLM-5.2
	---
	## Model Details

	This model is a MXFP4 and MXFP8 mixed model of [zai-org/GLM-5.2](https://huggingface.co/zai-org/GLM-5.2) generated by [intel/auto-round](https://github.com/intel/auto-round) with RTN mode. The model format is Compressed Tensor (CT), fully compatible with vLLM.

	<!-- Not real data
	\| GLM-5.2 \| gsm8k \| mmlu \| piqa \| hellaswag \| avg \| ratio \|
	\|-------------------\|---------\|---------\|---------\|------------\|--------\|--------\|
	\| Raw \| 0.9386 \| 0.8898 \| 0.8471 \| 0.7747 \| 0.863 \| \|
	\| INCModel2/GLM-5.2-MXFP4-Mixed-LLMC \| 0.9439 \| 0.8847 \| 0.8411 \| 0.7646 \| 0.859 \| 99.54% \|
	-->

	## vllm Infernece Example

	~~~bash
	vllm serve INCModel2/GLM-5.2-MXFP4-Mixed-LLMC \
	--kv-cache-dtype fp8_e4m3 \
	--tensor-parallel-size 4 \
	--tool-call-parser glm47 \
	--enable-auto-tool-choice \
	--reasoning-parser glm45 \
	--served-model-name glm \
	--max-model-len 4096
	~~~

	~~~bash
	curl http://localhost:8000/v1/chat/completions -H "Content-Type: application/json" -d ' {
	"model": "glm",
	"messages": [
	{"role": "system", "content": "You are a helpful assistant."},
	{"role": "user", "content": "Write code to fine-tune an LLM."}
	],
	"temperature": 1,
	"max_tokens": 2048
	} '

	~~~


	## Generate the Model

	RTN version

	commit: d1ddb5c9ba5f79adb8bbc124b8d438e6bafcb707 (high accuracy)
	~~~bash
	auto-round zai-org/GLM-5.2 --model_free --format llm_compressor --scheme MXFP8 --output_dir /workspace/models/zai-org/GLM-5.2-MXFP4-MXFP8 --ignore_layers layers.0,layers.1,layers.2,indexer.weights_proj,indexer.wk --layer_config "{mlp.experts:{scheme:MXFP4}}"
	~~~

	commit: e56290ac3ba50b56cd9ea66423a3f4c9004848ee
	~~~bash
	auto-round zai-org/GLM-5.2 --model_free --format llm_compressor --scheme MXFP8 --output_dir /workspace/models/zai-org/GLM-5.2-MXFP4-MXFP8 --ignore_layers indexer.weights_proj,indexer.wk --layer_config "{mlp.experts:{scheme:MXFP4}}"
	~~~


	## Ethical Considerations and Limitations

	The model can produce factually incorrect output, and should not be relied on to produce factually accurate information. Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs.

	Therefore, before deploying any applications of the model, developers should perform safety testing.

	## Caveats and Recommendations

	Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.

	Here are a couple of useful links to learn more about Intel's AI software:

	- [Intel Neural Compressor](https://github.com/intel/neural-compressor)

	## Disclaimer

	The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes.

	## Cite

	@article{cheng2023optimize, title={Optimize weight rounding via signed gradient descent for the quantization of llms}, author={Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi}, journal={arXiv preprint arXiv:2309.05516}, year={2023} }

	[arxiv](https://arxiv.org/abs/2309.05516) [github](https://github.com/intel/auto-round)