Instructions to use allura-org/GLM4-32B-Neon-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use allura-org/GLM4-32B-Neon-v2 with Transformers:

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

pipe = pipeline("text-generation", model="allura-org/GLM4-32B-Neon-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("allura-org/GLM4-32B-Neon-v2")
model = AutoModelForCausalLM.from_pretrained("allura-org/GLM4-32B-Neon-v2", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use allura-org/GLM4-32B-Neon-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "allura-org/GLM4-32B-Neon-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "allura-org/GLM4-32B-Neon-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/allura-org/GLM4-32B-Neon-v2

SGLang

How to use allura-org/GLM4-32B-Neon-v2 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 "allura-org/GLM4-32B-Neon-v2" \
    --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": "allura-org/GLM4-32B-Neon-v2",
		"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 "allura-org/GLM4-32B-Neon-v2" \
        --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": "allura-org/GLM4-32B-Neon-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use allura-org/GLM4-32B-Neon-v2 with Docker Model Runner:
```
docker model run hf.co/allura-org/GLM4-32B-Neon-v2
```

Model has trouble understanding who it's supposed to talk as.

by BigBeavis - opened May 25, 2025

Discussion

BigBeavis

May 25, 2025

Not sure if it's because of text completion instead of chat completion. If it wants to respond as user's persona, you can't convince it otherwise. It's like it gets confused and lost in the text.

inflatebot

Allura org May 25, 2025

Give it a shot in chat completion (and if it works, see if switching to text completion but mimicking the sampler settings keeps it fixed.) We suspect there may some fuckery with the GLM4 template.

AuriAetherwiing

Allura org May 26, 2025

To debug it - please ensure that you are using the exact template, as shown in the repo, or ST presets if you are using it, check if your backend incorrectly adds BOS (this model doesn't have it, [gMASK]<sop> is not a BOS token config-wise) - some versions of llama.cpp and tabbyAPI add <|endoftext|> as BOS which is incorrect. Also, if you are using KoboldCPP - please try using recent version of llama.cpp server instead.

Henk717

Dec 12, 2025

KoboldCpp actually has fixes for GLM that make it work in text completions making it a better choice than llamacpp server.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment