Instructions to use naaviii/glm-prun-4bit-32g-nextj with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use naaviii/glm-prun-4bit-32g-nextj with Transformers:

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

pipe = pipeline("text-generation", model="naaviii/glm-prun-4bit-32g-nextj")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("naaviii/glm-prun-4bit-32g-nextj")
model = AutoModelForCausalLM.from_pretrained("naaviii/glm-prun-4bit-32g-nextj")
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

vLLM

How to use naaviii/glm-prun-4bit-32g-nextj with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "naaviii/glm-prun-4bit-32g-nextj"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "naaviii/glm-prun-4bit-32g-nextj",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/naaviii/glm-prun-4bit-32g-nextj

SGLang

How to use naaviii/glm-prun-4bit-32g-nextj 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 "naaviii/glm-prun-4bit-32g-nextj" \
    --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": "naaviii/glm-prun-4bit-32g-nextj",
		"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 "naaviii/glm-prun-4bit-32g-nextj" \
        --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": "naaviii/glm-prun-4bit-32g-nextj",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use naaviii/glm-prun-4bit-32g-nextj with Docker Model Runner:
```
docker model run hf.co/naaviii/glm-prun-4bit-32g-nextj
```

Prerequisite

VLLM_USE_PRECOMPILED=1 pip install git+https://github.com/vllm-project/vllm.git@main
pip install git+https://github.com/huggingface/transformers.git

Basic Usage

vllm serve naaviii/glm-prun-4bit-32g-nextj \
     --tool-call-parser glm47 \
     --reasoning-parser glm45 \
     --enable-auto-tool-choice \

vLLM

using pip (must use pypi.org as the index url):

pip install -U vllm --pre --index-url https://pypi.org/simple --extra-index-url https://wheels.vllm.ai/nightly
pip install git+https://github.com/huggingface/transformers.git

vLLM

vllm serve naaviii/glm-prun-4bit-32g-nextj \
     --tensor-parallel-size 4 \
     --speculative-config.method mtp \
     --speculative-config.num_speculative_tokens 1 \
     --tool-call-parser glm47 \
     --reasoning-parser glm45 \
     --enable-auto-tool-choice \

Downloads last month: 2

Safetensors

Model size

31B params

Tensor type

I64

F32

I32

BF16