Instructions to use puchuneko/GLM-4-32B-0414-Z1-SLERP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use puchuneko/GLM-4-32B-0414-Z1-SLERP with Transformers:

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

pipe = pipeline("text-generation", model="puchuneko/GLM-4-32B-0414-Z1-SLERP")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("puchuneko/GLM-4-32B-0414-Z1-SLERP")
model = AutoModelForCausalLM.from_pretrained("puchuneko/GLM-4-32B-0414-Z1-SLERP", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use puchuneko/GLM-4-32B-0414-Z1-SLERP with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "puchuneko/GLM-4-32B-0414-Z1-SLERP"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "puchuneko/GLM-4-32B-0414-Z1-SLERP",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/puchuneko/GLM-4-32B-0414-Z1-SLERP

SGLang

How to use puchuneko/GLM-4-32B-0414-Z1-SLERP 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 "puchuneko/GLM-4-32B-0414-Z1-SLERP" \
    --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": "puchuneko/GLM-4-32B-0414-Z1-SLERP",
		"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 "puchuneko/GLM-4-32B-0414-Z1-SLERP" \
        --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": "puchuneko/GLM-4-32B-0414-Z1-SLERP",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use puchuneko/GLM-4-32B-0414-Z1-SLERP with Docker Model Runner:
```
docker model run hf.co/puchuneko/GLM-4-32B-0414-Z1-SLERP
```

GLM-4-32B-0414-Z1-SLERP

A SLERP merge of GLM-4-32B-0414 (instruct) and GLM-Z1-32B-0414 (reasoning) at t=0.3 (~70% instruct / 30% reasoning). No Korean fine-tuning — this is an experimental base artifact, shared transparently.

TL;DR (honest)

On GSM8K (5-shot, 300 samples) this merge scores 94.0% vs 88.3% for its instruct parent — a +5.7pp gain (~2.4 sigma, statistically significant). It absorbs some of the reasoning parent's math skill while keeping the instruct parent's concise answering. This is the only benchmark run. Not a SOTA claim.

Results

Model	GSM8K (5-shot)	n	stderr
This merge (SLERP t=0.3)	0.940	300	+/-0.014
GLM-4-32B-0414 (instruct parent)	0.883	300	+/-0.019
GLM-Z1-32B-0414 (reasoning parent)	0.43*	100	+/-0.05

*The reasoning parent's low score is an evaluation artifact: its long chain-of-thought is truncated at the default generation length — not its true ability.

Recipe

merge_method: slerp
base_model: zai-org/GLM-4-32B-0414
models:
  - model: zai-org/GLM-Z1-32B-0414
parameters:
  t: 0.3
dtype: bfloat16

Made with mergekit. Note: task-vector methods (dare_ties / ties with a base) collapsed this instruct+reasoning pair into incoherent multilingual/code output; only SLERP (direct interpolation, no base subtraction) yielded a coherent model.

Limitations

Only GSM8K evaluated — no general, safety, or Korean benchmarks.
Instruct parent diluted 30%; other capabilities may regress.
No Korean fine-tuning (future work).
Transparent reproducible reference, not a production/SOTA model.

Attribution

GLM-4-32B-0414 / GLM-Z1-32B-0414 (c) Zhipu AI (Z.ai), MIT License. Merged with mergekit (Arcee AI).

Downloads last month: 368

Safetensors

Model size

33B params

Tensor type

BF16

Model tree for puchuneko/GLM-4-32B-0414-Z1-SLERP

zai-org/GLM-4-32B-0414

zai-org/GLM-Z1-32B-0414

Merge model

this model