Instructions to use aimeri/spoomplesmaxx-glm4-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aimeri/spoomplesmaxx-glm4-32B with Transformers:

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

pipe = pipeline("text-generation", model="aimeri/spoomplesmaxx-glm4-32B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aimeri/spoomplesmaxx-glm4-32B")
model = AutoModelForCausalLM.from_pretrained("aimeri/spoomplesmaxx-glm4-32B", 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 aimeri/spoomplesmaxx-glm4-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aimeri/spoomplesmaxx-glm4-32B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aimeri/spoomplesmaxx-glm4-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aimeri/spoomplesmaxx-glm4-32B

SGLang

How to use aimeri/spoomplesmaxx-glm4-32B 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 "aimeri/spoomplesmaxx-glm4-32B" \
    --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": "aimeri/spoomplesmaxx-glm4-32B",
		"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 "aimeri/spoomplesmaxx-glm4-32B" \
        --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": "aimeri/spoomplesmaxx-glm4-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use aimeri/spoomplesmaxx-glm4-32B with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for aimeri/spoomplesmaxx-glm4-32B to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for aimeri/spoomplesmaxx-glm4-32B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for aimeri/spoomplesmaxx-glm4-32B to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="aimeri/spoomplesmaxx-glm4-32B",
    max_seq_length=2048,
)

Docker Model Runner
How to use aimeri/spoomplesmaxx-glm4-32B with Docker Model Runner:
```
docker model run hf.co/aimeri/spoomplesmaxx-glm4-32B
```

aimeri commited on Mar 8

Commit

a25fa0b

verified ·

1 Parent(s): 32338c3

(Trained with Unsloth)

Browse files

Files changed (2) hide show

config.json +28 -0
tokenizer_config.json +3 -2

config.json ADDED Viewed

	@@ -0,0 +1,28 @@

+{
+    "architectures": [
+        "Glm4ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "torch_dtype": "bfloat16",
+    "eos_token_id": 151329,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 6144,
+    "initializer_range": 0.02,
+    "intermediate_size": 23040,
+    "max_position_embeddings": 32768,
+    "model_name": "/content/aimeri/spoomplesmaxx-base-glm4-32b",
+    "model_type": "glm4",
+    "num_attention_heads": 48,
+    "num_hidden_layers": 61,
+    "num_key_value_heads": 2,
+    "pad_token_id": 151343,
+    "partial_rotary_factor": 0.5,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 10000.0,
+    "tie_word_embeddings": false,
+    "unsloth_version": "2026.3.3",
+    "use_cache": true,
+    "vocab_size": 151552
+}

tokenizer_config.json CHANGED Viewed

@@ -149,5 +149,6 @@
   "pad_token": "<|PAD_TOKEN|>",
   "padding_side": "left",
   "remove_space": false,
-  "tokenizer_class": "PreTrainedTokenizerFast"
-}

   "pad_token": "<|PAD_TOKEN|>",
   "padding_side": "left",
   "remove_space": false,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "chat_template": "{%- for message in messages %}\n    {%- if message.role == 'system' %}\n        {{- '<|system|>' + messages[0].content + '<|endoftext|>' + '\\n' }}\n    {%- elif message.role == 'user' %}\n        {{- '<|user|>' + message.content + '<|endoftext|>' + '\\n' }}\n    {%- elif message.role == 'assistant' %}\n        {{- '<|assistant|>' + message.content + '<|endoftext|>' + '\\n' }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|assistant|>' }}\n{%- endif %}"
+}