Instructions to use inference-optimization/GLM-5.2-0.8B-A0.8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inference-optimization/GLM-5.2-0.8B-A0.8B with Transformers:

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

pipe = pipeline("text-generation", model="inference-optimization/GLM-5.2-0.8B-A0.8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("inference-optimization/GLM-5.2-0.8B-A0.8B")
model = AutoModelForCausalLM.from_pretrained("inference-optimization/GLM-5.2-0.8B-A0.8B", 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 inference-optimization/GLM-5.2-0.8B-A0.8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "inference-optimization/GLM-5.2-0.8B-A0.8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "inference-optimization/GLM-5.2-0.8B-A0.8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/inference-optimization/GLM-5.2-0.8B-A0.8B

SGLang

How to use inference-optimization/GLM-5.2-0.8B-A0.8B 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 "inference-optimization/GLM-5.2-0.8B-A0.8B" \
    --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": "inference-optimization/GLM-5.2-0.8B-A0.8B",
		"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 "inference-optimization/GLM-5.2-0.8B-A0.8B" \
        --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": "inference-optimization/GLM-5.2-0.8B-A0.8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use inference-optimization/GLM-5.2-0.8B-A0.8B with Docker Model Runner:
```
docker model run hf.co/inference-optimization/GLM-5.2-0.8B-A0.8B
```

GLM-5.2-0.8B-A0.8B / README.md

kylesayrs

Upload folder using huggingface_hub

210c4dc verified about 1 month ago

preview code

Raw

History Blame Contribute Delete

2.67 kB

	---
	license: mit
	base_model:
	- zai-org/GLM-5.2
	library_name: transformers
	---

	# GLM-5.2-0.8B-A0.8B

	This is a tiny version of [zai-org/GLM-5.2](https://huggingface.co/zai-org/GLM-5.2) created for testing and development.

	## Model Details

	- Base Model: zai-org/GLM-5.2
	- Architecture: glm_moe_dsa (GLM MoE with DeepSeek Sparse Attention)
	- Total Parameters: 0.85B
	- Activated Parameters: ~0.77B

	## Configuration Changes

	The following parameters were reduced from the original model:

	\| Parameter \| Original \| Tiny \|
	\|-----------\|----------\|------\|
	\| num_hidden_layers \| 78 \| 6 \|
	\| hidden_size \| 6144 \| 2048 \|
	\| intermediate_size \| 12288 \| 4096 \|
	\| num_attention_heads \| 64 \| 16 \|
	\| num_key_value_heads \| 64 \| 16 \|
	\| n_routed_experts \| 256 \| 8 \|
	\| num_experts_per_tok \| 8 \| 2 \|
	\| moe_intermediate_size \| 2048 \| 512 \|
	\| kv_lora_rank \| 512 \| 128 \|
	\| q_lora_rank \| 2048 \| 512 \|
	\| v_head_dim \| 256 \| 128 \|
	\| index_n_heads \| 32 \| 8 \|
	\| index_head_dim \| 128 \| 64 \|
	\| first_k_dense_replace \| 3 \| 2 \|

	## Checkpoint Structure

	Single safetensors file containing 194 tensors in float32. Layers 0-1 have dense MLP, layers 2-5 have MoE MLP. Layers 0-2 have full DSA indexer weights, layers 3-5 use shared indexer.

	## Usage

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer

	model = AutoModelForCausalLM.from_pretrained("inference-optimization/GLM-5.2-0.8B-A0.8B", device_map="auto")
	tokenizer = AutoTokenizer.from_pretrained("inference-optimization/GLM-5.2-0.8B-A0.8B")

	input_ids = tokenizer("According to all known laws", return_tensors="pt").input_ids.to(model.device)
	output = model.generate(input_ids, max_new_tokens=20)
	print(tokenizer.decode(output[0]))
	```

	## Creation Process

	1. Inspected original GLM-5.2 config (78 layers, 256 experts, hidden_size=6144)
	2. Reduced all dimensions to target ~1B parameters while preserving architecture
	3. Created model with float32 dtype for training stability
	4. Fine-tuned on copypasta dataset to perplexity ~1.0
	5. Validated checkpoint structure matches original model naming conventions
	6. Validated model loads, inferences, and generates correctly

	## Validation Output

	```
	Success: 1.0000379085540771 <= 10.0
	Generating sample text:
	According to all known laws of aviation, there is no way a bee should be able to fly.
	```

	## Notes

	- The model uses float32 dtype (original uses bfloat16) to ensure proper initialization and training of the tiny model
	- Architecture preserves both dense and sparse MLP layer types, MLA attention with compressed Q/KV, and DSA indexer with full/shared patterns
	- The model has been fine-tuned on a toy dataset and is intended for testing purposes only