Instructions to use PYTHAI/GLM-5.3-fork with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PYTHAI/GLM-5.3-fork with Transformers:

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

pipe = pipeline("text-generation", model="PYTHAI/GLM-5.3-fork")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PYTHAI/GLM-5.3-fork")
model = AutoModelForCausalLM.from_pretrained("PYTHAI/GLM-5.3-fork", 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 PYTHAI/GLM-5.3-fork with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PYTHAI/GLM-5.3-fork"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PYTHAI/GLM-5.3-fork",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PYTHAI/GLM-5.3-fork

SGLang

How to use PYTHAI/GLM-5.3-fork 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 "PYTHAI/GLM-5.3-fork" \
    --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": "PYTHAI/GLM-5.3-fork",
		"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 "PYTHAI/GLM-5.3-fork" \
        --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": "PYTHAI/GLM-5.3-fork",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PYTHAI/GLM-5.3-fork with Docker Model Runner:
```
docker model run hf.co/PYTHAI/GLM-5.3-fork
```

GLM-5.3-fork / FORK.json

Gregory-L

pointer fork of zai-org/GLM-5.3@aca966e4e027: licence, config, tokenizer, code; no weights

c28f709 verified 12 days ago

Raw

History Blame Contribute Delete

1.97 kB

	{
	"kind": "licence-locked pointer fork",
	"source_repo": "zai-org/GLM-5.3",
	"source_url": "https://huggingface.co/zai-org/GLM-5.3",
	"source_commit": "aca966e4e02791568aa6a4ced368624b3d897f42",
	"forked_at_utc": "2026-09-13T23:55:35Z",
	"licence_tag": "other",
	"licence_file": {
	"path": "LICENSE",
	"bytes": 4263,
	"sha256": "96e1622099fc9d6b70c9760f007d99e66d7497eec636b63c60fe208401e9170c"
	},
	"weights_copied": false,
	"weights_not_copied": {
	"files": 141,
	"bytes": 755632050320
	},
	"parameters": 753329940480,
	"load_weights_with": "from_pretrained('zai-org/GLM-5.3', revision='aca966e4e02791568aa6a4ced368624b3d897f42')",
	"files": [
	{
	"path": "LICENSE",
	"bytes": 4263,
	"sha256": "96e1622099fc9d6b70c9760f007d99e66d7497eec636b63c60fe208401e9170c"
	},
	{
	"path": "README.md",
	"bytes": 14209,
	"sha256": "ed1c0a4563c437a32f8953d637a1db9bd831de1b24bd3062a5ace9e04340b1cf"
	},
	{
	"path": "chat_template.jinja",
	"bytes": 10734,
	"sha256": "3740abcea51c45830cb3ca562084ad5fb2ef53589376f73332e9886f93ade41c"
	},
	{
	"path": "config.json",
	"bytes": 29464,
	"sha256": "3ac72612095574542f7fff847ada8e59d9199dd8af44bdf625d7e02615572e69"
	},
	{
	"path": "generation_config.json",
	"bytes": 194,
	"sha256": "ac76b43d8683d3b930126870fc8be73d8679308fe752fa1f381096d8354f6a55"
	},
	{
	"path": "model.safetensors.index.json",
	"bytes": 11359251,
	"sha256": "e0fe7f28c1f853d4824e4d796374e3dacf1fe470988773952c79b063768134bf"
	},
	{
	"path": "tokenizer.json",
	"bytes": 20217442,
	"sha256": "19e773648cb4e65de8660ea6365e10acca112d42a854923df93db4a6f333a82d"
	},
	{
	"path": "tokenizer_config.json",
	"bytes": 761,
	"sha256": "98b1271574f41abf89427ae2dda030d94dc9478f0edc5a8bd240db213c6fd5fc"
	}
	],
	"why": "preserve the licence terms of this exact commit and pin the revision; the weights stay at the source and are addressed by commit sha",
	"forked_by": "mindX (PYTHAI) via the node token"
	}