Instructions to use QuantTrio/GLM-4.5V-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantTrio/GLM-4.5V-AWQ with Transformers:

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

pipe = pipeline("image-text-to-text", model="QuantTrio/GLM-4.5V-AWQ")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("QuantTrio/GLM-4.5V-AWQ")
model = AutoModelForMultimodalLM.from_pretrained("QuantTrio/GLM-4.5V-AWQ", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use QuantTrio/GLM-4.5V-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuantTrio/GLM-4.5V-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuantTrio/GLM-4.5V-AWQ",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/QuantTrio/GLM-4.5V-AWQ

SGLang

How to use QuantTrio/GLM-4.5V-AWQ 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 "QuantTrio/GLM-4.5V-AWQ" \
    --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": "QuantTrio/GLM-4.5V-AWQ",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "QuantTrio/GLM-4.5V-AWQ" \
        --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": "QuantTrio/GLM-4.5V-AWQ",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use QuantTrio/GLM-4.5V-AWQ with Docker Model Runner:
```
docker model run hf.co/QuantTrio/GLM-4.5V-AWQ
```

GLM-4.5V-AWQ / config.json

tclf90

Update config.json

57b42d7 verified 12 months ago

Raw

History Blame Contribute Delete

3.91 kB

	{
	"name_or_path": "tclf90/GLM-4.5V-AWQ",
	"architectures": [
	"Glm4vMoeForConditionalGeneration"
	],
	"model_type": "glm4v_moe",
	"text_config": {
	"pad_token_id": 151329,
	"vocab_size": 151552,
	"eos_token_id": [
	151329,
	151336,
	151338
	],
	"image_end_token_id": 151340,
	"image_start_token_id": 151339,
	"image_token_id": 151363,
	"head_dim": 128,
	"attention_bias": true,
	"attention_dropout": 0.0,
	"first_k_dense_replace": 1,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"initializer_range": 0.02,
	"intermediate_size": 11264,
	"max_position_embeddings": 65536,
	"model_type": "glm4v_moe_text",
	"moe_intermediate_size": 1408,
	"n_group": 1,
	"n_routed_experts": 128,
	"n_shared_experts": 1,
	"norm_topk_prob": true,
	"num_attention_heads": 96,
	"num_experts_per_tok": 8,
	"num_hidden_layers": 46,
	"num_key_value_heads": 8,
	"partial_rotary_factor": 0.5,
	"rms_norm_eps": 1e-05,
	"torch_dtype": "bfloat16",
	"rope_scaling": {
	"rope_type": "default",
	"mrope_section": [
	8,
	12,
	12
	]
	},
	"rope_theta": 10000.0,
	"routed_scaling_factor": 1.0,
	"topk_group": 1,
	"use_cache": true,
	"use_qk_norm": false
	},
	"torch_dtype": "float16",
	"transformers_version": "4.55.0.dev0",
	"video_end_token_id": 151342,
	"video_start_token_id": 151341,
	"video_token_id": 151364,
	"vision_config": {
	"attention_bias": false,
	"attention_dropout": 0.0,
	"depth": 24,
	"hidden_act": "silu",
	"hidden_size": 1536,
	"image_size": 336,
	"in_channels": 3,
	"initializer_range": 0.02,
	"intermediate_size": 11264,
	"model_type": "glm4v_moe",
	"num_heads": 12,
	"out_hidden_size": 4096,
	"patch_size": 14,
	"rms_norm_eps": 1e-05,
	"spatial_merge_size": 2,
	"temporal_patch_size": 2
	},
	"quantization_config": {
	"quant_method": "awq_marlin",
	"bits": 4,
	"group_size": 128,
	"version": "gemm",
	"zero_point": true,
	"modules_to_not_convert": ["visual.", "model.embed_tokens", "model.layers.0.mlp.shared_experts.", "model.layers.1.mlp.shared_experts.", "model.layers.2.mlp.shared_experts.", "model.layers.3.mlp.shared_experts.", "model.layers.4.mlp.shared_experts.", "model.layers.5.mlp.shared_experts.", "model.layers.6.mlp.shared_experts.", "model.layers.7.mlp.shared_experts.", "model.layers.8.mlp.shared_experts.", "model.layers.9.mlp.shared_experts.", "model.layers.10.mlp.shared_experts.", "model.layers.11.mlp.shared_experts.", "model.layers.12.mlp.shared_experts.", "model.layers.13.mlp.shared_experts.", "model.layers.14.mlp.shared_experts.", "model.layers.15.mlp.shared_experts.", "model.layers.16.mlp.shared_experts.", "model.layers.17.mlp.shared_experts.", "model.layers.18.mlp.shared_experts.", "model.layers.19.mlp.shared_experts.", "model.layers.20.mlp.shared_experts.", "model.layers.21.mlp.shared_experts.", "model.layers.22.mlp.shared_experts.", "model.layers.23.mlp.shared_experts.", "model.layers.24.mlp.shared_experts.", "model.layers.25.mlp.shared_experts.", "model.layers.26.mlp.shared_experts.", "model.layers.27.mlp.shared_experts.", "model.layers.28.mlp.shared_experts.", "model.layers.29.mlp.shared_experts.", "model.layers.30.mlp.shared_experts.", "model.layers.31.mlp.shared_experts.", "model.layers.32.mlp.shared_experts.", "model.layers.33.mlp.shared_experts.", "model.layers.34.mlp.shared_experts.", "model.layers.35.mlp.shared_experts.", "model.layers.36.mlp.shared_experts.", "model.layers.37.mlp.shared_experts.", "model.layers.38.mlp.shared_experts.", "model.layers.39.mlp.shared_experts.", "model.layers.40.mlp.shared_experts.", "model.layers.41.mlp.shared_experts.", "model.layers.42.mlp.shared_experts.", "model.layers.43.mlp.shared_experts.", "model.layers.44.mlp.shared_experts.", "model.layers.45.mlp.shared_experts.", "lm_head"]
	}
	}