Instructions to use zai-org/GLM-4.5V-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zai-org/GLM-4.5V-FP8 with Transformers:

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

pipe = pipeline("image-text-to-text", model="zai-org/GLM-4.5V-FP8")
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("zai-org/GLM-4.5V-FP8")
model = AutoModelForMultimodalLM.from_pretrained("zai-org/GLM-4.5V-FP8", 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]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use zai-org/GLM-4.5V-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zai-org/GLM-4.5V-FP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zai-org/GLM-4.5V-FP8",
		"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/zai-org/GLM-4.5V-FP8

SGLang

How to use zai-org/GLM-4.5V-FP8 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 "zai-org/GLM-4.5V-FP8" \
    --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": "zai-org/GLM-4.5V-FP8",
		"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 "zai-org/GLM-4.5V-FP8" \
        --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": "zai-org/GLM-4.5V-FP8",
		"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 zai-org/GLM-4.5V-FP8 with Docker Model Runner:
```
docker model run hf.co/zai-org/GLM-4.5V-FP8
```

zRzRzRzRzRzRzR commited on Oct 25, 2025

Commit

5c16395

1 Parent(s): d7278ee

update for new format config of transformers lib / sglang lib

Browse files

Files changed (2) hide show

config.json +10 -18
generation_config.json +1 -1

config.json CHANGED Viewed

@@ -3,15 +3,16 @@
     "Glm4vMoeForConditionalGeneration"
   ],
   "model_type": "glm4v_moe",
-  "rope_scaling": {
-    "rope_type": "default",
-    "mrope_section": [
-      8,
-      12,
-      12
-    ]
-  },
   "text_config": {
     "pad_token_id": 151329,
     "vocab_size": 151552,
     "eos_token_id": [
@@ -19,9 +20,6 @@
       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,
@@ -31,7 +29,6 @@
     "initializer_range": 0.02,
     "intermediate_size": 10944,
     "max_position_embeddings": 65536,
-    "model_type": "glm4v_moe_text",
     "moe_intermediate_size": 1408,
     "n_group": 1,
     "n_routed_experts": 128,
@@ -43,7 +40,7 @@
     "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": [
@@ -58,11 +55,6 @@
     "use_cache": true,
     "use_qk_norm": false
   },
-  "torch_dtype": "bfloat16",
-  "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,

     "Glm4vMoeForConditionalGeneration"
   ],
   "model_type": "glm4v_moe",
+  "image_start_token_id": 151339,
+  "image_end_token_id": 151340,
+  "video_start_token_id": 151341,
+  "video_end_token_id": 151342,
+  "image_token_id": 151363,
+  "video_token_id": 151364,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
   "text_config": {
+    "model_type": "glm4v_moe_text",
     "pad_token_id": 151329,
     "vocab_size": 151552,
     "eos_token_id": [
       151336,
       151338
     ],
     "head_dim": 128,
     "attention_bias": true,
     "attention_dropout": 0.0,
     "initializer_range": 0.02,
     "intermediate_size": 10944,
     "max_position_embeddings": 65536,
     "moe_intermediate_size": 1408,
     "n_group": 1,
     "n_routed_experts": 128,
     "num_key_value_heads": 8,
     "partial_rotary_factor": 0.5,
     "rms_norm_eps": 1e-05,
+    "dtype": "bfloat16",
     "rope_scaling": {
       "rope_type": "default",
       "mrope_section": [
     "use_cache": true,
     "use_qk_norm": false
   },
   "vision_config": {
     "attention_bias": false,
     "attention_dropout": 0.0,

generation_config.json CHANGED Viewed

@@ -10,5 +10,5 @@
   "temperature": 1.0,
   "top_k": 1,
   "top_p": 0.0001,
-  "transformers_version": "4.55.0.dev"
 }

   "temperature": 1.0,
   "top_k": 1,
   "top_p": 0.0001,
+  "transformers_version": "4.57.1"
 }