Instructions to use zai-org/GLM-5.1-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zai-org/GLM-5.1-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="zai-org/GLM-5.1-FP8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zai-org/GLM-5.1-FP8")
model = AutoModelForCausalLM.from_pretrained("zai-org/GLM-5.1-FP8", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use zai-org/GLM-5.1-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-5.1-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-5.1-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zai-org/GLM-5.1-FP8

SGLang

How to use zai-org/GLM-5.1-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-5.1-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-5.1-FP8",
		"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 "zai-org/GLM-5.1-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-5.1-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zai-org/GLM-5.1-FP8 with Docker Model Runner:
```
docker model run hf.co/zai-org/GLM-5.1-FP8
```

Add a response template and fix tool calls with null content

by Rocketknight1 HF Staff - opened 10 days ago

base: refs/heads/main

←

from: refs/pr/8

Discussion Files changed

+49

-2

Files changed (2) hide show

chat_template.jinja +1 -1
tokenizer_config.json +48 -1

chat_template.jinja CHANGED Viewed

@@ -42,7 +42,7 @@ For each function call, output the function name and arguments within the follow
                 {{- item }}
             {%- endif -%}
         {%- endfor -%}
-    {%- else -%}
         {{- content }}
     {%- endif -%}
 {%- endmacro -%}

                 {{- item }}
             {%- endif -%}
         {%- endfor -%}
+    {%- elif content is not none -%}
         {{- content }}
     {%- endif -%}
 {%- endmacro -%}

tokenizer_config.json CHANGED Viewed

@@ -29,5 +29,52 @@
   "pad_token": "<|endoftext|>",
   "padding_side": "left",
   "remove_space": false,
-  "tokenizer_class": "TokenizersBackend"
 }

   "pad_token": "<|endoftext|>",
   "padding_side": "left",
   "remove_space": false,
+  "tokenizer_class": "TokenizersBackend",
+  "response_template": {
+    "defaults": {
+      "role": "assistant"
+    },
+    "start_anchor": "<|assistant|>",
+    "fields": {
+      "reasoning_content": {
+        "open_pattern": "<think>|(?=</think>)",
+        "close_pattern": "</think>|(?=<tool_call>)",
+        "content": "text",
+        "content_args": {
+          "strip": true
+        },
+        "repeats": true,
+        "join": ""
+      },
+      "tool_calls": {
+        "open_pattern": "\\s*<tool_call>\\s*(?P<name>[^<]*?)\\s*(?=<arg_key>|</tool_call>)",
+        "close": "</tool_call>",
+        "repeats": true,
+        "content": "xml-inline",
+        "content_args": {
+          "tag_pattern": "<arg_key>\\s*(?P<key>.*?)\\s*</arg_key>\\s*<arg_value>(?P<value>.*?)</arg_value>"
+        },
+        "transform": {
+          "type": "function",
+          "function": {
+            "name": "{name}",
+            "arguments": "{content}"
+          }
+        }
+      },
+      "content": {
+        "close": [
+          "<|user|>",
+          "<|observation|>",
+          "<|endoftext|>"
+        ],
+        "content": "text",
+        "content_args": {
+          "strip": false
+        },
+        "repeats": true,
+        "join": ""
+      }
+    }
+  }
 }