Instructions to use TitanML/GLM-5.2-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TitanML/GLM-5.2-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="TitanML/GLM-5.2-FP8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TitanML/GLM-5.2-FP8")
model = AutoModelForCausalLM.from_pretrained("TitanML/GLM-5.2-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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TitanML/GLM-5.2-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TitanML/GLM-5.2-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": "TitanML/GLM-5.2-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TitanML/GLM-5.2-FP8

SGLang

How to use TitanML/GLM-5.2-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 "TitanML/GLM-5.2-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": "TitanML/GLM-5.2-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 "TitanML/GLM-5.2-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": "TitanML/GLM-5.2-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TitanML/GLM-5.2-FP8 with Docker Model Runner:
```
docker model run hf.co/TitanML/GLM-5.2-FP8
```

jamesdborin commited on Jun 17

Commit

566e087

verified ·

1 Parent(s): 5c392d4

Update chat_template.jinja

Browse files

Files changed (1) hide show

chat_template.jinja +2 -2

chat_template.jinja CHANGED Viewed

@@ -90,7 +90,7 @@ For each function call, output the function name and arguments within the follow
 {%- endif %}
 {%- if m.content is string -%}
     {{- '<tool_response>' + m.content + '</tool_response>' -}}
-{%- elif m.content is iterable and m.content is not mapping and m.content and m.content.0.type == "tool_reference" -%}
     {{- '<tool_response><tools>\n' -}}
     {% for tr in m.content %}
         {%- for tool in tools -%}
@@ -103,7 +103,7 @@ For each function call, output the function name and arguments within the follow
         {%- endfor -%}
     {%- endfor -%}
     {{- '</tools></tool_response>' -}}
-{%- elif m.content is iterable and m.content is not mapping and m.content and m.content.0 is mapping and m.content.0.output is defined -%}
     {%- for tr in m.content -%}
         {{- '<tool_response>' + tr.output + '</tool_response>' -}}
     {%- endfor -%}

 {%- endif %}
 {%- if m.content is string -%}
     {{- '<tool_response>' + m.content + '</tool_response>' -}}
+{%- elif m.content is iterable and m.content is not mapping and m.content and m.content[0]type == "tool_reference" -%}
     {{- '<tool_response><tools>\n' -}}
     {% for tr in m.content %}
         {%- for tool in tools -%}
         {%- endfor -%}
     {%- endfor -%}
     {{- '</tools></tool_response>' -}}
+{%- elif m.content is iterable and m.content is not mapping and m.content and m.content[0] is mapping and m.content.0.output is defined -%}
     {%- for tr in m.content -%}
         {{- '<tool_response>' + tr.output + '</tool_response>' -}}
     {%- endfor -%}