Instructions to use zai-org/LongWriter-glm4-9b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zai-org/LongWriter-glm4-9b with Transformers:

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

pipe = pipeline("text-generation", model="zai-org/LongWriter-glm4-9b", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("zai-org/LongWriter-glm4-9b", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use zai-org/LongWriter-glm4-9b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zai-org/LongWriter-glm4-9b"
# 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/LongWriter-glm4-9b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zai-org/LongWriter-glm4-9b

SGLang

How to use zai-org/LongWriter-glm4-9b 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/LongWriter-glm4-9b" \
    --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/LongWriter-glm4-9b",
		"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/LongWriter-glm4-9b" \
        --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/LongWriter-glm4-9b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zai-org/LongWriter-glm4-9b with Docker Model Runner:
```
docker model run hf.co/zai-org/LongWriter-glm4-9b
```

Fix for missing _extract_past_from_model_output (cpu, text-generation-webui)

#12

by Kefpull - opened Jul 18, 2025

Discussion

Kefpull

Jul 18, 2025

•

edited Jul 18, 2025

Heya folks,
For text-generation-webui on cpu if you try downloading this model out of the box you will get an error. Through a little bit of time and searching chinese forums you need to add this to modeling_chatglm.py: (into line 971):

def _extract_past_from_model_output(self, outputs: ModelOutput, standardize_cache_format: bool = False):
     past_key_values = None
     cache_name = None
 if "past_key_values" in outputs:
    past_key_values = outputs.past_key_values
    cache_name = "past_key_values"
 elif "mems" in outputs:
    past_key_values = outputs.mems
    cache_name = "mems"
 elif "past_buckets_states" in outputs:
    past_key_values = outputs.past_buckets_states
    cache_name = "past_buckets_states"

if standardize_cache_format and hasattr(self, "_convert_to_standard_cache"):
    batch_size = outputs.logits.shape[0]
    past_key_values = self._convert_to_standard_cache(past_key_values, batch_size=batch_size)

return cache_name, past_key_values

This will probably be mostly for myself because I will forget I did this but if it helps anyone else then that would be great

source: https://blog.csdn.net/qq_43749831/article/details/146022858

Kefpull changed discussion title from Fix for missing _extract_past_from_model_output (cpu, text-generation-webuit) to Fix for missing _extract_past_from_model_output (cpu, text-generation-webui) Jul 18, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment