Instructions to use zai-org/GLM-4.7-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zai-org/GLM-4.7-Flash with Transformers:

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

pipe = pipeline("text-generation", model="zai-org/GLM-4.7-Flash")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zai-org/GLM-4.7-Flash")
model = AutoModelForCausalLM.from_pretrained("zai-org/GLM-4.7-Flash")
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]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use zai-org/GLM-4.7-Flash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zai-org/GLM-4.7-Flash"
# 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-4.7-Flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zai-org/GLM-4.7-Flash

SGLang

How to use zai-org/GLM-4.7-Flash 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-4.7-Flash" \
    --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-4.7-Flash",
		"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-4.7-Flash" \
        --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-4.7-Flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zai-org/GLM-4.7-Flash with Docker Model Runner:
```
docker model run hf.co/zai-org/GLM-4.7-Flash
```

There is no module or parameter named 'model.layers.5.mlp.gate.e_score_correction_bias' in TransformersMoEForCausalLM

#34

by divinefeng - opened Jan 22

Discussion

divinefeng

Jan 22

Loading safetensors checkpoint shards: 0% Completed | 0/48 [00:00<?, ?it/s]
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] WorkerProc failed to start.
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] Traceback (most recent call last):
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] File "/opt/conda/envs/vllm0122/lib/python3.10/site-packages/vllm/v1/executor/multiproc_executor.py", line 720, in worker_main
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] worker = WorkerProc(*args, **kwargs)
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] File "/opt/conda/envs/vllm0122/lib/python3.10/site-packages/vllm/v1/executor/multiproc_executor.py", line 560, in init
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] self.worker.load_model()
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] File "/opt/conda/envs/vllm0122/lib/python3.10/site-packages/vllm/v1/worker/gpu_worker.py", line 274, in load_model
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] self.model_runner.load_model(eep_scale_up=eep_scale_up)
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] File "/opt/conda/envs/vllm0122/lib/python3.10/site-packages/vllm/v1/worker/gpu_model_runner.py", line 3827, in load_model
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] self.model = model_loader.load_model(
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] File "/opt/conda/envs/vllm0122/lib/python3.10/site-packages/vllm/model_executor/model_loader/base_loader.py", line 58, in load_model
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] self.load_weights(model, model_config)
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] File "/opt/conda/envs/vllm0122/lib/python3.10/site-packages/vllm/model_executor/model_loader/default_loader.py", line 288, in load_weights
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] loaded_weights = model.load_weights(self.get_all_weights(model_config, model))
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] File "/opt/conda/envs/vllm0122/lib/python3.10/site-packages/vllm/model_executor/models/transformers/base.py", line 492, in load_weights
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] return loader.load_weights(weights, mapper=self.hf_to_vllm_mapper)
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] File "/opt/conda/envs/vllm0122/lib/python3.10/site-packages/vllm/model_executor/model_loader/online_quantization.py", line 173, in patched_model_load_weights
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] return original_load_weights(auto_weight_loader, weights, mapper=mapper)
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] File "/opt/conda/envs/vllm0122/lib/python3.10/site-packages/vllm/model_executor/models/utils.py", line 335, in load_weights
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] autoloaded_weights = set(self._load_module("", self.module, weights))
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] File "/opt/conda/envs/vllm0122/lib/python3.10/site-packages/vllm/model_executor/models/utils.py", line 288, in _load_module
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] yield from self._load_module(
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] File "/opt/conda/envs/vllm0122/lib/python3.10/site-packages/vllm/model_executor/models/utils.py", line 288, in _load_module
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] yield from self._load_module(
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] File "/opt/conda/envs/vllm0122/lib/python3.10/site-packages/vllm/model_executor/models/utils.py", line 288, in _load_module
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] yield from self._load_module(
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] [Previous line repeated 2 more times]
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] File "/opt/conda/envs/vllm0122/lib/python3.10/site-packages/vllm/model_executor/models/utils.py", line 319, in _load_module
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] raise ValueError(msg)
(Worker_TP0 pid=125587) ERROR 01-22 18:25:44 [multiproc_executor.py:749] ValueError: There is no module or parameter named 'model.layers.5.mlp.gate.e_score_correction_bias' in TransformersMoEForCausalLM

xiaofengmao

Jan 22

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