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

Libraries

How to use whitecircle/GLM-4.7-Flash-Coder with Transformers:

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

pipe = pipeline("text-generation", model="whitecircle/GLM-4.7-Flash-Coder")
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("whitecircle/GLM-4.7-Flash-Coder")
model = AutoModelForCausalLM.from_pretrained("whitecircle/GLM-4.7-Flash-Coder", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use whitecircle/GLM-4.7-Flash-Coder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "whitecircle/GLM-4.7-Flash-Coder"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "whitecircle/GLM-4.7-Flash-Coder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/whitecircle/GLM-4.7-Flash-Coder

SGLang

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

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

q4 +mtp

by victor11sk - opened 22 days ago

Discussion

victor11sk

22 days ago

any plans to quant and add mtp?

MrDevolver

4 days ago

MTP or some alternative solution would be perfect for GLM 4.7 Flash model. Honestly, I loved the original model, but it was too slow for me despite being a MoE. It's been a while so maybe the inference was slightly improved since then, but honestly when done just right, prediction models can make a big difference in speed, so I usually look for alternatives that come with them already bundled in.

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