Instructions to use harrisonvanderbyl/GLM-4.6-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use harrisonvanderbyl/GLM-4.6-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="harrisonvanderbyl/GLM-4.6-FP8")

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

tokenizer = AutoTokenizer.from_pretrained("harrisonvanderbyl/GLM-4.6-FP8")
model = AutoModelForCausalLM.from_pretrained("harrisonvanderbyl/GLM-4.6-FP8", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use harrisonvanderbyl/GLM-4.6-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "harrisonvanderbyl/GLM-4.6-FP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "harrisonvanderbyl/GLM-4.6-FP8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/harrisonvanderbyl/GLM-4.6-FP8

SGLang

How to use harrisonvanderbyl/GLM-4.6-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 "harrisonvanderbyl/GLM-4.6-FP8" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "harrisonvanderbyl/GLM-4.6-FP8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "harrisonvanderbyl/GLM-4.6-FP8" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "harrisonvanderbyl/GLM-4.6-FP8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use harrisonvanderbyl/GLM-4.6-FP8 with Docker Model Runner:
```
docker model run hf.co/harrisonvanderbyl/GLM-4.6-FP8
```

harrisonvanderbyl commited on Jun 29

Commit

c0cee68

verified ·

1 Parent(s): 529af1c

Upload model-00013.safetensors with huggingface_hub

Browse files

Files changed (1) hide show

model-00013.safetensors +3 -0

model-00013.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8bbcae937442c0aef9a3f3fc54d73ee288b4dc8448f64bc3790de23254fd5526
+size 3937553728