Instructions to use Johnblick187/grok-zero-fp8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Johnblick187/grok-zero-fp8 with Transformers:

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

pipe = pipeline("text-generation", model="Johnblick187/grok-zero-fp8", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Johnblick187/grok-zero-fp8", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Johnblick187/grok-zero-fp8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Johnblick187/grok-zero-fp8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Johnblick187/grok-zero-fp8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Johnblick187/grok-zero-fp8

SGLang

How to use Johnblick187/grok-zero-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 "Johnblick187/grok-zero-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": "Johnblick187/grok-zero-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 "Johnblick187/grok-zero-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": "Johnblick187/grok-zero-fp8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Johnblick187/grok-zero-fp8 with Docker Model Runner:
```
docker model run hf.co/Johnblick187/grok-zero-fp8
```

⚠️!WARNING!⚠️

MODEL IS CURRENTLY IN VERIFICATION/TESTING PHASE. PLEASE DO NOT DOWNLOAD UNLESS YOU HAVE SUFFICIENT HARDWARE AND ARE WILLING TO RUN INFERENCE AND RETURN THE RESULTS AS IT WILL LIKELY EITHER NOT WORK OR BE INCOHERENT. THIS REPO IS ONLY FOR CHECKPOINTING PURPOSES RIGHT NOW

Downloads last month: 25

Safetensors

Model size

270B params

Tensor type

BF16

F8_E4M3