Instructions to use AtomicChat/Ling-3.0-flash-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AtomicChat/Ling-3.0-flash-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="AtomicChat/Ling-3.0-flash-NVFP4", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("AtomicChat/Ling-3.0-flash-NVFP4", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AtomicChat/Ling-3.0-flash-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AtomicChat/Ling-3.0-flash-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AtomicChat/Ling-3.0-flash-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AtomicChat/Ling-3.0-flash-NVFP4

SGLang

How to use AtomicChat/Ling-3.0-flash-NVFP4 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 "AtomicChat/Ling-3.0-flash-NVFP4" \
    --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": "AtomicChat/Ling-3.0-flash-NVFP4",
		"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 "AtomicChat/Ling-3.0-flash-NVFP4" \
        --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": "AtomicChat/Ling-3.0-flash-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AtomicChat/Ling-3.0-flash-NVFP4 with Docker Model Runner:
```
docker model run hf.co/AtomicChat/Ling-3.0-flash-NVFP4
```

Safetensors Version

by iSkye - opened about 23 hours ago

Discussion

iSkye

about 23 hours ago

Hi, could you also please Release a safetensors version for vllm?

worthant

Atomic Chat org about 22 hours ago

Hi @iSkye ! Absolutely, I'm working on imatrix-aware NVFP4 version to make it a bit smarter and will release safetensors here as soon as i will get proper numbers. Stay tuned!

iSkye changed discussion title from Safetensors Versio to Safetensors Version about 22 hours ago

worthant

Atomic Chat org about 21 hours ago

•

edited about 19 hours ago

*now there is a support for it in inclusionAI/vllm-ling-v3, great

worthant

Atomic Chat org about 16 hours ago

Hey @iSkye ! It's ready :D

You can find NVFP4 in safetensors format right in this repo, and in GGUF format in the other one.

iSkye

about 16 hours ago

Many thanks :)
Will try it later on the spark

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