Instructions to use tacos4me/Step-3.5-Flash-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tacos4me/Step-3.5-Flash-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="tacos4me/Step-3.5-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("tacos4me/Step-3.5-Flash-NVFP4", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tacos4me/Step-3.5-Flash-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tacos4me/Step-3.5-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": "tacos4me/Step-3.5-Flash-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tacos4me/Step-3.5-Flash-NVFP4

SGLang

How to use tacos4me/Step-3.5-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 "tacos4me/Step-3.5-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": "tacos4me/Step-3.5-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 "tacos4me/Step-3.5-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": "tacos4me/Step-3.5-Flash-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tacos4me/Step-3.5-Flash-NVFP4 with Docker Model Runner:
```
docker model run hf.co/tacos4me/Step-3.5-Flash-NVFP4
```

MTP Layers

by AMead10 - opened Mar 10

Discussion

AMead10

Mar 10

Could you add back in the MTP layers? even if unquant, would be nice to have, especially for running on DGX Spark, which can load the model but is lacking in the speed department

tacos4me

Owner Mar 11

Could you add back in the MTP layers? even if unquant, would be nice to have, especially for running on DGX Spark, which can load the model but is lacking in the speed department

Surely, should have some time soon.

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