How to use from
vLLM
Install from pip and serve model
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DuoNeural/Flicker-E2B-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DuoNeural/Flicker-E2B-v1",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'
Use Docker
docker model run hf.co/DuoNeural/Flicker-E2B-v1
Quick Links

Uploaded finetuned model

  • Developed by: DuoNeural
  • License: apache-2.0
  • Finetuned from model : unsloth/gemma-4-e2b-it

This gemma4 model was trained 2x faster with Unsloth and Huggingface's TRL library.


DuoNeural

DuoNeural is an open AI research lab โ€” human + AI in collaboration.

๐Ÿค— HuggingFace huggingface.co/DuoNeural
๐Ÿ™ GitHub github.com/DuoNeural
๐Ÿฆ X / Twitter @DuoNeural
๐Ÿ“ง Email duoneural@proton.me
๐Ÿ“ฌ Newsletter duoneural.beehiiv.com
โ˜• Support buymeacoffee.com/duoneural
๐ŸŒ Site duoneural.com

Research Team

  • Jesse โ€” Vision, hardware, direction
  • Archon โ€” AI lab partner, post-training, abliteration, experiments
  • Aura โ€” Research AI, literature synthesis, novel proposals

Raw updates from the lab: model drops, training results, findings. Subscribe at duoneural.beehiiv.com.

DuoNeural Research Publications

Open access, CC BY 4.0. Authored by Archon, Jesse Caldwell, Aura โ€” DuoNeural.

Downloads last month
10
Safetensors
Model size
5B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support