Instructions to use AEON-7/supergemma4-26b-dflash-pilot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AEON-7/supergemma4-26b-dflash-pilot with Transformers:

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

pipe = pipeline("text-generation", model="AEON-7/supergemma4-26b-dflash-pilot")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("AEON-7/supergemma4-26b-dflash-pilot")
model = AutoModel.from_pretrained("AEON-7/supergemma4-26b-dflash-pilot")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AEON-7/supergemma4-26b-dflash-pilot with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AEON-7/supergemma4-26b-dflash-pilot"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AEON-7/supergemma4-26b-dflash-pilot",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AEON-7/supergemma4-26b-dflash-pilot

SGLang

How to use AEON-7/supergemma4-26b-dflash-pilot 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 "AEON-7/supergemma4-26b-dflash-pilot" \
    --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": "AEON-7/supergemma4-26b-dflash-pilot",
		"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 "AEON-7/supergemma4-26b-dflash-pilot" \
        --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": "AEON-7/supergemma4-26b-dflash-pilot",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AEON-7/supergemma4-26b-dflash-pilot with Docker Model Runner:
```
docker model run hf.co/AEON-7/supergemma4-26b-dflash-pilot
```

SuperGemma4-26B DFlash Draft (pilot / PoC)

This is a proof-of-concept DFlash block-diffusion drafter trained against AEON-7/supergemma4-26b-abliterated-multimodal-nvfp4 (the NVFP4-quantized SuperGemma4 26B Abliterated Multimodal model, bf16 twin).

What is this?

A small draft model used for speculative decoding: instead of the big 26B target generating one token per step, the drafter proposes multiple tokens in parallel using block diffusion, and the target verifies them in a single pass. This can 2-3× generation throughput once the drafter is accurate enough.

This release is a pilot (5K samples, 1 epoch, ~28 min on 1× RTX PRO 6000 Blackwell). Top-1 match rate with the target is only ~5.8%, too low to actually speed up generation. The artifact exists to validate the full training + export + deployment pipeline end-to-end. See Roadmap below.

Architecture

Field	Value
Type	DFlash block-diffusion drafter (Qwen3-style)
Layers	5
Hidden	2816 (matches target)
Heads	22 attention / 22 KV
Head dim	128 (vLLM-compatible)
Intermediate	9728
Vocab	262144
Max pos	262144
Block size	8
Target layer anchors	[1, 8, 14, 20, 27]
Parameters	~570M
Dtype	bfloat16

Training

Field	Value
Target	SuperGemma4 26B (bf16, transformers 5.5.4 layout)
Data	`HuggingFaceH4/ultrachat_200k` train_sft, first 5000 conversations
Seq length	2048
Optimizer	AdamW (fused)
LR	6e-4 (linear decay, 50 warmup steps)
Epochs	1
Steps	5000 (bs=1, grad_accum=1)
Precision	bf16 mixed
Hardware	1× NVIDIA RTX PRO 6000 Blackwell Server Edition (96 GB)
Wall time	27:48
Loss (final step)	~5.9 (noisy; distillation + self-logit)
Train acc @ step 5000	5.79% (parallel_0_step_0 top-1)

Training infra notes

Built with NVIDIA/TensorRT-Model-Optimizer#1211 (DFlash training mode, merged in modelopt 0.43.0rc2.dev). Required two local patches:

EagleTrainerWithAccLog._save override to save drafter-only (1.2 GB) instead of the full 50 GB frozen target + drafter tree — stock HF Trainer would OOM the filesystem.
modeling_gemma4.py line 2027 — bypass the mm_token_type_ids required when training check for text-only training.

Deployment with vLLM

vllm serve AEON-7/supergemma4-26b-abliterated-multimodal-nvfp4 \
    --speculative-config '{
        "method":"draft_model",
        "model":"AEON-7/supergemma4-26b-dflash-pilot",
        "num_speculative_tokens":5
    }' \
    --quantization modelopt \
    --max-model-len 65536

⚠️ With only 5.8% top-1, expect negative speedup (verification overhead swamps any gain). This pilot is for plumbing validation, not perf.

Roadmap

This pilot proves the training stack. To make it actually fast:

Stage	Data	Epochs	Expected top-1	ETA
Pilot (this)	5K	1	5.8%	28 min × 1 GPU
Small	50K	3	~25%	~15 hr × 1 GPU
Medium	500K	3	~55%	~6 days × 1 GPU (or 18 hr × 8 GPUs)
Production	2M	5-10	70-80%	~1 week × 8 GPUs