Instructions to use pszemraj/franken-gemma-4-dense-1b-untrained with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pszemraj/franken-gemma-4-dense-1b-untrained with Transformers:

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

pipe = pipeline("image-text-to-text", model="pszemraj/franken-gemma-4-dense-1b-untrained")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("pszemraj/franken-gemma-4-dense-1b-untrained")
model = AutoModelForMultimodalLM.from_pretrained("pszemraj/franken-gemma-4-dense-1b-untrained")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pszemraj/franken-gemma-4-dense-1b-untrained with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pszemraj/franken-gemma-4-dense-1b-untrained"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pszemraj/franken-gemma-4-dense-1b-untrained",
		"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/pszemraj/franken-gemma-4-dense-1b-untrained

SGLang

How to use pszemraj/franken-gemma-4-dense-1b-untrained 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 "pszemraj/franken-gemma-4-dense-1b-untrained" \
    --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": "pszemraj/franken-gemma-4-dense-1b-untrained",
		"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 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 "pszemraj/franken-gemma-4-dense-1b-untrained" \
        --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": "pszemraj/franken-gemma-4-dense-1b-untrained",
		"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"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use pszemraj/franken-gemma-4-dense-1b-untrained with Docker Model Runner:
```
docker model run hf.co/pszemraj/franken-gemma-4-dense-1b-untrained
```

franken-gemma-4-dense-1b: untrained

A frankenstein-init Gemma 4 (dense) image/text model with ~1b params:

assembled by weight-transplant from Gemma 3 1B (text backbone) and Gemma 4 E2B-IT (vision tower + tokenizer + processor).
Architecturally mirrors google/gemma-4-31B-it (hybrid attention head-dim, no MoE, no PLE, no shared KV) but smol

This is a trained model.. NOT!

It will not produce coherent text out of the box.
It is intended for testing fine-tuning frameworks/configurations (Axolotl, TRL, DeepSpeed, FSDP) at a 'pilot' scale
should train more easily than.. random weights though

Architecture

component	value
hidden_size	1152
intermediate_size	6912
num_hidden_layers	18 (15 sliding + 3 full, pattern 5:1)
num_attention_heads	4
num_key_value_heads	1
head_dim (sliding)	256
head_dim (global)	512
sliding_window	1024
max_position_embeddings	32768
attention_k_eq_v	True (global layers)
final_logit_softcapping	30.0
vocab_size	262148 (Gemma 4 tokenizer)

Vision tower: hidden=768, 16 layers, head_dim=64 (copied from Gemma 4 E2B-IT)

As parameter counts/modules:

=============================================================
Layer (type)                              Param #   Trainable
=============================================================
      Gemma4TextScaledWordEmbedding   301,989,888        True
      ModuleList                      490,237,440        True
      Gemma4RMSNorm                         1,152        True
      Gemma4TextRotaryEmbedding                --       False
    Gemma4TextModel                   792,228,480        True
      Gemma4VisionPatchEmbedder        16,318,464        True
      Gemma4VisionEncoder             151,046,144        True
      Gemma4VisionPooler                       --       False
    Gemma4VisionModel                 167,364,608        True
      Linear                              884,736        True
      Gemma4RMSNorm                            --       False
    Gemma4MultimodalEmbedder              884,736        True
  Gemma4Model                         960,477,824        True
  Linear                              301,989,888        True
Gemma4ForConditionalGeneration        960,477,824        True
=============================================================
Total params: 960,477,824
Trainable params: 960,477,824
Non-trainable params: --
=============================================================

frankenstein component inventory

Component	Source	Method
Text embeddings	gemma-3-1b-it	Direct copy + 4 rows mean-resized for Gemma 4 special tokens
Text MLP weights	gemma-3-1b-it	Direct copy
Sliding-attention Q/K/V/O	gemma-3-1b-it	Direct copy
Global-attention Q/K	gemma-3-1b-it	Per-head tile (256 → 512)
Global-attention O	gemma-3-1b-it	Per-head split-halves (preserves O @ V = O_old @ V_old at init)
Global-attention V	---	Dropped (attention_k_eq_v=True; V reuses K)
RMSNorm weights	gemma-3-1b-it	Convention-converted (1.0 + w)
q_norm / k_norm	gemma-3-1b-it	Rescaled by 1/√head_dim to compensate for Gemma 4's scaling=1.0
Vision tower	gemma-4-e2b-it	Direct copy
embed_vision projection	---	Fresh init (shape mismatch 768→1536 vs 768→1152)
Tokenizer + processor	gemma-4-e2b-it	Wholesale

License

Gemma Terms of Use apply. This is a derivative of Gemma 3 1B and Gemma 4 E2B-IT weights. See https://ai.google.dev/gemma/terms

Downloads last month: 5

Safetensors

Model size

1.0B params

Tensor type

BF16

Model tree for pszemraj/franken-gemma-4-dense-1b-untrained

Base model

google/gemma-3-1b-pt

Finetuned

google/gemma-3-1b-it

Finetuned

(562)

this model

Finetunes

1 model