Instructions to use RekklesAI/LogicFlow-Gemma-3-27b-thinking with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RekklesAI/LogicFlow-Gemma-3-27b-thinking with Transformers:

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

pipe = pipeline("image-text-to-text", model="RekklesAI/LogicFlow-Gemma-3-27b-thinking")
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("RekklesAI/LogicFlow-Gemma-3-27b-thinking")
model = AutoModelForMultimodalLM.from_pretrained("RekklesAI/LogicFlow-Gemma-3-27b-thinking", device_map="auto")
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 RekklesAI/LogicFlow-Gemma-3-27b-thinking with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RekklesAI/LogicFlow-Gemma-3-27b-thinking"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RekklesAI/LogicFlow-Gemma-3-27b-thinking",
		"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/RekklesAI/LogicFlow-Gemma-3-27b-thinking

SGLang

How to use RekklesAI/LogicFlow-Gemma-3-27b-thinking 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 "RekklesAI/LogicFlow-Gemma-3-27b-thinking" \
    --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": "RekklesAI/LogicFlow-Gemma-3-27b-thinking",
		"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 "RekklesAI/LogicFlow-Gemma-3-27b-thinking" \
        --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": "RekklesAI/LogicFlow-Gemma-3-27b-thinking",
		"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 RekklesAI/LogicFlow-Gemma-3-27b-thinking with Docker Model Runner:
```
docker model run hf.co/RekklesAI/LogicFlow-Gemma-3-27b-thinking
```

Where is tokenizer.model ?

by testamentaddress01 - opened Sep 8, 2025

Discussion

testamentaddress01

Sep 8, 2025

When I downloaded this model, I received an error message stating that tokenizer.model was missing. Please check the hash value of the uploaded file just to be sure. Please also upload tokenizer.model.

RekklesAI

Owner Sep 12, 2025

Hi, thanks for raising this.
This repo only includes tokenizer.json (the JSON format tokenizer), which works fine with vLLM and newer versions of Hugging Face Transformers. That’s why it runs without issues on my side.

If your environment is still looking for tokenizer.model, it’s likely because you are using an older version of Transformers that expects the SentencePiece file. Updating to the latest transformers should solve the problem.

Alternatively, you can copy the tokenizer.model file from the official Gemma-3-27B repo (google/gemma-3-27b-it) into this folder if you need compatibility.

Hope this helps!

RekklesAI

Owner Sep 12, 2025

I’ve just uploaded a copy of the tokenizer.model file from the official Gemma-3-27B repo to this repository.

testamentaddress01

Sep 12, 2025

Thank you for uploading tokenizer.model.

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