Instructions to use OddTheGreat/Mars_27B_V.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OddTheGreat/Mars_27B_V.1 with Transformers:

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

pipe = pipeline("image-text-to-text", model="OddTheGreat/Mars_27B_V.1")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("OddTheGreat/Mars_27B_V.1")
model = AutoModelForImageTextToText.from_pretrained("OddTheGreat/Mars_27B_V.1")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OddTheGreat/Mars_27B_V.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OddTheGreat/Mars_27B_V.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OddTheGreat/Mars_27B_V.1",
		"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/OddTheGreat/Mars_27B_V.1

SGLang

How to use OddTheGreat/Mars_27B_V.1 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 "OddTheGreat/Mars_27B_V.1" \
    --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": "OddTheGreat/Mars_27B_V.1",
		"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 "OddTheGreat/Mars_27B_V.1" \
        --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": "OddTheGreat/Mars_27B_V.1",
		"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 OddTheGreat/Mars_27B_V.1 with Docker Model Runner:
```
docker model run hf.co/OddTheGreat/Mars_27B_V.1
```

Model VRAM Usage

by LyraNovaHeart - opened Jan 6

Discussion

LyraNovaHeart

Jan 6

Hey Hey! I saw at the bottom of your readme that you had trouble fitting it into your GPUs VRAM.

You can fit it in 16GB, it just takes a bit of tweaking

1. Use an IQ4_XS quant, and turn on Flash Attention
1. Set the context to 16k tokens, then set it as Sliding Window Attention (SWA)
1. Set the KV quant to 8 bit

This should load nearly all the model into VRAM, only a little bit spills out and it's still relatively fast on my system (25-30T/s).

Hope this helps! Maybe I'll try the model soon too!

OddTheGreat

Owner Jan 6

Good day and thank you for the advice. I did not try to quantize the context on gemma models, as in tests this negated one of the main advantages of this family - accurate attention to context. However, I will try your settings on week. Thanks again.

Theory-of-mind

Mar 2

I run models on a CPU with 32 GB of RAM and encountered excessive memory usage with some models, particularly the Gemma 3 27B and Mistral Small. When running Q4 (Q4_K_M and IQ4_XS) with --mlock, the memory was filled to 32 GB. However, I noticed that running the same models on Q5 uses significantly less RAM. I looked at the llama.cpp log and found the following:

Q4:
srv load_model: loading model 'E:\LLM\GGUFs\Mars_27B_V.1.Q4_K_M.gguf'
...
load_tensors: CPU_Mapped model buffer size = 16529.63 MiB
load_tensors: CPU_REPACK model buffer size = 11694.38 MiB

Q5:
srv load_model: loading model 'E:\LLM\GGUFs\Mars_27B_V.1.Q5_K_M.gguf'
...
load_tensors: CPU_Mapped model buffer size = 19296.38 MiB

I discussed this with GLM-5 and he said that llama.cpp was creating a copy of the weights (CPU_REPACK) when running Q4 to speed up inference.

I'm not sure I understood everything correctly, but perhaps this information will be useful to someone.

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