Instructions to use Ddavidich/LOMONOSOV-ZENIT-27B-1M-INDEV with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ddavidich/LOMONOSOV-ZENIT-27B-1M-INDEV with Transformers:

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

pipe = pipeline("text-generation", model="Ddavidich/LOMONOSOV-ZENIT-27B-1M-INDEV", trust_remote_code=True)
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("Ddavidich/LOMONOSOV-ZENIT-27B-1M-INDEV", trust_remote_code=True)
model = AutoModelForImageTextToText.from_pretrained("Ddavidich/LOMONOSOV-ZENIT-27B-1M-INDEV", trust_remote_code=True, 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 Ddavidich/LOMONOSOV-ZENIT-27B-1M-INDEV with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ddavidich/LOMONOSOV-ZENIT-27B-1M-INDEV"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ddavidich/LOMONOSOV-ZENIT-27B-1M-INDEV",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ddavidich/LOMONOSOV-ZENIT-27B-1M-INDEV

SGLang

How to use Ddavidich/LOMONOSOV-ZENIT-27B-1M-INDEV 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 "Ddavidich/LOMONOSOV-ZENIT-27B-1M-INDEV" \
    --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": "Ddavidich/LOMONOSOV-ZENIT-27B-1M-INDEV",
		"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 "Ddavidich/LOMONOSOV-ZENIT-27B-1M-INDEV" \
        --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": "Ddavidich/LOMONOSOV-ZENIT-27B-1M-INDEV",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Ddavidich/LOMONOSOV-ZENIT-27B-1M-INDEV with Docker Model Runner:
```
docker model run hf.co/Ddavidich/LOMONOSOV-ZENIT-27B-1M-INDEV
```

LOMONOSOV-ZENIT-27B-1M-INDEV / receipts /vision_probe.json

Ddavidich

Прижатие доли памяти чинилось только при автовыборе окна — теперь всегда

28a6813 verified 2 months ago

Raw History Blame Contribute Delete

1.93 kB

	{
	"schema": "lomonosov_zenit_vision_v1",
	"status": "FAIL",
	"failed_at": "request",
	"question": "проходит ли изображение через модель на настоящем запросе",
	"answer": "НЕТ. Мультимодальность на этом чекпойнте не работает.",
	"host": "локальная RTX 5090, 32 ГБ, рабочий стол занимает ~1.3 ГиБ",
	"max_model_len": 32768,
	"load_seconds": 64.0,
	"image": "logo.png 1200x842",
	"path": [
	"qwen3_vl.py:_process_image_input",
	"self.visual(pixel_values, grid_thw)",
	"kernels/linear/mixed_precision/humming.py:apply_weights",
	"humming/layer.py:forward_layer -> ops.humming_gemm",
	"torch.ops.humming.launch_kernel"
	],
	"error": "RuntimeError: check_curesult, humming/csrc/launcher/utils.h:11, cuFuncSetAttribute failed with error: CUDA_ERROR_INVALID_VALUE",
	"diagnosis": "зрительная башня квантована SELECTIVE_W8_W4_A16 и считается ядром humming; ядро просит у карты больше разделяемой памяти, чем та отдаёт, и не запускается. skip_mm_profiling обходит то же падение ПРИ СТАРТЕ и потому маскировал дефект",
	"consequence": "заявлять мультимодальность нельзя. В карточке и в любых анонсах должно стоять: сейчас только текст",
	"candidate_fix": "хранить зрительную башню в BF16 без квантования — это 371 380 976 параметров, около 743 МБ, и путь humming тогда не задействуется вовсе. Языковую часть это не трогает",
	"note": "родословная зрения сама помечена promotion: forbidden_until_multimodal_A_B_and_raw1010k_PASS"
	}