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 / NOOSPHERE_MODEL_ABI.json

Ddavidich

Карточка, лицензия, конфиг, рантайм и QR-коды. Веса следом.

86b5732 verified 10 days ago

Raw

History Blame Contribute Delete

4.67 kB

	{
	"altay_kv_layout": {
	"actual_cache_units": 70,
	"allocated_cache_slots": 72,
	"attention_padding_cache_slots": 0,
	"enabled": true,
	"full_attention_cache_units": 16,
	"gdn_cache_units": 54,
	"gdn_padding_cache_slots": 2,
	"group_size": 8,
	"kv_content_modified": false,
	"legacy_allocated_cache_slots": 80,
	"padding_cache_slots": 2,
	"repair_id": "ALTAY72_KV_ATTENTION_EXACT_G8_V2",
	"schema": "lomonosov_zenit_altay_kv_layout_v1",
	"weights_modified": false
	},
	"altay_overlay": {
	"architecture_id": "LOMONOSOV_ZENIT_ALTAY_72M_SKV_V1",
	"file_sha256": "3e355f35a2e05c7d96d808160e410bf94b256adf67dc7d8fa3cf2039669766f6",
	"filename": "model-altay-overlay.safetensors",
	"quantization_invariant": true,
	"tensor_entries": 28,
	"tensor_payload_bytes": 15204384,
	"tensor_set_sha256": "18fd863ab724f1a1ea475df37d2bf89df943c6836085c264740a9095a6760d96"
	},
	"architecture": "LomonosovZenitAltayForConditionalGeneration",
	"config_sha256": "dfb9d51dad800e7d712550ee053428baf2ae104180d0d1967fe40c32b6d19d0f",
	"logical_context_tokens": 1010000,
	"multimodal_parent": "Qwen3_5ForConditionalGeneration",
	"noosphere_execution_contract": "raw_plus_additive",
	"noosphere_in_model_generate": true,
	"noosphere_in_vllm_model_processor": true,
	"quantization_config_sha256": "9cbfd01ea212797c4a0c79d06756d59fa1b225d64af319e8f0644862d6babc2c",
	"quantization_independent_runtime_sha256": "d10bfff29a6df93031e81cc0696b8f7396de0108da95920ce52deb4de327ad4c",
	"raw_tokens_preserved": true,
	"routing_replaces_raw": false,
	"runtime_files": {
	"custom_generate/__init__.py": "31767bbe7a7f1c6036b325a7b2be13f9f89e04f1fa06706851db5553664ae183",
	"custom_generate/generate.py": "ba676176b434881995417bd31cd9514372a54505efc039147840b16e5abe7af3",
	"custom_generate/jit_guard.py": "36b5ca9f6f537683857aea1d92b223f6fcc17bafb6072d9524c22d1e93ce63dd",
	"custom_generate/noosphere/__init__.py": "69bb1feee377f5e00a5b778c5ce7b769f392dfbed583a135cadad1b74d5328d0",
	"custom_generate/noosphere/additive.py": "339466bbbbf592191c546741b8248b1a8632a3885dbda982d86c4e5cd5ee4f82",
	"custom_generate/noosphere/h1.py": "269dbe4f54f821a217b16889e02541227757eb9c44f803d8d9711da9ad18b6b8",
	"custom_generate/noosphere/ledger.py": "cf349793cd00764ac8f748f442dab192034e5cf8276c900c4dc039ee6cc5c761",
	"custom_generate/noosphere/model_memory.py": "f2bf760a861485fd4ab021f40768f3a426494be1b9927ee9bcdcff052435d51c",
	"custom_generate/noosphere/shell.py": "3702c69a5ceda0ac868e74b51b83bf0584794926ddb1f4c7d48c1eccbb033319",
	"custom_generate/noosphere/surface.py": "a5db814ab3527e3cdea224b2ed7fb6cc93c619ad17c46d32c076fd19b8551ae8",
	"custom_generate/noosphere/weave.py": "d9b89b389c81799de504b39b91868ea27eaa58eed70877c477b13ac3f1326eff",
	"custom_generate/offline_noosphere_path.py": "42e9a0c2011995a443ff1741dad6af272da7cbc3ae50256ee9da679ec1747503",
	"custom_generate/requirements.txt": "f7e6cee3d6ce0e1601be1df1011e35667401f7599a40c2b6ae7da033b3e91f0c",
	"custom_generate/serving_profiles.py": "2a27e341e83ee8e6263b2093e6e07d650a35318bfc3ac9fe9260e773a5799aac",
	"custom_generate/tq_embedding_quant.py": "de370dedae5f021b67b36454a31fea8968e983379ce3ccf28cacc86603dd7375",
	"custom_generate/tq_tiled_prefill.py": "64384ac8685789872e9b3bd5374c4d8967502d584b615338ad4f59a00cb361fd",
	"custom_generate/tq_value_mse.py": "0be4774fb1a6405e06072f1e56f715469f66acc28f730996e4b3b69c936fee9c",
	"custom_generate/tq_value_mse_decode.py": "4cc436c96d30978a2235d245874fa07b5b7d321e68518fc028ffc03ee77d2c82",
	"custom_generate/tq_value_mse_kernels.py": "ada075366a88d22db2a06a1472c289cf2a745f50efd46138129f9e970254c7da",
	"custom_generate/vllm_altay.py": "c19b8bf0deb7c5c7d7d9d1ba11a991684e8604e2eb5e5ffc1ba8526266f9d7e1",
	"custom_generate/vllm_kv_layout.py": "8ad7a4be290a7269613694b53816325463c550ecfdd9c88e65fd7ee331422d4b",
	"custom_generate/vllm_model.py": "56b79a9f4173f7b255afe8b5fb297905fb3ae7dde121836b8d837d9df1052c35",
	"custom_generate/vllm_plugin.py": "3e1e87674b6fb3268aeeaca22944915fc79aa5b5c9104dc8685e675ed76ecdce",
	"custom_generate/vllm_renderer.py": "b81c22f19086efa2bccfadf51838bc42401fd80ac7e27794cf110b5bc9610d3d",
	"custom_generate/vllm_turboquant.py": "6c5cad10dc4a21c753f7a1f17d69abcb366da8b864de4fdba537d52d5c0cafe4",
	"pyproject.toml": "dbb4468342f9c0af955e092491800f4ecb22ceb916d703756dd2db7e19d3c3af"
	},
	"schema": "lomonosov_zenit_altay_noosphere_quant_binding_v1",
	"status": "BOUND_UNVERIFIED",
	"weight_index_sha256": "a786196aad388a89fd9e9335c9d7614d03ab5d23e5b054a0d723a45b9e3e0095",
	"weights_modified": false
	}