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
```

Ddavidich commited on 8 days ago

Commit

7d43654

verified ·

1 Parent(s): a95dc44

Теги: transformers и 3-bit; library_name намеренно остаётся vllm

Browse files

Тег transformers добавлен для поиска, но library_name не меняется. Причина
замерена и описана в разделе про transformers: модель там ЗАГРУЖАЕТСЯ за
12.7 с на 18.2 ГБ, но прямой проход требует около 55 ГБ — у compressed-tensors
в transformers нет квантованных ядер, и первый forward разворачивает модель в
bf16 на месте (их же model_compressor.py: 'This allows for generation without
requiring CT to handle quantized kernels'). Поставить library_name: transformers
значило бы включить виджет вывода, ведущий на путь, требующий 64 ГБ.

Тег 3-bit отражает новую раскладку: поздние 32 слоя MLP в несимметричных трёх
битах. На требование transformers это не влияет — разворачивание идёт в bf16
независимо от разрядности в файле.

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -21,8 +21,10 @@ tags:
   - rtx-5090
   - rtx-4090
   - vllm
   - quantization
   - nvfp4
   - fp8
   - int8
   - kv-cache-quantization

   - rtx-5090
   - rtx-4090
   - vllm
+  - transformers
   - quantization
   - nvfp4
+  - 3-bit
   - fp8
   - int8
   - kv-cache-quantization