Text Generation
Transformers
Safetensors
Russian
English
qwen2
MANTA
autocomplete
word-completion
text-generation-inference
Instructions to use average23/MANTA-20M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use average23/MANTA-20M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="average23/MANTA-20M")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("average23/MANTA-20M") model = AutoModelForCausalLM.from_pretrained("average23/MANTA-20M", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use average23/MANTA-20M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "average23/MANTA-20M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "average23/MANTA-20M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/average23/MANTA-20M
- SGLang
How to use average23/MANTA-20M 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 "average23/MANTA-20M" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "average23/MANTA-20M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "average23/MANTA-20M" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "average23/MANTA-20M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use average23/MANTA-20M with Docker Model Runner:
docker model run hf.co/average23/MANTA-20M
Download pyproject.toml from average23/MANTA-20M: direct link, hf CLI and curl.
- Browser
- Download file 598 Bytes
-
https://huggingface.co/average23/MANTA-20M/resolve/main/pyproject.toml
- Command line
-
hf download hf://average23/MANTA-20M/pyproject.toml
-
curl -L -o pyproject.toml https://huggingface.co/average23/MANTA-20M/resolve/main/pyproject.toml
598 Bytes
| [build-system] | |
| requires = ["hatchling>=1.27"] | |
| build-backend = "hatchling.build" | |
| [project] | |
| name = "manta-keyboard" | |
| version = "0.1.0" | |
| description = "Compact Russian conversational language model for next-word prediction and word completion." | |
| readme = "README.md" | |
| requires-python = ">=3.11" | |
| license = "Apache-2.0" | |
| dependencies = [ | |
| "torch>=2.7,<3", | |
| "numpy>=1.26,<3", | |
| "transformers==4.57.6", | |
| "tokenizers==0.22.2", | |
| "huggingface-hub>=0.34,<1", | |
| "safetensors>=0.5,<1", | |
| ] | |
| [tool.hatch.build.targets.wheel] | |
| packages = ["manta"] | |
| [tool.pytest.ini_options] | |
| testpaths = ["tests"] | |
| pythonpath = ["."] | |