How to use from
vLLM
Install from pip and serve model
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "domce20/mGPT-Lithuanian"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "domce20/mGPT-Lithuanian",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'
Use Docker
docker model run hf.co/domce20/mGPT-Lithuanian
Quick Links

Model Card for Model ID

mGPT model additionally trained for Lithuanian.

Model Description

The model is additionally trained on a modified partition of the Lithuanian partition of the mC4 dataset.

The training was done on Vilnius University supercomputer.

Downloads last month
6
Safetensors
Model size
1B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for domce20/mGPT-Lithuanian

Base model

ai-forever/mGPT
Finetuned
(3)
this model

Datasets used to train domce20/mGPT-Lithuanian