metadata
model-index:
- name: Kulyk-EN-UK
results:
- task:
type: text-generation
dataset:
type: facebook/flores
name: FLORES
split: devtest
metrics:
- type: bleu
value: 27.24
name: BLEU
library_name: transformers
license: other
license_name: lfm1.0
license_link: LICENSE
language:
- en
- uk
pipeline_tag: text-generation
tags:
- liquid
- lfm2
- edge
datasets:
- lang-uk/FiftyFiveShades
base_model:
- LiquidAI/LFM2-350M
A new lightweight model to do machine translation from English to Ukrainian using recently published LFM2 model. Use demo to test it.
Facts:
- Fine-tuned with 40M samples (filtered by quality metric) from ~53.5M for 1.4 epochs
- 354M params
- Requires 1 GB of RAM to run with bf16
- BLEU on FLORES-200: 27.24
- Tokens per second: 229.93 (bs=1), 1664.40 (bs=10), 8392.48 (bs=64)
- License: lfm1.0
Info:
- Model name is inherited from name of Sergiy Kulyk who was chargé d'affaires of Ukraine in the United States
Training Info:
- Learning Rate: 3e-5
- Learning Rate scheduler type: cosine
- Warmup Ratio: 0.05
- Max length: 2048
packed=True- Sentences <= 1000 chars
- Gradient accumulation steps: 4
- Used Flash Attention 2
- Time for epoch: 32 hours
- 2 cards of NVIDIA RTX 3090 Ti (24G)
acceleratewith DeepSpeed, offloading into CPU- Memory usage: 22.212GB-22.458GB
- torch 2.7.1
Acknowledgements:
- Serhiy Stetskovych for providing compute to train this model
- lang-uk members for their compilation of different MT datasets