metadata
library_name: transformers
model_name: model_checkpoints
tags:
- generated_from_trainer
- sft
- trl
- unsloth
licence: license
license: mit
language:
- tr
- en
base_model:
- LiquidAI/LFM2-8B-A1B
pipeline_tag: translation
This is an EN<>TR translation model fine-tuned from the LiquidAI/LFM2-8B-A1B model. While convenient, it can occasionally make simple spelling errors.
The system message should be "Task: Translation."
Suggested settings:
top_k = 10,
top_p = 0.95,
temperature = 0.2
The message above was translated with this model.
Bu, LiquidAI/LFM2-8B-A1B modelinden fine-tune edilmiş bir EN<>TR çeviri modelidir. Kullanışlı olmasına rağmen bazen basit imla hataları yapabilir. Sistem mesajı "Task: Translation." olmalıdır.
Önerilen ayarlar:
top_k = 10,
top_p = 0.95,
temperature = 0.2
More training details:
Dataset: Private dataset, ~100M tokens Full fine-tuning via unsloth ~7hrs x A100 40GB
Citations
Cite TRL as:
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}