---
base_model: allenai/Bolmo-7B
library_name: transformers
model_name: LYRICAL_MT_ru2en_Bolmo7b_SFT
tags:
- generated_from_trainer
- trl
- Translation
- MT
- Russian
- English
- poetry
- poem
- lyrics
- CharacterLevel
- ByteLevel
- Lyrical
- Olmo
- Bolmo
- verse
- sft
licence: license
datasets:
- AlekseyCalvin/Lyrical_Ru2En_Poems_Songs_MeterMatched_csv_SFT
---

# Model Card for BYTE LYRICAL TRANSLATION MODEL Var.2 (SFT stage)

This model is a fine-tuned version of [allenai/Bolmo-7B](https://huggingface.co/allenai/Bolmo-7B).
It has been trained using [TRL](https://github.com/huggingface/trl).

## Installation

Bolmo models have been tested with transformers 4.57.3 and Python 3.11:
```bash
pip install transformers>=4.57.3
```
Bolmo additionally requires the [xlstm package](https://github.com/NX-AI/xlstm) (which needs Python>=3.11):

```bash
pip install xlstm==2.0.4
```
## Inference
You can use this byte-level variant of the LYRICAL Poetry Translation model with the standard HuggingFace transformers library:

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda"
bolmo = AutoModelForCausalLM.from_pretrained("AlekseyCalvin/Lyrical_Bolmo_7b_SFT_Merged", trust_remote_code=True).to(device)
tokenizer = AutoTokenizer.from_pretrained("AlekseyCalvin/Lyrical_Bolmo_7b_SFT_Merged", trust_remote_code=True)
message = ["Translate the following verses: Совершить ли мне горшочек для вмещения кишочек вымещения червей красоты земли моей  "]
input_ids = tokenizer(message, return_tensors="pt")["input_ids"].to(device)
# `max_new_tokens` is the amount of bytes to generate
response = bolmo.generate(input_ids, max_new_tokens=256, do_sample=True, temperature=0.1)
print(tokenizer.decode(response[0], skip_special_tokens=True))
```

## Training procedure
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/alekseycalvin/huggingface/runs/mxn0q550) 


This model was trained with SFT.
### Framework versions

- TRL: 0.26.2
- Sacrebleu (for BLEU Machine Translation evaluations)
- Transformers: 4.57.3
- Pytorch: 2.9.0+cu126
- Datasets: 4.0.0
- Tokenizers: 0.22.1

Cite TRL as:
    
```bibtex
@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}}
}
```