Downloads · 30 days
11
4% of all-time downloads
HayatoHongo/lfm2-vl-ja-finetuned-enmt1ep-jamt10eponall-vqa
lfm2-vl-ja-finetuned-enmt1ep-jamt10eponall-vqa is a image-text-to-text model from HayatoHongo. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as cc-by-4.0.
torchrun --nprocpernode=8 trainVQAdiflr.py \ --modelid HayatoHongo/lfm2-vl-ja-finetuned-enmt1ep-jamt10eponall \ --chatjson /workspace/JapaneseVQA192642.jsonl \ --imagefolder /workspace/images \ --outputdir /workspace/…
Downloads · 30 days
11
4% of all-time downloads
All-time downloads
296
Public
Parameters
451M
1.6 GB on disk
Likes
3
Public
Click a slice to open those files.
.safetensors902 MB · 99%
From the Hugging Face model README
torchrun --nproc_per_node=8 train_VQA_diflr.py
--model_id HayatoHongo/lfm2-vl-ja-finetuned-enmt1ep-jamt10eponall
--chat_json /workspace/Japanese_VQA_192642.jsonl
--image_folder /workspace/images
--output_dir /workspace/output
--epochs 1
--lr 1e-5
--text_lr_scale 0.1
--per_device_train_batch_size 16
--gradient_accumulation_steps 1
--bf16
--tf32
--report_to wandb
--logging_steps 20
--seed 42
This model is a fine-tuned version of HayatoHongo/lfm2-vl-ja-finetuned-enmt1ep-jamt10eponall. It has been trained using TRL.
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="None", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
This model was trained with SFT.
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}}
}