End of training

efb8e24 verified 3 months ago

1.99 kB

base_model: CohereLabs/tiny-aya-global
datasets: bebechien/SimpleToolCalling
library_name: transformers
model_name: tiny-aya-global-SFT
tags:
  - generated_from_trainer
  - >-
    trackio:https://emihf-tiny-aya-global-SFT.hf.space?project=huggingface&runs=emihf-1775773401&sidebar=collapsed
  - sft
  - trl
  - trackio
licence: license

Model Card for tiny-aya-global-SFT

This model is a fine-tuned version of CohereLabs/tiny-aya-global on the bebechien/SimpleToolCalling dataset. It has been trained using TRL.

Quick start

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="emihf/tiny-aya-global-SFT", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with SFT.

Framework versions

TRL: 0.29.0
Transformers: 5.5.3
Pytorch: 2.9.1
Datasets: 4.8.4
Tokenizers: 0.22.2

Citations

Cite TRL as:

@software{vonwerra2020trl,
  title   = {{TRL: Transformers Reinforcement Learning}},
  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
  license = {Apache-2.0},
  url     = {https://github.com/huggingface/trl},
  year    = {2020}
}