7.0 KiB
7.0 KiB
Quantization made by Richard Erkhov.
openai-gsm8k_meta-llama-Llama-3.2-1B - GGUF
- Model creator: https://huggingface.co/YWZBrandon/
- Original model: https://huggingface.co/YWZBrandon/openai-gsm8k_meta-llama-Llama-3.2-1B/
Original model description:
base_model: meta-llama/Llama-3.2-1B datasets: openai/gsm8k library_name: transformers model_name: openai-gsm8k_meta-llama-Llama-3.2-1B tags:
- generated_from_trainer
- trl
- sft licence: license
Model Card for openai-gsm8k_meta-llama-Llama-3.2-1B
This model is a fine-tuned version of meta-llama/Llama-3.2-1B on the openai/gsm8k 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="YWZBrandon/openai-gsm8k_meta-llama-Llama-3.2-1B", 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: 0.12.2
- Transformers: 4.46.3
- Pytorch: 2.5.1
- Datasets: 3.1.0
- Tokenizers: 0.20.3
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 Gallouédec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}