YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

Quantization made by Richard Erkhov.

Github

Discord

Request more models

self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2 - GGUF

Name Quant method Size
self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2.Q2_K.gguf Q2_K 1.39GB
self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2.IQ3_XS.gguf IQ3_XS 1.53GB
self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2.IQ3_S.gguf IQ3_S 1.59GB
self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2.Q3_K_S.gguf Q3_K_S 1.59GB
self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2.IQ3_M.gguf IQ3_M 1.65GB
self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2.Q3_K.gguf Q3_K 1.73GB
self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2.Q3_K_M.gguf Q3_K_M 1.73GB
self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2.Q3_K_L.gguf Q3_K_L 1.85GB
self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2.IQ4_XS.gguf IQ4_XS 1.91GB
self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2.Q4_0.gguf Q4_0 1.99GB
self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2.IQ4_NL.gguf IQ4_NL 2.0GB
self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2.Q4_K_S.gguf Q4_K_S 2.0GB
self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2.Q4_K.gguf Q4_K 2.09GB
self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2.Q4_K_M.gguf Q4_K_M 2.09GB
self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2.Q4_1.gguf Q4_1 2.18GB
self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2.Q5_0.gguf Q5_0 2.37GB
self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2.Q5_K_S.gguf Q5_K_S 2.37GB
self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2.Q5_K.gguf Q5_K 2.41GB
self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2.Q5_K_M.gguf Q5_K_M 2.41GB
self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2.Q5_1.gguf Q5_1 2.55GB
self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2.Q6_K.gguf Q6_K 2.76GB
self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2.Q8_0.gguf Q8_0 3.58GB

Original model description:

base_model: RyanYr/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter1 library_name: transformers model_name: self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2 tags: - generated_from_trainer - trl - dpo licence: license

Model Card for self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2

This model is a fine-tuned version of RyanYr/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter1. 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="RyanYr/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

Visualize in Weights & Biases

This model was trained with DPO, a method introduced in Direct Preference Optimization: Your Language Model is Secretly a Reward Model.

Framework versions

  • TRL: 0.12.0.dev0
  • Transformers: 4.45.2
  • Pytorch: 2.4.0
  • Datasets: 3.0.1
  • Tokenizers: 0.20.1

Citations

Cite DPO as:

@inproceedings{rafailov2023direct,
    title        = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
    author       = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
    year         = 2023,
    booktitle    = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
    url          = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
    editor       = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
}

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}}
}

Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more quants, at much higher speed, than I would otherwise be able to.

Downloads last month
111
GGUF
Model size
3.61B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference API
Unable to determine this model's library. Check the docs .