Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3 - GGUF - Model creator: https://huggingface.co/RyanYr/ - Original model: https://huggingface.co/RyanYr/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3/ | Name | Quant method | Size | | ---- | ---- | ---- | | [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q2_K.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q2_K.gguf) | Q2_K | 1.39GB | | [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.IQ3_XS.gguf) | IQ3_XS | 1.53GB | | [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.IQ3_S.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.IQ3_S.gguf) | IQ3_S | 1.59GB | | [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q3_K_S.gguf) | Q3_K_S | 1.59GB | | [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.IQ3_M.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.IQ3_M.gguf) | IQ3_M | 1.65GB | | [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q3_K.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q3_K.gguf) | Q3_K | 1.73GB | | [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q3_K_M.gguf) | Q3_K_M | 1.73GB | | [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q3_K_L.gguf) | Q3_K_L | 1.85GB | | [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.IQ4_XS.gguf) | IQ4_XS | 1.91GB | | [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q4_0.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q4_0.gguf) | Q4_0 | 1.99GB | | [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.IQ4_NL.gguf) | IQ4_NL | 2.0GB | | [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q4_K_S.gguf) | Q4_K_S | 2.0GB | | [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q4_K.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q4_K.gguf) | Q4_K | 2.09GB | | [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q4_K_M.gguf) | Q4_K_M | 2.09GB | | [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q4_1.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q4_1.gguf) | Q4_1 | 2.18GB | | [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q5_0.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q5_0.gguf) | Q5_0 | 2.37GB | | [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q5_K_S.gguf) | Q5_K_S | 2.37GB | | [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q5_K.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q5_K.gguf) | Q5_K | 2.41GB | | [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q5_K_M.gguf) | Q5_K_M | 2.41GB | | [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q5_1.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q5_1.gguf) | Q5_1 | 2.55GB | | [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q6_K.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q6_K.gguf) | Q6_K | 2.76GB | | [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q8_0.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3.Q8_0.gguf) | Q8_0 | 3.58GB | Original model description: --- base_model: RyanYr/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2 library_name: transformers model_name: self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3 tags: - generated_from_trainer - trl - dpo licence: license --- # Model Card for self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter3 This model is a fine-tuned version of [RyanYr/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2](https://huggingface.co/RyanYr/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2). It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python 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_iter3", 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](https://wandb.ai/yyr/huggingface/runs/27c74iwj) This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290). ### 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: ```bibtex @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: ```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 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.