Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) Mistral7B-PairRM-SPPO-Iter1 - GGUF - Model creator: https://huggingface.co/UCLA-AGI/ - Original model: https://huggingface.co/UCLA-AGI/Mistral7B-PairRM-SPPO-Iter1/ | Name | Quant method | Size | | ---- | ---- | ---- | | [Mistral7B-PairRM-SPPO-Iter1.Q2_K.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Mistral7B-PairRM-SPPO-Iter1-gguf/blob/main/Mistral7B-PairRM-SPPO-Iter1.Q2_K.gguf) | Q2_K | 2.53GB | | [Mistral7B-PairRM-SPPO-Iter1.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Mistral7B-PairRM-SPPO-Iter1-gguf/blob/main/Mistral7B-PairRM-SPPO-Iter1.Q3_K_S.gguf) | Q3_K_S | 2.95GB | | [Mistral7B-PairRM-SPPO-Iter1.Q3_K.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Mistral7B-PairRM-SPPO-Iter1-gguf/blob/main/Mistral7B-PairRM-SPPO-Iter1.Q3_K.gguf) | Q3_K | 3.28GB | | [Mistral7B-PairRM-SPPO-Iter1.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Mistral7B-PairRM-SPPO-Iter1-gguf/blob/main/Mistral7B-PairRM-SPPO-Iter1.Q3_K_M.gguf) | Q3_K_M | 3.28GB | | [Mistral7B-PairRM-SPPO-Iter1.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Mistral7B-PairRM-SPPO-Iter1-gguf/blob/main/Mistral7B-PairRM-SPPO-Iter1.Q3_K_L.gguf) | Q3_K_L | 3.56GB | | [Mistral7B-PairRM-SPPO-Iter1.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Mistral7B-PairRM-SPPO-Iter1-gguf/blob/main/Mistral7B-PairRM-SPPO-Iter1.IQ4_XS.gguf) | IQ4_XS | 3.67GB | | [Mistral7B-PairRM-SPPO-Iter1.Q4_0.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Mistral7B-PairRM-SPPO-Iter1-gguf/blob/main/Mistral7B-PairRM-SPPO-Iter1.Q4_0.gguf) | Q4_0 | 3.83GB | | [Mistral7B-PairRM-SPPO-Iter1.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Mistral7B-PairRM-SPPO-Iter1-gguf/blob/main/Mistral7B-PairRM-SPPO-Iter1.IQ4_NL.gguf) | IQ4_NL | 3.87GB | | [Mistral7B-PairRM-SPPO-Iter1.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Mistral7B-PairRM-SPPO-Iter1-gguf/blob/main/Mistral7B-PairRM-SPPO-Iter1.Q4_K_S.gguf) | Q4_K_S | 3.86GB | | [Mistral7B-PairRM-SPPO-Iter1.Q4_K.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Mistral7B-PairRM-SPPO-Iter1-gguf/blob/main/Mistral7B-PairRM-SPPO-Iter1.Q4_K.gguf) | Q4_K | 4.07GB | | [Mistral7B-PairRM-SPPO-Iter1.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Mistral7B-PairRM-SPPO-Iter1-gguf/blob/main/Mistral7B-PairRM-SPPO-Iter1.Q4_K_M.gguf) | Q4_K_M | 4.07GB | | [Mistral7B-PairRM-SPPO-Iter1.Q4_1.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Mistral7B-PairRM-SPPO-Iter1-gguf/blob/main/Mistral7B-PairRM-SPPO-Iter1.Q4_1.gguf) | Q4_1 | 4.24GB | | [Mistral7B-PairRM-SPPO-Iter1.Q5_0.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Mistral7B-PairRM-SPPO-Iter1-gguf/blob/main/Mistral7B-PairRM-SPPO-Iter1.Q5_0.gguf) | Q5_0 | 4.65GB | | [Mistral7B-PairRM-SPPO-Iter1.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Mistral7B-PairRM-SPPO-Iter1-gguf/blob/main/Mistral7B-PairRM-SPPO-Iter1.Q5_K_S.gguf) | Q5_K_S | 4.65GB | | [Mistral7B-PairRM-SPPO-Iter1.Q5_K.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Mistral7B-PairRM-SPPO-Iter1-gguf/blob/main/Mistral7B-PairRM-SPPO-Iter1.Q5_K.gguf) | Q5_K | 4.78GB | | [Mistral7B-PairRM-SPPO-Iter1.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Mistral7B-PairRM-SPPO-Iter1-gguf/blob/main/Mistral7B-PairRM-SPPO-Iter1.Q5_K_M.gguf) | Q5_K_M | 4.78GB | | [Mistral7B-PairRM-SPPO-Iter1.Q5_1.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Mistral7B-PairRM-SPPO-Iter1-gguf/blob/main/Mistral7B-PairRM-SPPO-Iter1.Q5_1.gguf) | Q5_1 | 5.07GB | | [Mistral7B-PairRM-SPPO-Iter1.Q6_K.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Mistral7B-PairRM-SPPO-Iter1-gguf/blob/main/Mistral7B-PairRM-SPPO-Iter1.Q6_K.gguf) | Q6_K | 5.53GB | | [Mistral7B-PairRM-SPPO-Iter1.Q8_0.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_Mistral7B-PairRM-SPPO-Iter1-gguf/blob/main/Mistral7B-PairRM-SPPO-Iter1.Q8_0.gguf) | Q8_0 | 7.17GB | Original model description: --- license: apache-2.0 datasets: - openbmb/UltraFeedback language: - en pipeline_tag: text-generation --- Self-Play Preference Optimization for Language Model Alignment (https://arxiv.org/abs/2405.00675) # Mistral7B-PairRM-SPPO-Iter1 This model was developed using [Self-Play Preference Optimization](https://arxiv.org/abs/2405.00675) at iteration 1, based on the [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) architecture as starting point. We utilized the prompt sets from the [openbmb/UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback) dataset, splited to 3 parts for 3 iterations by [snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset](https://huggingface.co/datasets/snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset). All responses used are synthetic. **This is the model reported in the paper** , with K=5 (generate 5 responses per iteration). We attached the Arena-Hard eval results in this model page. ## Links to Other Models - [Mistral7B-PairRM-SPPO-Iter1](https://huggingface.co/UCLA-AGI/Mistral7B-PairRM-SPPO-Iter1) - [Mistral7B-PairRM-SPPO-Iter2](https://huggingface.co/UCLA-AGI/Mistral7B-PairRM-SPPO-Iter2) - [Mistral7B-PairRM-SPPO-Iter3](https://huggingface.co/UCLA-AGI/Mistral7B-PairRM-SPPO-Iter3) - [Mistral7B-PairRM-SPPO](https://huggingface.co/UCLA-AGI/Mistral7B-PairRM-SPPO) ### Model Description - Model type: A 7B parameter GPT-like model fine-tuned on synthetic datasets. - Language(s) (NLP): Primarily English - License: Apache-2.0 - Finetuned from model: mistralai/Mistral-7B-Instruct-v0.2 ## [AlpacaEval Leaderboard Evaluation Results](https://tatsu-lab.github.io/alpaca_eval/) | Model | LC. Win Rate | Win Rate | Avg. Length | |-------------------------------------------|:------------:|:--------:|:-----------:| | Mistral7B-PairRM-SPPO Iter 1 | 24.79 | 23.51 | 1855 | | Mistral7B-PairRM-SPPO Iter 2 | 26.89 | 27.62 | 2019 | | Mistral7B-PairRM-SPPO Iter 3 | 28.53 | 31.02 | 2163 | | Mistral7B-PairRM-SPPO Iter 1 (best-of-16) | 28.71 | 27.77 | 1901 | | Mistral7B-PairRM-SPPO Iter 2 (best-of-16) | 31.23 | 32.12 | 2035 | | Mistral7B-PairRM-SPPO Iter 3 (best-of-16) | 32.13 | 34.94 | 2174 | ## [Arena-Hard Evaluation Results](https://github.com/lm-sys/arena-hard) Model | Score | 95% CI | average \# Tokens | |----------|-----------|--------------|-----------| Mistral7B-PairRM-SPPO-Iter3| 23.3 | (-1.8, 1.8)|578| ## [Open LLM Leaderboard Evaluation Results](https://github.com/EleutherAI/lm-evaluation-harness) Results are reported by using [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) v0.4.1 | | arc_challenge | truthfulqa_mc2 | winogrande | gsm8k | hellaswag | mmlu | average | |--------|---------------|----------------|------------|-------|-----------|-------|---------| | Mistral7B-PairRM-SPPO Iter 1 | 65.02 | 69.4 | 77.82 | 43.82 | 85.11 | 58.84 | 66.67 | | Mistral7B-PairRM-SPPO Iter 2 | 65.53 | 69.55 | 77.03 | 44.35 | 85.29 | 58.72 | 66.75 | | Mistral7B-PairRM-SPPO Iter 3 | 65.36 | 69.97 | 76.8 | 42.68 | 85.16 | 58.45 | 66.4 | ## [MT-Bench Evaluation Results](https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge) | | 1st Turn | 2nd Turn | Average | |--------|----------|----------|---------| | Mistral7B-PairRM-SPPO Iter 1 | 7.63 | 6.79 | 7.21 | | Mistral7B-PairRM-SPPO Iter 2 | 7.90 | 7.08 | 7.49 | | Mistral7B-PairRM-SPPO Iter 3 | 7.84 | 7.34 | 7.59 | ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-07 - eta: 1000 - per_device_train_batch_size: 8 - gradient_accumulation_steps: 1 - seed: 42 - distributed_type: deepspeed_zero3 - num_devices: 8 - optimizer: RMSProp - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_train_epochs: 18.0 (stop at epoch=1.0) ## Citation ``` @misc{wu2024self, title={Self-Play Preference Optimization for Language Model Alignment}, author={Wu, Yue and Sun, Zhiqing and Yuan, Huizhuo and Ji, Kaixuan and Yang, Yiming and Gu, Quanquan}, year={2024}, eprint={2405.00675}, archivePrefix={arXiv}, primaryClass={cs.LG} } ```