154 lines
6.4 KiB
Markdown
154 lines
6.4 KiB
Markdown
---
|
||
language:
|
||
- en
|
||
license: apache-2.0
|
||
library_name: transformers
|
||
|
||
---
|
||
|
||
# Model Card for Mistral-7B-ReMax-v0.1
|
||
|
||
|
||
The Mistral-7B-ReMax-v0.1 Large Language Model (LLM) is a Reinforcement Learning from Human Preference (RLHF) fine-tuned version of [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2).
|
||
|
||
The fine-tuning algorithm is ReMax and please find algorithm details in the [paper](https://arxiv.org/abs/2310.10505).
|
||
|
||
## Model Details
|
||
|
||
- Developed by: Ziniu Li
|
||
- License: apache-2.0
|
||
- Finetuned from [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
|
||
|
||
## Uses
|
||
|
||
### Direct Use
|
||
|
||
The instruction format is the same as Mistral-7B-Instruct-v0.2. Specifically, the prompt should be surrounded by \[INST\] and \[/INST\] tokens.
|
||
|
||
```
|
||
text = "<s>[INST] What is your favourite condiment? [/INST]"
|
||
"Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!</s> "
|
||
"[INST] Do you have mayonnaise recipes? [/INST]"
|
||
```
|
||
|
||
|
||
## Training Details
|
||
|
||
### Training Data
|
||
|
||
10k prompts from the [lmsys-chat-1m](https://huggingface.co/datasets/lmsys/lmsys-chat-1m) dataset. Note that no responses from this dataset are used in training.
|
||
|
||
### Reward Model
|
||
|
||
The reward model is based on [UltraRM-13b](https://huggingface.co/openbmb/UltraRM-13b).
|
||
|
||
**Important**: UltraRM-13b uses a different instruction template with Mistral-7B. To address this issue, we change the chat template to that of UltraRM-13b when evaluating the reward score in RLHF fine-tuning.
|
||
|
||
|
||
### Training Procedure
|
||
|
||
The training algorithm is ReMax, whose details are available in the [paper](https://arxiv.org/abs/2310.10505), and implementations are available in the [repository](https://github.com/liziniu/ReMax).
|
||
|
||
|
||
### Training Hyperparameters
|
||
|
||
```
|
||
max_prompt_seq: 384
|
||
max_answer_seq: 384
|
||
learning_rate: 5e-7
|
||
num_train_epochs: 1
|
||
kl_penalty: full_step
|
||
kl_ctl: 0.1
|
||
reward_clip_value: 1.0
|
||
temperature for sampling: 0.7
|
||
top_p for sampling: 0.9
|
||
```
|
||
|
||
|
||
## Evaluation
|
||
|
||
|
||
### Chat1M
|
||
|
||
|
||
Since we fine-tune Mistral-7B-Instruct-v0.2 with the lmsys-chat-1m dataset, we first evaluate the quality of responses. We randomly select 500 prompts from the lmsys-chat-1m dataset and lets the models to generate responses. Then, we let GPT-4 to evaluate the binary win rate. The average win-rate of Mistral-7B-ReMax-v0.1 is 57.8%.
|
||
|
||
| | Mistral-7B-ReMax-v0.1 Wins | Mistral-7B-ReMax-v0.1 Wins |
|
||
| ------------------------ | -------------------------- | -------------------------- |
|
||
| Mistral-7B-Instruct-v0.2 | 289 | 211 |
|
||
|
||
Samples of responses are provided below.
|
||
|
||
```
|
||
==================Instruction================
|
||
你好
|
||
==================Mistral-7B-Instruct-v0.2================
|
||
你好！我是一位帮助您解答问题的机器人。如果您有任何问题，请告诉我，我会尽力回答。
|
||
|
||
你好（Hello）是中文语言中的一个常用词语，常用于问候或表示亲和，意思是“你好，你很好”。
|
||
|
||
在我帮助您之前，我想先问一下，您是否知道什么是机器学习？机器学习是人工智能领域中的一种技术，它允许计算机自动学习和改进其行为，以便从数据中提取出有价值的信息，并使计算机能够做出更智能的决策。
|
||
|
||
如果您已经熟悉机器学习，那么我可以帮助您深入探讨相关主题，如神经网络、支持向量机、决策树等。但是，如果您对机器学习不太熟悉，我可以简单地解释它的基本原理，以及它在现实生活中的应用。
|
||
|
||
请告诉我您的需求，我会尽力满足您的期望。
|
||
|
||
再次问候您：你好！
|
||
==================Mistral-7B-ReMax-v0.1================
|
||
好的，欢迎使用我的帮助！（Hello, welcome to use my help!）
|
||
|
||
是的，我可以以中文回答你的问题，或者帮你完成一些简单的任务。（Yes, I can answer your questions in Chinese or help you with some simple tasks.）
|
||
|
||
请问有什么特定的问题需要我帮忙呢？（What specific question do you need my help with?）
|
||
|
||
或者，你可以告诉我什么方面我可以提供帮助。（Or you can tell me which area I can provide help in.）
|
||
|
||
希望我能帮到你！（I hope I can help you!）
|
||
```
|
||
|
||
|
||
### AlpacaEval
|
||
|
||
[AlpacaEval](https://github.com/tatsu-lab/alpaca_eval) provides 805 test questions that the model has not been trained on. We provide the evaluation results below:
|
||
|
||
| | AlpacaEval | AlpacaEval 2 | Response Length |
|
||
| ------------------------ | ---------- | ------------ | --------------- |
|
||
| Mistral-7B-Instruct-v0.2 | 92.78 | 14.72 | 1676 |
|
||
| Mistral-7B-ReMax-v0.1 | 94.40 | 16.00 | 1478 |
|
||
| LLaMa2 Chat 7B | 71.37 | 4.96 | 1479 |
|
||
| LLaMa2 Chat 70B | 92.66 | 13.87 | 1790 |
|
||
| GPT-4 | 95.28 | 23.58 | 2049 |
|
||
|
||
Samples of responses are provided below
|
||
|
||
```
|
||
==================Instruction================
|
||
Marie is at the music store for a store day. She bought two $50 combos. Then, for $25 she bought two t-shirts for $5 each and five hoodies for $2 each. Then, she bought sneakers for $8 each. How much did she spend total?
|
||
==================Mistral-7B-Instruct-v0.2================
|
||
Marie bought 2 combos at $50 each, so that's $100. She bought 2 t-shirts at $5 each, which is $10. She bought 5 hoodies at $2 each, which is $10. The sneakers cost $8. So Marie spent a total of $118. ($100 + $10 + $8 = $118)
|
||
==================Mistral-7B-ReMax-v0.1================
|
||
Marie bought two combos at $50 each, so that's $100. She bought two t-shirts for $5 each, which totals $10. She bought five hoodies for $2 each, so that's $10. The sneakers cost $8.
|
||
|
||
So Marie spent $100 + $10 + $10 + $8 = $128 in total.
|
||
```
|
||
|
||
## Limitations
|
||
|
||
The Mistral-7B-ReMax-v0.1 model demonstrates that the optimization algorithm ReMax is effective. This model shares the same limitations as the Mistral-7B-Instruct-v0.2 model. In particular, it does not have any moderation mechanisms.
|
||
|
||
## Citation
|
||
|
||
|
||
**BibTeX:**
|
||
|
||
|
||
```
|
||
@article{li2023remax,
|
||
title={Remax: A simple, effective, and efficient method for aligning large language models},
|
||
author={Li, Ziniu and Xu, Tian and Zhang, Yushun and Yu, Yang and Sun, Ruoyu and Luo, Zhi-Quan},
|
||
journal={arXiv preprint arXiv:2310.10505},
|
||
year={2023}
|
||
}
|
||
```
|
||
|