117 lines
4.6 KiB
Markdown
117 lines
4.6 KiB
Markdown
---
|
|
license: apache-2.0
|
|
language:
|
|
- en
|
|
---
|
|
# WestSeverus - 7B - DPO - v2
|
|
|
|
|
|
|
|
## ☘️ Model Description
|
|
|
|
WestSeverus-7B-DPO-v2 is a WestLake Family model trained over [WestSeverus-7B](https://huggingface.co/FelixChao/WestSeverus-7B).
|
|
|
|
The model was trained on several dpo datasets and it can perform well on basic math problem.
|
|
|
|
WestSeverus-7B-DPO-v2 can be used in mathematics, chemical, physics and even coding for further research and reference.
|
|
|
|
# 📖 Table of Contents
|
|
1. [Nous Benchmark Results](#🪄-nous-benchmark-results)
|
|
- AGIEval
|
|
- GPT4All
|
|
- TruthfulQA Scores
|
|
- BigBench
|
|
|
|
2. [Open LLM Leaderboard](#🏆-open-llm-leaderboard)
|
|
- ARC
|
|
- HellaSwag
|
|
- MMLU
|
|
- TruthfulQA
|
|
- Winogrande
|
|
- GSM8K
|
|
3. [EvalPlus Leaderboard](#⚡-evalplus-leaderboard)
|
|
- HumanEval
|
|
- HumanEval_Plus
|
|
- MBPP
|
|
- MBPP_Plus
|
|
4. [Prompt Format](#⚗️-prompt-format)
|
|
5. [Quantized Models](#🛠️-quantized-models)
|
|
6. [Gratitude](#🙏-gratitude)
|
|
|
|
## 🪄 Nous Benchmark Results
|
|
|
|
WestSeverus-7B-DPO-v2 is currently on the top of the [YALL - Yet Another LLM Leaderboard](https://huggingface.co/spaces/CultriX/Yet_Another_LLM_Leaderboard) created by CultriX and it outperforms on TruthfulQA Scores and BigBench.
|
|
|
|
| Model | Average | AGIEval | GPT4All | TruthfulQA | Bigbench |
|
|
|---|---:|---:|---:|---:|---:|
|
|
| [**WestSeverus-7B-DPO-v2**](https://huggingface.co/FelixChao/WestSeverus-7B-DPO-v2)| **60.98**| 45.29 | 77.2| **72.72**| **48.71**|
|
|
| [CultriX/Wernicke-7B-v1](https://huggingface.co/CultriX/Wernicke-7B-v1)| 60.73| 45.59 | 77.36 | 71.46 | 48.49 |
|
|
| [mlabonne/NeuralBeagle14-7B](https://huggingface.co/mlabonne/NeuralBeagle14-7B) | 60.25 |46.06|76.77 | 70.32 |47.86 |
|
|
| [CultriX/MistralTrix-v1](https://huggingface.co/CultriX/MistralTrix-v1) | 60.05 | 44.98 | 76.62 | 71.44 | 47.17 |
|
|
| [senseable/WestLake-7B-v2](https://huggingface.co/senseable/WestLake-7B-v2) | 59.42 | 44.27 | 77.86 | 67.46 | 48.09 |
|
|
| [mlabonne/Daredevil-7B](https://huggingface.co/mlabonne/Daredevil-7B) | 58.22 | 44.85 | 76.07 | 64.89 | 47.07 |
|
|
| [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) | 44.61 | 27.96 | 70.84 | 44.46 | 35.17 |
|
|
|
|
## 🏆 Open LLM Leaderboard
|
|
|
|
WestSeverus-7B-DPO-v2 is one of the top 7B model in Open LLM Leaderboard and it outperforms on TruthfulQA and GSM8K.
|
|
|
|
| Metric |Value|
|
|
|---------------------------------|----:|
|
|
|Avg. |75.29|
|
|
|AI2 Reasoning Challenge (25-Shot)|71.42|
|
|
|HellaSwag (10-Shot) |88.27|
|
|
|MMLU (5-Shot) |64.79|
|
|
|TruthfulQA (0-shot) |72.37|
|
|
|Winogrande (5-shot) |83.27|
|
|
|GSM8k (5-shot) |71.65|
|
|
|
|
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_FelixChao__WestSeverus-7B-DPO-v2)
|
|
|
|
## ⚡ EvalPlus Leaderboard
|
|
|
|
| Model | HumanEval | HumanEval_Plus| MBPP | MBPP_Plus |
|
|
|---|---:|---:|---:|---:|
|
|
| phi-2-2.7B |48.2|43.3|61.9|51.4|
|
|
| **WestSeverus-7B-DPO-v2**| 43.3 | 34.1 |TBD |TBD |
|
|
| SOLAR-10.7B-Instruct-v1.0 | 42.1 | 34.3 | 42.9 | 34.6 |
|
|
| CodeLlama-7B| 37.8| 34.1 | 57.6 |45.4 |
|
|
|
|
|
|
|
|
## ⚗️ Prompt Format
|
|
|
|
WestSeverus-7B-DPO-v2 was trained using the ChatML prompt templates with system prompts. An example follows below:
|
|
|
|
```
|
|
<|im_start|>system
|
|
{system_message}<|im_end|>
|
|
<|im_start|>user
|
|
{prompt}<|im_end|>
|
|
<|im_start|>assistant
|
|
```
|
|
|
|
## 🛠️ Quantized Models
|
|
|
|
### Another version of WestSeverus Model:
|
|
|
|
* [**PetroGPT/WestSeverus-7B-DPO**](https://huggingface.co/PetroGPT/WestSeverus-7B-DPO)
|
|
|
|
* **GGUF**: https://huggingface.co/TheBloke/WestSeverus-7B-DPO-GGUF
|
|
* **GGUF**: https://huggingface.co/s3nh/WestSeverus-7B-DPO-GGUF
|
|
* **GPTQ**: https://huggingface.co/TheBloke/WestSeverus-7B-DPO-GPTQ
|
|
* **AWQ**: https://huggingface.co/TheBloke/WestSeverus-7B-DPO-AWQ
|
|
|
|
### MaziyarPanahi/WestSeverus-7B-DPO-v2-GGUF
|
|
|
|
* **GGUF**: https://huggingface.co/MaziyarPanahi/WestSeverus-7B-DPO-v2-GGUF
|
|
|
|
## 🙏 Gratitude
|
|
|
|
* Thanks to @senseable for [senseable/WestLake-7B-v2](https://huggingface.co/senseable/WestLake-7B-v2).
|
|
* Thanks to @jondurbin for [jondurbin/truthy-dpo-v0.1 dataset](https://huggingface.co/datasets/jondurbin/truthy-dpo-v0.1).
|
|
* Thanks to @Charles Goddard for MergeKit.
|
|
* Thanks to @TheBloke, @s3nh, @MaziyarPanahi for Quantized Models.
|
|
* Thanks to @mlabonne, @CultriX for YALL - Yet Another LLM Leaderboard.
|
|
* Thank you to all the other people in the Open Source AI community who utilized this model for further research and improvement.
|