58 lines
2.1 KiB
Markdown
58 lines
2.1 KiB
Markdown
---
|
||
license: apache-2.0
|
||
datasets:
|
||
- openbmb/UltraFeedback
|
||
- openbmb/UltraInteract_pair
|
||
tags:
|
||
- reasoning
|
||
- preference_learning
|
||
- kto
|
||
pipeline_tag: text-generation
|
||
base_model: openbmb/Eurus-7b-kto
|
||
---
|
||
|
||
# openbmb/Eurus-7b-kto-GGUF
|
||
|
||
- This is quantized version of [openbmb/Eurus-7b-kto](https://huggingface.co/openbmb/Eurus-7b-kto)
|
||
|
||
# Model Description
|
||
|
||
Eurus-7B-KTO is [KTO](https://arxiv.org/abs/2402.01306) fine-tuned from [Eurus-7B-SFT](https://huggingface.co/openbmb/Eurus-7b-sft) on all multi-turn trajectory pairs in [UltraInteract](https://huggingface.co/openbmb/UltraInteract) and all pairs in [UltraFeedback](https://huggingface.co/openbmb/UltraFeedback).
|
||
|
||
It achieves the best overall performance among open-source models of similar sizes and even outperforms specialized models in corresponding domains in many cases. Notably, Eurus-7B-KTO outperforms baselines that are 5× larger.
|
||
|
||
## Usage
|
||
|
||
We apply tailored prompts for coding and math, consistent with UltraInteract data formats:
|
||
|
||
**Coding**
|
||
|
||
```
|
||
[INST] Write Python code to solve the task:
|
||
{Instruction} [/INST]
|
||
```
|
||
**Math-CoT**
|
||
|
||
```
|
||
[INST] Solve the following math problem step-by-step.
|
||
Simplify your answer as much as possible. Present your final answer as \\boxed{Your Answer}.
|
||
{Instruction} [/INST]
|
||
```
|
||
|
||
**Math-PoT**
|
||
|
||
```
|
||
[INST] Tool available:
|
||
[1] Python interpreter
|
||
When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment.
|
||
Solve the following math problem step-by-step.
|
||
Simplify your answer as much as possible.
|
||
{Instruction} [/INST]
|
||
```
|
||
|
||
## Evaluation
|
||
- Eurus, both the 7B and 70B variants, achieve the best overall performance among open-source models of similar sizes. Eurus even outperforms specialized models in corresponding domains in many cases. Notably, Eurus-7B outperforms baselines that are 5× larger, and Eurus-70B achieves better performance than GPT-3.5 Turbo.
|
||
- Preference learning with UltraInteract can further improve performance, especially in math and the multi-turn ability.
|
||
<img src="figures_main_exp.png" alt="stats" style="zoom: 40%;" />
|
||
|