|
--- |
|
library_name: trl |
|
license: apache-2.0 |
|
datasets: |
|
- argilla/dpo-mix-7k |
|
language: |
|
- en |
|
tags: |
|
- distilabel |
|
- dpo |
|
- rlaif |
|
- rlhf |
|
--- |
|
|
|
# CapybaraHermes-2.5-Mistral-7B |
|
<div> |
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/60420dccc15e823a685f2b03/Vmr0FtTvnny6Snm-UDM_n.png"> |
|
</div> |
|
|
|
<p align="center"> |
|
<a href="https://github.com/argilla-io/distilabel"> |
|
<img src="https://raw.githubusercontent.com/argilla-io/distilabel/main/docs/assets/distilabel-badge-light.png" alt="Built with Distilabel" width="200" height="32"/> |
|
</a> |
|
</p> |
|
|
|
|
|
This model is the launching partner of the [capybara-dpo dataset](https://huggingface.co./datasets/argilla/distilabel-capybara-dpo-9k-binarized) build with ⚗️ distilabel. It's a preference tuned [OpenHermes-2.5-Mistral-7B](https://huggingface.co./teknium/OpenHermes-2.5-Mistral-7B). |
|
|
|
CapybaraHermes has been preference tuned with LoRA and TRL for 3 epochs using argilla's [dpo mix 7k](https://huggingface.co./datasets/argilla/dpo-mix-7k). |
|
|
|
To test the impact on multi-turn performance we have used MTBench. We also include the Nous Benchmark results and Mistral-7B-Instruct-v0.2 for reference as it's a strong 7B model on MTBench: |
|
|
|
| Model | AGIEval | GPT4All | TruthfulQA | Bigbench | MTBench First Turn | MTBench Second Turn | Nous avg. | MTBench avg. | |
|
|-----------------------------------|---------|---------|------------|----------|------------|-------------|-----------|--------------| |
|
| argilla/CapybaraHermes-2.5-Mistral-7B | **43.8** | **73.35** | 57.07 | **42.44** | 8.24375 | **7.5625** | 54.16 | **7.903125** | |
|
| teknium/OpenHermes-2.5-Mistral-7B | 42.75 | 72.99 | 52.99 | 40.94 | **8.25** | 7.2875 | 52.42 | 7.76875 | |
|
| Mistral-7B-Instruct-v0.2 | 38.5 | 71.64 | **66.82** | 42.29 | 7.8375 | 7.1 | **54.81** | 7.46875 | |
|
|
|
The most interesting aspect in the context of the capybara-dpo dataset is the increased performance in MTBench Second Turn scores. |
|
|
|
For the merge lovers, we also preference tuned Beagle14-7B with a mix of capybara-dpo and distilabel orca pairs using the same recipe as NeuralBeagle (see [ YALL - Yet Another LLM Leaderboard](https://huggingface.co./spaces/mlabonne/Yet_Another_LLM_Leaderboard) for reference): |
|
|
|
| Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average| |
|
|------------------------------------------------------------------------------------------------------------------------------------|------:|------:|---------:|-------:|------:| |
|
|[DistilabelBeagle14-7B](https://huggingface.co./dvilasuero/DistilabelBeagle14-7B)| 45.29| 76.92| 71.66| 48.78| 60.66| |
|
|
|
|
|
|
|
|
|
## Model Details |
|
|
|
### Model Description |
|
|
|
<!-- Provide a longer summary of what this model is. --> |
|
|
|
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. |
|
|
|
- **Developed by:** Argilla |
|
- **Shared by [optional]:** Argilla |
|
- **Model type:** 7B chat model |
|
- **Language(s) (NLP):** English |
|
- **License:** Same as OpenHermes |
|
- **Finetuned from model [optional]:** [OpenHermes-2.5-Mistral-7B](https://huggingface.co./teknium/OpenHermes-2.5-Mistral-7B) |
|
|
|
|
