|
--- |
|
license: apache-2.0 |
|
--- |
|
GGUF files for [Magic-Dolphin-7b](https://huggingface.co/InferenceIllusionist/Magic-Dolphin-7b) |
|
|
|
--- |
|
# Magic-Dolphin-7b |
|
<img src="https://huggingface.co/InferenceIllusionist/Magic-Dolphin-7b/resolve/main/magic-dolphin.jfif" width="500"/> |
|
|
|
For fp16 files please look [here](https://huggingface.co/InferenceIllusionist/Magic-Dolphin-7b) |
|
|
|
A linear merge of: |
|
- [cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser](https://huggingface.co/cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser) |
|
- [Locutusque/Hyperion-1.5-Mistral-7B](https://huggingface.co/Locutusque/Hyperion-1.5-Mistral-7B) |
|
- [ibm/merlinite-7b](https://huggingface.co/ibm/merlinite-7b) |
|
|
|
|
|
These three models showed excellent acumen in technical topics so I wanted to see how they would behave together in a merge. Several different ratios were tested before this release, in the end a higher weighting for merlinite-7b helped smooth out some edges. This model is a test of how LAB tuning is impacted by merges with models leveraging DPO. |
|
|
|
### Benchmark Performance |
|
| Name | Avg. | ARC | HellaSwag | MMLU | TruthfulQA | Winograde | GSM8K | |
|
| ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | |
|
| <b>Magic-Dolphin-7b</b> | <u><b>67.48</b></u> | 65.78 | 85.61 | 64.64 | 58.01 | <u><b>79.64</b></u> | <u><b>51.18</b></u> | |
|
| dolphin-2.6-mistral-7b-dpo-laser | 67.28 | 66.3 | 85.73 | 63.16 | 61.71 | 79.16 | 47.61 | |
|
| merlinite-7b | N/A | 63.99 | 84.37 | 64.88 | N/A | 78.24 | N/A | |
|
| Hyperion-1.5-Mistral-7B | 61.43 | 60.49 | 83.64 | 63.57 | 41.78 | 78.61 | 40.49 | |
|
|
|
This was my first experiment with merging models so any feedback is greatly appreciated. |
|
|
|
Uses Alpaca template. |
|
|
|
<p align="center"> |
|
|
|
</p> |
|
|
|
<b>Sample Question</b> |
|
<img src="https://huggingface.co/InferenceIllusionist/Magic-Dolphin-7b/resolve/main/magic-dolphin.JPG" width="750"/> |
|
|
|
## Merge Details |
|
### Merge Method |
|
|
|
This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser](https://huggingface.co/cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser) |
|
* [Locutusque/Hyperion-1.5-Mistral-7B](https://huggingface.co/Locutusque/Hyperion-1.5-Mistral-7B) |
|
* [ibm/merlinite-7b](https://huggingface.co/ibm/merlinite-7b) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
models: |
|
- model: models/dolphin-2.6-mistral-7b-dpo-laser |
|
parameters: |
|
weight: 1.0 |
|
- model: models/Hyperion-1.5-Mistral-7B |
|
parameters: |
|
weight: 0.3 |
|
- model: models/merlinite-7b |
|
parameters: |
|
weight: 0.5 |
|
merge_method: linear |
|
dtype: float16 |
|
|
|
``` |
