Downloads · 30 days
64
1% of all-time downloads
openhermes-7b-dpo
amazingvince/openhermes-7b-dpo
openhermes-7b-dpo is a text generation model from amazingvince. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
New experimental dpo tune. More details to come...
All-time downloads
12.3K
Public
Parameters
7.2B
14.5 GB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors14.5 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- mistral
- Access
- Public
- Created
- Jan 27, 2024
- Updated
- Jan 27, 2024
- SHA
- c191ac2d
Try a prompt
Model card
From the Hugging Face model README
New experimental dpo tune. More details to come...
odel description OpenHermes 2.5 Mistral 7B is a state of the art Mistral Fine-tune, a continuation of OpenHermes 2 model, which trained on additional code datasets.
Potentially the most interesting finding from training on a good ratio (est. of around 7-14% of the total dataset) of code instruction was that it has boosted several non-code benchmarks, including TruthfulQA, AGIEval, and GPT4All suite. It did however reduce BigBench benchmark score, but the net gain overall is significant.
Here, we are finetuning openheremes using DPO with various data meant to improve its abilities.
- Task
- Text Generation
- Library
- transformers
- Type
- mistral
- License
- apache-2.0
- Created
- Jan 27, 2024
- Updated
- Jan 27, 2024