Downloads · 30 days
66
1% of all-time downloads
DistilHermes-2.5-Mistral-7B
eren23/DistilHermes-2.5-Mistral-7B
DistilHermes-2.5-Mistral-7B is a question answering model from eren23. Use it when the input is a question plus a passage. It is set up for transformers. The card lists the license as apache-2.0.
DPO Finetuned teknium/OpenHermes-2.5-Mistral-7B using argilla/distilabel-intel-orca-dpo-pairs.
All-time downloads
12.7K
Public
Parameters
7.2B
14.5 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors14.5 GB · 100%
At a glance
- Task
- Question Answering
- Library
- transformers
- License
- apache-2.0
- Model type
- mistral
- Access
- Public
- Created
- Jan 26, 2024
- Updated
- Mar 5, 2024
- SHA
- 769deb27
Try a prompt
Model card
From the Hugging Face model README
DPO Finetuned teknium/OpenHermes-2.5-Mistral-7B using argilla/distilabel-intel-orca-dpo-pairs.
Intel orca dpo pairs is a distilled version: https://huggingface.co/datasets/argilla/distilabel-intel-orca-dpo-pairs
of https://huggingface.co/datasets/Intel/orca_dpo_pairs
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 67.76 |
| AI2 Reasoning Challenge (25-Shot) | 65.87 |
| HellaSwag (10-Shot) | 84.78 |
| MMLU (5-Shot) | 63.65 |
| TruthfulQA (0-shot) | 54.24 |
| Winogrande (5-shot) | 78.22 |
| GSM8k (5-shot) | 59.82 |
- Task
- Question Answering
- Library
- transformers
- Type
- mistral
- License
- apache-2.0
- Languages
- en
- Created
- Jan 26, 2024
- Updated
- Mar 5, 2024