Downloads · 30 days
2
4% of all-time downloads
hedronstone_-_OpenHermes-7B-Symbolic-4bits
RichardErkhov/hedronstone_-_OpenHermes-7B-Symbolic-4bits
hedronstone_-_OpenHermes-7B-Symbolic-4bits is a text generation model from RichardErkhov. Use it when you need the model to write or continue text. It is set up for transformers.
All-time downloads
45
Public
Parameters
7.4B
4.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.5 GB · 100%
Parameter types
How the weights are stored.
U87B · 95%
Try a prompt
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
OpenHermes-7B-Symbolic - bnb 4bits
- Model creator: https://huggingface.co/hedronstone/
- Original model: https://huggingface.co/hedronstone/OpenHermes-7B-Symbolic/
Original model description:
license: apache-2.0
OpenHermes-7B-Symbolic <img src="https://i.ibb.co/zJJyywL/DALL-E-2023-12-10-22-19-40-A-digital-art-piece-that-creatively-represents-the-famous-Thinking-Man-st.png" width="45%" height="auto">
Model description
OpenHermes-7B-Symbolic is a OpenHermes-2.5-Mistral-7B fine-tuned on 93K comprehensive and meticulously curated samples. Each sample was structured to facilitate the model's understanding and generation of complex, hierarchical ICD medical coding system.
| Benchmark | OpenHermes-7B-Symbolic | OpenHermes-2.5-Mistral-7B |
|---|---|---|
| Average | 64.44 | 65.26 |
| ARC | 63.14 | 64.93 |
| HellaSwag | 82.73 | 84.18 |
| MMLU | 62.62 | 63.64 |
| TruthfulQA | 48.82 | 52.24 |
| Winogrande | 75.85 | 78.06 |
| GSM8K | 53.45 | 48.52 |
- Task
- Text Generation
- Library
- transformers
- Type
- mistral
- Created
- May 17, 2024
- Updated
- May 17, 2024