Update README.md
#2
by
bartowski
- opened
README.md
CHANGED
|
@@ -36,6 +36,12 @@ This model is intended for researchers and practitioners looking for a powerful
|
|
| 36 |
## Training Data
|
| 37 |
The `Locutusque/Hyperion-2.0-Mistral-7B` model was fine-tuned on the Hyperion-v2.0 dataset, which amalgamates various datasets rich in diversity and complexity, including programming, medical texts, mathematical problems, and reasoning tasks.
|
| 38 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
## Evaluation Results
|
| 40 |
0-shot AGIEval
|
| 41 |
| Tasks |Version|Filter|n-shot| Metric |Value | |Stderr|
|
|
|
|
| 36 |
## Training Data
|
| 37 |
The `Locutusque/Hyperion-2.0-Mistral-7B` model was fine-tuned on the Hyperion-v2.0 dataset, which amalgamates various datasets rich in diversity and complexity, including programming, medical texts, mathematical problems, and reasoning tasks.
|
| 38 |
|
| 39 |
+
## Quants
|
| 40 |
+
|
| 41 |
+
ExLlamaV2: https://huggingface.co/bartowski/Hyperion-2.0-Mistral-7B-exl2
|
| 42 |
+
|
| 43 |
+
GGUF: https://huggingface.co/bartowski/Hyperion-2.0-Mistral-7B-GGUF
|
| 44 |
+
|
| 45 |
## Evaluation Results
|
| 46 |
0-shot AGIEval
|
| 47 |
| Tasks |Version|Filter|n-shot| Metric |Value | |Stderr|
|