Add Quants
Browse files
README.md
CHANGED
|
@@ -40,6 +40,12 @@ The `Locutusque/NeuralHyperion-2.0-Mistral-7B` model was fine-tuned on 1,550,000
|
|
| 40 |
## Evaluation Results
|
| 41 |
Coming soon.
|
| 42 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
## How to Use
|
| 44 |
```python
|
| 45 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
|
|
| 40 |
## Evaluation Results
|
| 41 |
Coming soon.
|
| 42 |
|
| 43 |
+
## Quants
|
| 44 |
+
|
| 45 |
+
ExLlamaV2: https://huggingface.co/bartowski/NeuralHyperion-2.0-Mistral-7B-exl2
|
| 46 |
+
|
| 47 |
+
GGUF: https://huggingface.co/bartowski/NeuralHyperion-2.0-Mistral-7B-GGUF
|
| 48 |
+
|
| 49 |
## How to Use
|
| 50 |
```python
|
| 51 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|