Update README.md
Browse files
README.md
CHANGED
|
@@ -20,8 +20,6 @@ Calibration dataset: <a href="https://huggingface.co/datasets/cosmicvalor/toxic-
|
|
| 20 |
| [8_0](https://huggingface.co/Apel-sin/llama-3-8B-abliterated-v3-exl2/tree/8_0) | 8.0 | 8.0 | 10.1 GB | 10.5 GB | 11.5 GB | 13.6 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
|
| 21 |
| [6_5](https://huggingface.co/Apel-sin/llama-3-8B-abliterated-v3-exl2//tree/6_5) | 6.5 | 8.0 | 8.9 GB | 9.3 GB | 10.3 GB | 12.4 GB | Very similar to 8.0, good tradeoff of size vs performance, **recommended**. |
|
| 22 |
|
| 23 |
-
# ORIGINAL README
|
| 24 |
-
|
| 25 |
# Llama-3-8B-Instruct-abliterated-v3 Model Card
|
| 26 |
|
| 27 |
[My Jupyter "cookbook" to replicate the methodology can be found here, refined library coming soon](https://huggingface.co/failspy/llama-3-70B-Instruct-abliterated/blob/main/ortho_cookbook.ipynb)
|
|
|
|
| 20 |
| [8_0](https://huggingface.co/Apel-sin/llama-3-8B-abliterated-v3-exl2/tree/8_0) | 8.0 | 8.0 | 10.1 GB | 10.5 GB | 11.5 GB | 13.6 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
|
| 21 |
| [6_5](https://huggingface.co/Apel-sin/llama-3-8B-abliterated-v3-exl2//tree/6_5) | 6.5 | 8.0 | 8.9 GB | 9.3 GB | 10.3 GB | 12.4 GB | Very similar to 8.0, good tradeoff of size vs performance, **recommended**. |
|
| 22 |
|
|
|
|
|
|
|
| 23 |
# Llama-3-8B-Instruct-abliterated-v3 Model Card
|
| 24 |
|
| 25 |
[My Jupyter "cookbook" to replicate the methodology can be found here, refined library coming soon](https://huggingface.co/failspy/llama-3-70B-Instruct-abliterated/blob/main/ortho_cookbook.ipynb)
|