Update README.md
Browse files
README.md
CHANGED
|
@@ -3,6 +3,8 @@ license: llama2
|
|
| 3 |
---
|
| 4 |
EXL2 quants of alpindale/goliath-120b (https://huggingface.co/alpindale/goliath-120b), to be used on exllamav2.
|
| 5 |
|
|
|
|
|
|
|
| 6 |
Calibration dataset is a cleaned, fixed pippa RP dataset, which does affect the results (in favor) for RP usage. You can find the calibration dataset [here.](https://huggingface.co/datasets/royallab/PIPPA-cleaned)
|
| 7 |
|
| 8 |
I've added a measurement.json file on the main branch if you want to do your own quants.
|
|
@@ -13,8 +15,6 @@ I've added a measurement.json file on the main branch if you want to do your own
|
|
| 13 |
|
| 14 |
[3bpw](https://huggingface.co/Panchovix/goliath-120b-exl2-rpcal/tree/3bpw)
|
| 15 |
|
| 16 |
-
Update 06/01/2024: Updated with new quant method after 2 months, thanks for the measurement [here](https://github.com/turboderp/exllamav2/files/13846439/goliath-120b-rpcal-measurement.json)
|
| 17 |
-
|
| 18 |
# Original model card
|
| 19 |
|
| 20 |
# Goliath 120B
|
|
|
|
| 3 |
---
|
| 4 |
EXL2 quants of alpindale/goliath-120b (https://huggingface.co/alpindale/goliath-120b), to be used on exllamav2.
|
| 5 |
|
| 6 |
+
Update 06/01/2024: Updated with new quant method after some time, thanks for the measurement [here](https://github.com/turboderp/exllamav2/files/13846439/goliath-120b-rpcal-measurement.json)
|
| 7 |
+
|
| 8 |
Calibration dataset is a cleaned, fixed pippa RP dataset, which does affect the results (in favor) for RP usage. You can find the calibration dataset [here.](https://huggingface.co/datasets/royallab/PIPPA-cleaned)
|
| 9 |
|
| 10 |
I've added a measurement.json file on the main branch if you want to do your own quants.
|
|
|
|
| 15 |
|
| 16 |
[3bpw](https://huggingface.co/Panchovix/goliath-120b-exl2-rpcal/tree/3bpw)
|
| 17 |
|
|
|
|
|
|
|
| 18 |
# Original model card
|
| 19 |
|
| 20 |
# Goliath 120B
|