Hugging Face's logo

Panchovix
/
goliath-120b-exl2-rpcal

Model card Files Community
8
Panchovix commited on
Commit
5a57db3
·
1 Parent(s): 2acbbf3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -3,7 +3,7 @@ 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://discord.com/channels/1111983596572520458/1152699950208139415/1152700764230271076) (You will need to be on TheBloke server)
7
 
8
  I've added a measurement.json file on the main branch if you want to do your own quants.
9
 
 
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.
9