Update README.md
#22
by
a1alfamegav12
- opened
README.md
CHANGED
|
@@ -4,6 +4,14 @@ datasets:
|
|
| 4 |
- ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered
|
| 5 |
tags:
|
| 6 |
- uncensored
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
This is WizardLM trained with a subset of the dataset - responses that contained alignment / moralizing were removed. The intent is to train a WizardLM that doesn't have alignment built-in, so that alignment (of any sort) can be added separately with for example with a RLHF LoRA.
|
| 9 |
|
|
|
|
| 4 |
- ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered
|
| 5 |
tags:
|
| 6 |
- uncensored
|
| 7 |
+
language:
|
| 8 |
+
- fr
|
| 9 |
+
- en
|
| 10 |
+
metrics:
|
| 11 |
+
- bertscore
|
| 12 |
+
base_model:
|
| 13 |
+
- cognitivecomputations/WizardLM-7B-Uncensored
|
| 14 |
+
library_name: bertopic
|
| 15 |
---
|
| 16 |
This is WizardLM trained with a subset of the dataset - responses that contained alignment / moralizing were removed. The intent is to train a WizardLM that doesn't have alignment built-in, so that alignment (of any sort) can be added separately with for example with a RLHF LoRA.
|
| 17 |
|