Update README.md
Browse files
README.md
CHANGED
|
@@ -6,6 +6,8 @@ language:
|
|
| 6 |
- en
|
| 7 |
---
|
| 8 |
|
|
|
|
|
|
|
| 9 |
This is a retraining of https://huggingface.co/WizardLM/WizardLM-13B-V1.0 with a filtered dataset, intended to reduce refusals, avoidance, and bias.
|
| 10 |
|
| 11 |
Note that LLaMA itself has inherent ethical beliefs, so there's no such thing as a "truly uncensored" model. But this model will be more compliant than WizardLM/WizardLM-13B-V1.0.
|
|
|
|
| 6 |
- en
|
| 7 |
---
|
| 8 |
|
| 9 |
+
This model is trained on top of CodeLlama-34b, which gives it some very good coding abilities.
|
| 10 |
+
|
| 11 |
This is a retraining of https://huggingface.co/WizardLM/WizardLM-13B-V1.0 with a filtered dataset, intended to reduce refusals, avoidance, and bias.
|
| 12 |
|
| 13 |
Note that LLaMA itself has inherent ethical beliefs, so there's no such thing as a "truly uncensored" model. But this model will be more compliant than WizardLM/WizardLM-13B-V1.0.
|