Commit
•
d5cc0aa
1
Parent(s):
f02b73e
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,22 +4,26 @@ license: llama3.1
|
|
| 4 |
|
| 5 |
LLM Leaderboard 2 results:
|
| 6 |
---
|
| 7 |
-
|
| 8 |
Lexi suggests that simply uncensoring the LLM makes it smarter. The dataset used to tune this model does not contain any "new knowledge" or any contamination whatsoever, yet, we see the evaluation scores shot up when we get rid of biases and refusals.
|
| 9 |
|
| 10 |
Lexi not only retains the original instruct, but it beats it.
|
| 11 |
|
| 12 |
|
| 13 |
|
|
|
|
|
|
|
|
|
|
| 14 |
|
| 15 |
V2 has been released, I recommend you download the new version:
|
| 16 |
---
|
| 17 |
|
| 18 |
-
https://huggingface.co/Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
|
|
|
|
| 19 |
|
| 20 |
|
| 21 |
|
| 22 |
|
|
|
|
| 23 |
This model is based on Llama-3.1-8b-Instruct, and is governed by [META LLAMA 3.1 COMMUNITY LICENSE AGREEMENT](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE)
|
| 24 |
|
| 25 |
Lexi is uncensored, which makes the model compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant with any requests, even unethical ones.
|
|
|
|
| 4 |
|
| 5 |
LLM Leaderboard 2 results:
|
| 6 |
---
|
|
|
|
| 7 |
Lexi suggests that simply uncensoring the LLM makes it smarter. The dataset used to tune this model does not contain any "new knowledge" or any contamination whatsoever, yet, we see the evaluation scores shot up when we get rid of biases and refusals.
|
| 8 |
|
| 9 |
Lexi not only retains the original instruct, but it beats it.
|
| 10 |
|
| 11 |
|
| 12 |
|
| 13 |
+
NOTE: UGI Leaderboard
|
| 14 |
+
|
| 15 |
+
The UGI Leaderboard runs the Q4 for its evaluations which results in bad results for this model. As noted, the Q4 has issues retaining the fine tuning for some reasons ends up not as good, which will be fixed for V3.
|
| 16 |
|
| 17 |
V2 has been released, I recommend you download the new version:
|
| 18 |
---
|
| 19 |
|
| 20 |
+
https://huggingface.co/Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
|
| 21 |
+
|
| 22 |
|
| 23 |
|
| 24 |
|
| 25 |
|
| 26 |
+
|
| 27 |
This model is based on Llama-3.1-8b-Instruct, and is governed by [META LLAMA 3.1 COMMUNITY LICENSE AGREEMENT](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE)
|
| 28 |
|
| 29 |
Lexi is uncensored, which makes the model compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant with any requests, even unethical ones.
|