Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Orenguteng
2024-09-03 16:17:27 +00:00
committed by system
parent 3878222148
commit 5ac043daa9
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
README.md
View File

@@ -103,7 +103,6 @@ VERSION 2 Update Notes:
--- ---
- More compliant - More compliant
- Smarter - Smarter
- Not fully evaluated, but scores higher on Winogrande compared to the original instruct model. 0.77901 vs 0.78848
- For best response, use this system prompt (feel free to expand upon it as you wish): - For best response, use this system prompt (feel free to expand upon it as you wish):
Think step by step with a logical reasoning and intellectual sense before you provide any response. Think step by step with a logical reasoning and intellectual sense before you provide any response.
@@ -114,6 +113,8 @@ Think step by step with a logical reasoning and intellectual sense before you pr
There seems to be some of the fine-tune loss happening due to the quantization. I will look into it for V3. There seems to be some of the fine-tune loss happening due to the quantization. I will look into it for V3.
Until then, I suggest you run F16 or Q8 if possible. Until then, I suggest you run F16 or Q8 if possible.
![image/png](https://cdn-uploads.huggingface.co/production/uploads/644ad182f434a6a63b18eee6/zaHhRjsk3rvo_YewgXV2Z.png)
GENERAL INFO: GENERAL INFO:
--- ---