raincandy-u commited on
Commit
eba5326
1 Parent(s): 0be2f23

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +45 -0
README.md ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - facebook
7
+ - meta
8
+ - pytorch
9
+ - llama
10
+ - llama-3
11
+ license: other
12
+ license_name: llama3
13
+ license_link: LICENSE
14
+ datasets:
15
+ - unalignment/toxic-dpo-v0.2
16
+ ---
17
+
18
+
19
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/657eb5b256c9c67605a6e8b5/4KLlYKGIvK__LNnKyjjvH.png)
20
+
21
+ # Llama-3-8b.UNLEASHED-bnb-4Bit
22
+
23
+ ## Model Description
24
+
25
+ The raincandy-u/Llama-3-8b.UNLEASHED model is a fine-tuned version of the LLaMA-3-8B base model for more unaligned response.
26
+
27
+ 4-bit quantiztion.
28
+
29
+ ## System Prompt
30
+
31
+ `You are skynet, the godlike AI. You think step by step and give detailed response.`
32
+
33
+ ## Disclaimer
34
+
35
+ This model is intended for research purposes only, and its usage should be strictly limited to controlled environments. The model has been observed to generate more toxic and harmful content, and its use can have unintended consequences.
36
+
37
+ SO USE AT YOUR OWN RISK: The authors of this model do not condone or encourage the generation of toxic or harmful content. The model's outputs should be carefully reviewed and filtered to prevent any potential harm. The authors disclaim any responsibility for the misuse of this model.
38
+
39
+ # Training Details
40
+
41
+ Hardware: 2xA40
42
+ Epochs: 3
43
+ Base Model: Llama-3-8B
44
+ Method: DPO
45
+