Adding README
Browse files
README.md
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
license: llama3
|
5 |
+
library_name: transformers
|
6 |
+
tags:
|
7 |
+
- merge
|
8 |
+
base_model:
|
9 |
+
- SillyTilly/Meta-Llama-3.1-70B
|
10 |
+
- SillyTilly/Meta-Llama-3.1-70B-Instruct
|
11 |
+
- unsloth/Llama-3.3-70B-Instruct
|
12 |
+
- SicariusSicariiStuff/Negative_LLAMA_70B
|
13 |
+
---
|
14 |
+
|
15 |
+
#
|
16 |
+
<img src=https://huggingface.co/altomek/RE-70B-ASED/resolve/main/RE.png>
|
17 |
+
<a href="https://www.youtube.com/watch?v=kYje-wdAUsg" title="i_o - Audio Dust" target="_blank">intro music...</a>
|
18 |
+
|
19 |
+
## Llama RE-70B-ASED
|
20 |
+
|
21 |
+
I desired a model that would unlock full Llama personality but still could follow instructions.
|
22 |
+
|
23 |
+
|
24 |
+
### Ingridients
|
25 |
+
|
26 |
+
- [Llama-3.1-70B](https://huggingface.co/SillyTilly/Meta-Llama-3.1-70B)
|
27 |
+
|
28 |
+
- [Llama-3.1-70B-Instruct](https://huggingface.co/SillyTilly/Meta-Llama-3.1-70B-Instruct)
|
29 |
+
|
30 |
+
- [Llama-3.3-70B-Instruct](https://huggingface.co/unsloth/Llama-3.3-70B-Instruct)
|
31 |
+
|
32 |
+
- [Negative_LLAMA_70B](https://huggingface.co/SicariusSicariiStuff/Negative_LLAMA_70B)
|
33 |
+
|
34 |
+
### Settings
|
35 |
+
|
36 |
+
Use Llama 3 template, model with ALpaca template sometimes halucinates and generates training materials ;P
|
37 |
+
|
38 |
+
|
39 |
+
### Quants
|
40 |
+
|
41 |
+
More quants are comming soon...
|
42 |
+
|
43 |
+
- [GGUF](https://huggingface.co/altomek/RE-70B-AS3D-GGUF)
|
44 |
+
|