ArtusDev commited on
Commit
c480ff8
·
verified ·
1 Parent(s): 78e13bd

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -43
README.md CHANGED
@@ -1,47 +1,13 @@
1
  ---
2
- license: other
 
 
 
 
 
 
3
  ---
4
- # Join our Discord! https://discord.gg/Nbv9pQ88Xb
5
- ## Nearly 4000 members strong 💪 Now with more channels! A hub for users and makers alike!
6
- ---
7
-
8
- [BeaverAI](https://huggingface.co/BeaverAI) proudly presents...
9
-
10
- # Skyfall 36B v2
11
-
12
- *Skyfall v2 is an upscaled version of Mistral Small 2501 with continued training for creativity and RP.*
13
-
14
- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65f2fd1c25b848bd061b5c2e/BTVVnSnCRmysFKKqRaDvu.png)
15
-
16
- ## Special Thanks
17
- - Thank you to each and everyone who donated and subscribed in [Ko-Fi](https://ko-fi.com/thedrummer) to make our venture a little bit easier.
18
- - I'm also recently unemployed. I am a Software Developer with 8 years of experience in Web, API, AI, and adapting to new tech and requirements. If you're hiring, feel free to reach out to me however.
19
- - To commercial hosters of my models: If you profit off someone's work, kindly consider contributing to the cause rather than turning a blind eye to those who provide value and are in need. A subscription/donation to my KoFi would be greatly appreciated!
20
-
21
- ## Supported Chat Templates
22
- - Mistral v7 Tekken (highly recommended)
23
- - Metharme (not recommended)
24
- - Alpaca (may be interesting, especially for cyoa / story)
25
-
26
- ## Description
27
-
28
- > Creativity, good writing style, good instruct, chain of thought capability, mathematics understanding, and solid tool use performance... This model is peak! This will be my new daily model over all the 70Bs I have used.
29
-
30
- > Skyfall v2 is without a doubt my favorite model I've ever managed to run locally, bar none
31
-
32
- > skyfall is kinda nuts i am quite impressed
33
-
34
- > The biggest stand out for me is how good Skyfall handles size differences especially. It actually beats all of the 70b's I have used for descriptions of how the character worked around our size difference.
35
-
36
- > I played with the Skyfall 3bit model, taking a new character card with which I had not previously RP'd, and damn, it was so alive! The character's speech was conceptually correct, not as dry as 24b, there was a comedy tag and damn I really laughed in places. I really liked it, maybe it was the specific prompt that played great together with Skyfall.
37
-
38
- > Seriously though, Skyfall is just insanely good for some reason
39
-
40
- > How did you make skyfall so good
41
 
42
- ## Links
43
- - Original: https://huggingface.co/TheDrummer/Skyfall-36B-v2
44
- - GGUF: https://huggingface.co/TheDrummer/Skyfall-36B-v2-GGUF
45
- - iMatrix (recommended): https://huggingface.co/bartowski/TheDrummer_Skyfall-36B-v2-GGUF
46
 
47
- ![image/gif](https://cdn-uploads.huggingface.co/production/uploads/65f2fd1c25b848bd061b5c2e/KU3Y3T0T9tT_OhUG_4iGR.gif)
 
1
  ---
2
+ base_model:
3
+ - TheDrummer/Skyfall-36B-v2
4
+ library_name: transformers
5
+ base_model_relation: quantized
6
+ tags:
7
+ - exl2
8
+ - 7-bit
9
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
 
11
+ This is an EXL2 quant (7.0bpw H8) of [TheDrummer/Skyfall-36B-v2](https://huggingface.co/TheDrummer/Skyfall-36B-v2).
 
 
 
12
 
13
+ EXL2 Quants by ArtusDev.