DavidAU commited on
Commit
b973c33
1 Parent(s): 7345506

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +25 -10
README.md CHANGED
@@ -11,12 +11,13 @@ tags:
11
  - story telling
12
  - 32 bit upscale
13
  - ultra high precision
 
14
  ---
15
 
16
- <B> Ultra High Quality - 20B Dark Forest Version 1 - 32 bit upscale </b>
17
 
18
  Fully rebuilt from master files, including full merge(s) to maintain full 32 bit precision right
19
- up until it is compressed into GGUF files.
20
 
21
  The result is far superior performance in reasoning, depth, nuence and emotion.
22
 
@@ -24,22 +25,36 @@ The result is far superior performance in reasoning, depth, nuence and emotion.
24
 
25
  Better prose, better instruction following and stronger creative brainpower.
26
 
27
- This is an all around upgrade.
28
-
29
- All GGUF quants are improved using 32 bit transfer.
30
-
31
- On average this means a q4km operates at Q6 levels and Q6 and Q8 exceed orginal model full precision performance.
32
 
33
  Perplexity drop (lower is better) is close to 10% (over 600 points for q4km) for all quants.
34
 
35
- That means precision has been enhanced for all 20 billion parameters.
 
36
 
37
- Quants uploading now. Imatrix quants to follow shortly.
 
 
38
 
39
  For more details, including a list of enhancements see our other 32 bit upscale rebuild here:
40
 
41
  [ https://huggingface.co/DavidAU/Psyonic-Cetacean-Ultra-Quality-20b-GGUF ]
42
 
43
- For orginal model spec and information please visit:
 
 
 
 
 
 
 
 
 
 
 
 
 
 
44
 
 
45
  [ https://huggingface.co/TeeZee/DarkForest-20B-v1.0 ]
 
11
  - story telling
12
  - 32 bit upscale
13
  - ultra high precision
14
+ - nsfw
15
  ---
16
 
17
+ <B> Ultra High Quality - 20B Dark Forest Version 1.0 - 32 bit upscale </b>
18
 
19
  Fully rebuilt from master files, including full merge(s) to maintain full 32 bit precision right
20
+ up until it is compressed into GGUF files which results on a top to bottom upgrade.
21
 
22
  The result is far superior performance in reasoning, depth, nuence and emotion.
23
 
 
25
 
26
  Better prose, better instruction following and stronger creative brainpower.
27
 
28
+ On average this means a q4km operates at Q6 levels and Q6 and Q8 exceeds original model full precision performance.
 
 
 
 
29
 
30
  Perplexity drop (lower is better) is close to 10% (over 600 points for q4km) for all quants.
31
 
32
+ That means precision has been enhanced for all 20 billion parameters which affects "brain density" / "function",
33
+ instruction following and output quality.
34
 
35
+ Quants uploading now.
36
+
37
+ Imatrix quants to follow shortly.
38
 
39
  For more details, including a list of enhancements see our other 32 bit upscale rebuild here:
40
 
41
  [ https://huggingface.co/DavidAU/Psyonic-Cetacean-Ultra-Quality-20b-GGUF ]
42
 
43
+ Special thanks to "TEEZEE" for making a fantasic model.
44
+
45
+ <b> Info from the original model card: </B>
46
+
47
+ Warning: This model can produce NSFW content!
48
+
49
+ Results
50
+
51
+ - produces SFW nad NSFW content without issues, switches context seamlessly.
52
+ - good at following instructions.
53
+ - good at tracking multiple characters in one scene.
54
+ - very creative, scenarios produced are mature and complicated, model doesn't shy from writing about PTSD, menatal issues or complicated relationships.
55
+ - NSFW output is more creative and suprising than typical limaRP output.
56
+ - definitely for mature audiences, not only because of vivid NSFW content but also because of overall maturity of stories it produces.
57
+ - This is NOT Harry Potter level storytelling.
58
 
59
+ For original model spec and information please visit:
60
  [ https://huggingface.co/TeeZee/DarkForest-20B-v1.0 ]