Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
tags:
|
| 6 |
+
- story
|
| 7 |
+
- roleplay
|
| 8 |
+
- creative
|
| 9 |
+
- rp
|
| 10 |
+
- fantasy
|
| 11 |
+
- story telling
|
| 12 |
+
- 32 bit upscale
|
| 13 |
+
- ultra high precision
|
| 14 |
+
- nsfw
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
<B> Ultra High Quality - 20B Dark Forest Version 2.0 - 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 superior performance in instruction following, reasoning, depth, nuance and emotion.
|
| 23 |
+
|
| 24 |
+
<img src="dark-forest.jpg">
|
| 25 |
+
|
| 26 |
+
On average this means a q4km operates at Q6 levels and Q6 and Q8 exceeds original model full precision performance.
|
| 27 |
+
|
| 28 |
+
Perplexity drop (lower is better) is close to 10% (over 752 points for q4km) for all quants.
|
| 29 |
+
|
| 30 |
+
That means precision has been enhanced for all 20 billion parameters which affects "brain density" / "function",
|
| 31 |
+
instruction following and output quality.
|
| 32 |
+
|
| 33 |
+
Imatrix quants to follow shortly.
|
| 34 |
+
|
| 35 |
+
For more details, including a list of enhancements see our other 32 bit
|
| 36 |
+
upscale of "Space Whale 20B" rebuild here:
|
| 37 |
+
|
| 38 |
+
[ https://huggingface.co/DavidAU/Psyonic-Cetacean-Ultra-Quality-20b-GGUF ]
|
| 39 |
+
|
| 40 |
+
Special thanks to "TEEZEE" for making a fantasic model.
|
| 41 |
+
|
| 42 |
+
<b> Info from the original model card: </B>
|
| 43 |
+
|
| 44 |
+
Warning: This model can produce NSFW content!
|
| 45 |
+
|
| 46 |
+
Results:
|
| 47 |
+
|
| 48 |
+
- main difference to v1.0 - model has much better sense of humor.
|
| 49 |
+
- produces SFW nad NSFW content without issues, switches context seamlessly.
|
| 50 |
+
- good at following instructions.
|
| 51 |
+
- good at tracking multiple characters in one scene.
|
| 52 |
+
- very creative, scenarios produced are mature and complicated, model doesn't shy from writing about PTSD, menatal issues or complicated relationships.
|
| 53 |
+
- NSFW output is more creative and suprising than typical limaRP output.
|
| 54 |
+
- definitely for mature audiences, not only because of vivid NSFW content but also because of overall maturity of stories it produces.
|
| 55 |
+
- This is NOT Harry Potter level storytelling.
|
| 56 |
+
|
| 57 |
+
|
| 58 |
+
For original model spec and information please visit:
|
| 59 |
+
|
| 60 |
+
[ https://huggingface.co/TeeZee/DarkForest-20B-v2.0 ]
|