Text Generation
GGUF
English
creative
creative writing
fiction writing
plot generation
sub-plot generation
story generation
scene continue
storytelling
fiction story
story
writing
fiction
roleplaying
horror
general usage
roleplay
neo quant
fantasy
story telling
ultra high precision
Inference Endpoints
imatrix
conversational
Update README.md
Browse files
README.md
CHANGED
@@ -17,8 +17,6 @@ tags:
|
|
17 |
- writing
|
18 |
- fiction
|
19 |
- roleplaying
|
20 |
-
- swearing
|
21 |
-
- rp
|
22 |
- horror
|
23 |
- story
|
24 |
- general usage
|
@@ -48,12 +46,11 @@ The DARK HORROR NEO Imatrix datasets does the following:
|
|
48 |
- Increases the raw vividness of prose.
|
49 |
- In some cases increase instruction following of the model (ie story, and prose).
|
50 |
- Brings a sense of impending "horror", THEN brings the "horror".
|
|
|
51 |
|
52 |
I created the HORROR datasets using <A href="https://huggingface.co/DavidAU/L3-Stheno-Maid-Blackroot-Grand-HORROR-16B-GGUF">Grand Horror 16B</a> using 90+ different horror prompts for generation.
|
53 |
This process created an incredibility intense, visceral and vivid horror stories in an ultra compact form - perfect for an Imatrix NEO class dataset.
|
54 |
|
55 |
-
Imagine taking the most intense scenes from 90+ top horror novels (but only the most intense one from each, cranked up to 11) and reading them each in order.
|
56 |
-
|
57 |
These Horror datasets have been tested on Command-R, Llama 3, Llama 3.1, Mistral Nemo and others. In all cases these "DARK HORROR" NEO class datasets move the model into "horror territory" so to speak.
|
58 |
|
59 |
A NEO Class dataset is a imatrix dataset formatted and calibrated to have maximum effect on a model. This process is a result
|
@@ -61,7 +58,7 @@ of a "deep dive" into testing several Imatrix datasets and measuring the differe
|
|
61 |
|
62 |
Please note this process is not the same (level) as a "fine tune", it is lighter than that.
|
63 |
|
64 |
-
That being said, if you are looking for intense, visceral and NSFW horror then the "Grand Horror 16B" (and it's brothers and sisters)
|
65 |
is the way to go:
|
66 |
|
67 |
[ https://huggingface.co/DavidAU/L3-Stheno-Maid-Blackroot-Grand-HORROR-16B-GGUF ]
|
|
|
17 |
- writing
|
18 |
- fiction
|
19 |
- roleplaying
|
|
|
|
|
20 |
- horror
|
21 |
- story
|
22 |
- general usage
|
|
|
46 |
- Increases the raw vividness of prose.
|
47 |
- In some cases increase instruction following of the model (ie story, and prose).
|
48 |
- Brings a sense of impending "horror", THEN brings the "horror".
|
49 |
+
- May produce and/or imply graphic horror depending on your prompt(s).
|
50 |
|
51 |
I created the HORROR datasets using <A href="https://huggingface.co/DavidAU/L3-Stheno-Maid-Blackroot-Grand-HORROR-16B-GGUF">Grand Horror 16B</a> using 90+ different horror prompts for generation.
|
52 |
This process created an incredibility intense, visceral and vivid horror stories in an ultra compact form - perfect for an Imatrix NEO class dataset.
|
53 |
|
|
|
|
|
54 |
These Horror datasets have been tested on Command-R, Llama 3, Llama 3.1, Mistral Nemo and others. In all cases these "DARK HORROR" NEO class datasets move the model into "horror territory" so to speak.
|
55 |
|
56 |
A NEO Class dataset is a imatrix dataset formatted and calibrated to have maximum effect on a model. This process is a result
|
|
|
58 |
|
59 |
Please note this process is not the same (level) as a "fine tune", it is lighter than that.
|
60 |
|
61 |
+
That being said, if you are looking for intense, visceral and NSFW horror (that is a specific use "Horror" with Finetuned models in it) then the "Grand Horror 16B" (and it's brothers and sisters)
|
62 |
is the way to go:
|
63 |
|
64 |
[ https://huggingface.co/DavidAU/L3-Stheno-Maid-Blackroot-Grand-HORROR-16B-GGUF ]
|