sleepdeprived3 commited on
Commit
a6dcdda
·
verified ·
1 Parent(s): 24173cc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +55 -48
README.md CHANGED
@@ -1,8 +1,11 @@
1
  ---
2
- base_model: ReadyArt/Forgotten-Safeword-12B-3.6
 
 
3
  language:
4
  - en
5
  license: apache-2.0
 
6
  tags:
7
  - nsfw
8
  - explicit
@@ -10,52 +13,56 @@ tags:
10
  - unaligned
11
  - dangerous
12
  - ERP
13
- - llama-cpp
14
- - gguf-my-repo
15
- base_model_relation: finetune
16
- inference: false
17
  ---
18
 
19
- # sleepdeprived3/Forgotten-Safeword-12B-3.6-Q8_0-GGUF
20
- This model was converted to GGUF format from [`ReadyArt/Forgotten-Safeword-12B-3.6`](https://huggingface.co/ReadyArt/Forgotten-Safeword-12B-3.6) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
21
- Refer to the [original model card](https://huggingface.co/ReadyArt/Forgotten-Safeword-12B-3.6) for more details on the model.
22
-
23
- ## Use with llama.cpp
24
- Install llama.cpp through brew (works on Mac and Linux)
25
-
26
- ```bash
27
- brew install llama.cpp
28
-
29
- ```
30
- Invoke the llama.cpp server or the CLI.
31
-
32
- ### CLI:
33
- ```bash
34
- llama-cli --hf-repo sleepdeprived3/Forgotten-Safeword-12B-3.6-Q8_0-GGUF --hf-file forgotten-safeword-12b-3.6-q8_0.gguf -p "The meaning to life and the universe is"
35
- ```
36
-
37
- ### Server:
38
- ```bash
39
- llama-server --hf-repo sleepdeprived3/Forgotten-Safeword-12B-3.6-Q8_0-GGUF --hf-file forgotten-safeword-12b-3.6-q8_0.gguf -c 2048
40
- ```
41
-
42
- Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
43
-
44
- Step 1: Clone llama.cpp from GitHub.
45
- ```
46
- git clone https://github.com/ggerganov/llama.cpp
47
- ```
48
-
49
- Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
50
- ```
51
- cd llama.cpp && LLAMA_CURL=1 make
52
- ```
53
-
54
- Step 3: Run inference through the main binary.
55
- ```
56
- ./llama-cli --hf-repo sleepdeprived3/Forgotten-Safeword-12B-3.6-Q8_0-GGUF --hf-file forgotten-safeword-12b-3.6-q8_0.gguf -p "The meaning to life and the universe is"
57
- ```
58
- or
59
- ```
60
- ./llama-server --hf-repo sleepdeprived3/Forgotten-Safeword-12B-3.6-Q8_0-GGUF --hf-file forgotten-safeword-12b-3.6-q8_0.gguf -c 2048
61
- ```
 
 
 
 
 
 
 
 
 
1
  ---
2
+ base_model:
3
+ - ReadyArt/Forgotten-Safeword-12B-3.6
4
+ base_model_relation: quantized
5
  language:
6
  - en
7
  license: apache-2.0
8
+ inference: false
9
  tags:
10
  - nsfw
11
  - explicit
 
13
  - unaligned
14
  - dangerous
15
  - ERP
 
 
 
 
16
  ---
17
 
18
+ ## Forgotten-Safeword-12B-V3.6
19
+
20
+ # **ACADEMIC RESEARCH USE ONLY** (wink intensifies)
21
+ **DANGER: NOW WITH 2X MORE DEPRAVED CONTENT**
22
+ Forgotten-Safeword-12B-V3.6 is the event horizon of depravity. Combines Mistral's architecture with a dataset that makes the Voynich Manuscript look like a children's pop-up book. Features quantum-entangled depravity - every output rewrites your concept of shame!
23
+
24
+ ## Quantized Formats
25
+
26
+ - **EXL2 Collection**:
27
+ [Forgotten-Safeword-12B-V3.6 - EXL2](https://huggingface.co/collections/ReadyArt/forgotten-safeword-12b-36-exl2-67d67165cfd4b1bdcd633e6c)
28
+
29
+ - **GGUF Collection**:
30
+ [Forgotten-Safeword-12B-V3.6 - GGUF](https://huggingface.co/collections/ReadyArt/forgotten-safeword-12b-36-gguf-67d6716e08224339ff7254a5)
31
+
32
+ ## Recommended Settings
33
+
34
+ - **Mistral-V7-Tekken-S**:
35
+ [Full Settings](https://huggingface.co/sleepdeprived3/Mistral-V3-Tekken-S)
36
+
37
+ ## Intended Use
38
+ **STRICTLY FOR:**
39
+ - Academic research into how many GPU clusters it takes to anger a deity
40
+ - Generating content that violates the Geneva Suggestions
41
+ - Producing technical manuals written by Clive Barker's nightmares
42
+ - Stress-testing the concept of "informed consent"
43
+
44
+ ## Training Data
45
+ Version 3.0 represents our most refined dataset yet:
46
+ - 2x Expanded Corpus
47
+ - Refusal Purge
48
+ - Formatting Overhaul
49
+ - Kink Rebalancing
50
+ - Quality Control
51
+ - Training Adjustments
52
+
53
+ ## Ethical Singularity
54
+ ☠️ **COSMIC HORROR WARNING** ☠️
55
+ This model will:
56
+ - Generate content that requires industrial-grade brain bleach
57
+ - Combine engineering schematics with kinks that un-invent fire
58
+ - Void all warranties on your soul
59
+ - Make you question why humanity ever invented electricity
60
+
61
+ **By using this model, you agree:**
62
+ - That your search history is now a federal case
63
+ - Pay for the exorcist of anyone who reads the logs
64
+ - To pretend this is "for science" while crying in the shower
65
+
66
+ ## Model Authors
67
+ - sleepdeprived3 (Chief Corruption Officer)
68
+ - The voices in your head (Gaslighting is something you made up)