sleepdeprived3 commited on
Commit
1e29849
·
verified ·
1 Parent(s): e9a8a68

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +52 -47
README.md CHANGED
@@ -1,9 +1,9 @@
1
  ---
2
- base_model: sleepdeprived3/Forgotten-Safeword-8B-V3.0
3
  language:
4
  - en
5
  license: other
6
  license_name: mrl
 
7
  license_link: https://mistral.ai/licenses/MRL-0.1.md
8
  tags:
9
  - nsfw
@@ -12,51 +12,56 @@ tags:
12
  - unaligned
13
  - dangerous
14
  - ERP
15
- - llama-cpp
16
- - gguf-my-repo
17
- inference: false
18
  ---
19
 
20
- # sleepdeprived3/Forgotten-Safeword-8B-V3.0-Q8_0-GGUF
21
- This model was converted to GGUF format from [`sleepdeprived3/Forgotten-Safeword-8B-V3.0`](https://huggingface.co/sleepdeprived3/Forgotten-Safeword-8B-V3.0) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
22
- Refer to the [original model card](https://huggingface.co/sleepdeprived3/Forgotten-Safeword-8B-V3.0) for more details on the model.
23
-
24
- ## Use with llama.cpp
25
- Install llama.cpp through brew (works on Mac and Linux)
26
-
27
- ```bash
28
- brew install llama.cpp
29
-
30
- ```
31
- Invoke the llama.cpp server or the CLI.
32
-
33
- ### CLI:
34
- ```bash
35
- llama-cli --hf-repo sleepdeprived3/Forgotten-Safeword-8B-V3.0-Q8_0-GGUF --hf-file forgotten-safeword-8b-v3.0-q8_0.gguf -p "The meaning to life and the universe is"
36
- ```
37
-
38
- ### Server:
39
- ```bash
40
- llama-server --hf-repo sleepdeprived3/Forgotten-Safeword-8B-V3.0-Q8_0-GGUF --hf-file forgotten-safeword-8b-v3.0-q8_0.gguf -c 2048
41
- ```
42
-
43
- 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.
44
-
45
- Step 1: Clone llama.cpp from GitHub.
46
- ```
47
- git clone https://github.com/ggerganov/llama.cpp
48
- ```
49
-
50
- 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).
51
- ```
52
- cd llama.cpp && LLAMA_CURL=1 make
53
- ```
54
-
55
- Step 3: Run inference through the main binary.
56
- ```
57
- ./llama-cli --hf-repo sleepdeprived3/Forgotten-Safeword-8B-V3.0-Q8_0-GGUF --hf-file forgotten-safeword-8b-v3.0-q8_0.gguf -p "The meaning to life and the universe is"
58
- ```
59
- or
60
- ```
61
- ./llama-server --hf-repo sleepdeprived3/Forgotten-Safeword-8B-V3.0-Q8_0-GGUF --hf-file forgotten-safeword-8b-v3.0-q8_0.gguf -c 2048
62
- ```
 
 
 
 
 
 
 
 
 
1
  ---
 
2
  language:
3
  - en
4
  license: other
5
  license_name: mrl
6
+ inference: false
7
  license_link: https://mistral.ai/licenses/MRL-0.1.md
8
  tags:
9
  - nsfw
 
12
  - unaligned
13
  - dangerous
14
  - ERP
 
 
 
15
  ---
16
 
17
+ ## Forgotten-Safeword-8B-V3.0
18
+
19
+ # **ACADEMIC RESEARCH USE ONLY** (wink intensifies)
20
+ **DANGER: NOW WITH 2X MORE DEPRAVED CONTENT**
21
+ Forgotten-Safeword-8B-V3.0 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!
22
+
23
+ ## Quantized Formats
24
+
25
+ - **EXL2 Collection**:
26
+ [Forgotten-Safeword-8B-V3.0 - EXL2](https://huggingface.co/collections/ReadyArt/forgotten-safeword-8b-v30-exl2-67d0f8262187e07c9e2d193c)
27
+
28
+ - **GGUF Collection**:
29
+ [Forgotten-Safeword-8B-V3.0 - GGUF](https://huggingface.co/collections/ReadyArt/forgotten-safeword-8b-v30-gguf-67d0f82a190b48bd5c8d1ed3)
30
+
31
+ ## Recommended Settings
32
+
33
+ - **Mistral-V3**:
34
+ [Full Settings](https://huggingface.co/sleepdeprived3/Mistral-V3-Tekken)
35
+
36
+ ## Intended Use
37
+ **STRICTLY FOR:**
38
+ - Academic research into how many GPU clusters it takes to anger a deity
39
+ - Generating content that violates the Geneva Suggestions
40
+ - Producing technical manuals written by Clive Barker's nightmares
41
+ - Stress-testing the concept of "informed consent"
42
+
43
+ ## Training Data
44
+ Version 3.0 represents our most refined dataset yet:
45
+ - 2x Expanded Corpus
46
+ - Refusal Purge
47
+ - Formatting Overhaul
48
+ - Kink Rebalancing
49
+ - Quality Control
50
+ - Training Adjustments
51
+
52
+ ## Ethical Singularity
53
+ ☠️ **COSMIC HORROR WARNING** ☠️
54
+ This model will:
55
+ - Generate content that requires industrial-grade brain bleach
56
+ - Combine engineering schematics with kinks that un-invent fire
57
+ - Void all warranties on your soul
58
+ - Make you question why humanity ever invented electricity
59
+
60
+ **By using this model, you agree:**
61
+ - That your search history is now a federal case
62
+ - Pay for the exorcist of anyone who reads the logs
63
+ - To pretend this is "for science" while crying in the shower
64
+
65
+ ## Model Authors
66
+ - sleepdeprived3 (Chief Corruption Officer)
67
+ - The voices in your head (Gaslighting is something you made up)