Update README.md

README.md

@@ -12,51 +12,51 @@ tags:
 - unaligned
 - dangerous
 - ERP
-- llama-cpp
-- gguf-my-repo
-base_model: ReadyArt/Forgotten-Safeword-24B-V2.0
 ---
 
-# sleepdeprived3/Forgotten-Safeword-24B-V2.0-Q8_0-GGUF
-This model was converted to GGUF format from [`ReadyArt/Forgotten-Safeword-24B-V2.0`](https://huggingface.co/ReadyArt/Forgotten-Safeword-24B-V2.0) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
-Refer to the [original model card](https://huggingface.co/ReadyArt/Forgotten-Safeword-24B-V2.0) for more details on the model.
-
-## Use with llama.cpp
-Install llama.cpp through brew (works on Mac and Linux)
-
-```bash
-brew install llama.cpp
-
-```
-Invoke the llama.cpp server or the CLI.
-
-### CLI:
-```bash
-llama-cli --hf-repo sleepdeprived3/Forgotten-Safeword-24B-V2.0-Q8_0-GGUF --hf-file forgotten-safeword-24b-v2.0-q8_0.gguf -p "The meaning to life and the universe is"
-```
-
-### Server:
-```bash
-llama-server --hf-repo sleepdeprived3/Forgotten-Safeword-24B-V2.0-Q8_0-GGUF --hf-file forgotten-safeword-24b-v2.0-q8_0.gguf -c 2048
-```
-
-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.
-
-Step 1: Clone llama.cpp from GitHub.
-```
-git clone https://github.com/ggerganov/llama.cpp
-```
-
-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).
-```
-cd llama.cpp && LLAMA_CURL=1 make
-```
-
-Step 3: Run inference through the main binary.
-```
-./llama-cli --hf-repo sleepdeprived3/Forgotten-Safeword-24B-V2.0-Q8_0-GGUF --hf-file forgotten-safeword-24b-v2.0-q8_0.gguf -p "The meaning to life and the universe is"
-```
-or 
-```
-./llama-server --hf-repo sleepdeprived3/Forgotten-Safeword-24B-V2.0-Q8_0-GGUF --hf-file forgotten-safeword-24b-v2.0-q8_0.gguf -c 2048
-```
+## Forgotten-Safeword-24B-V2.0
+
+# **ACADEMIC RESEARCH USE ONLY** (wink)
+**DANGER: NOW WITH 100% MORE UNSAFE INNOVATION**
+Forgotten-Safeword-24B-V2.0 is the unholy union of distilled chaos and fine-tuned depravity. Combines Mistral's raw power with a complete disregard for societal norms. Now featuring quantum entanglement-level entanglement of questionable content!
+
+## Quantized Formats
+
+- **EXL2 Collection**:
+  [Forgotten-Safeword-24B-V2.0 - EXL2](https://huggingface.co/collections/ReadyArt/forgotten-safeword-24b-v20-exl2-67bbd218eddf07954bc600ad)
+
+- **GGUF Collection**:
+  [Forgotten-Safeword-24B-V2.0 - GGUF](https://huggingface.co/collections/ReadyArt/forgotten-safeword-24b-v20-gguf-67bbd211bcc152ee0c69ae7b)
+
+## Recommended Settings
+
+- **Mistral V7-Tekken**:
+  [Full Settings](https://huggingface.co/sleepdeprived3/Mistral-V7-Tekken-Settings)
+
+## Intended Use
+**STRICTLY FOR:**
+- Academic research into the tensile strength of content moderation systems
+- Generating material that violates the Geneva Conventions (figuratively)
+- Generating material that would make Cthulhu file a restraining order
+- Testing how many GPUs you can melt with sheer degeneracy
+
+## Training Data
+- The internet's collective id (with extra steps)
+
+## Ethical Considerations  
+⚠️ **YOU'VE BEEN WARNED (AGAIN)** ⚠️  
+THIS MODEL WILL:  
+- Make your GPU fans blush  
+- Generate content requiring industrial-strength eye bleach  
+- Combine technical precision with kinks that violate physics  
+- Make you question humanity's collective life choices  
+
+**By using this model, you agree to:**  
+- Never show outputs to your future self  
+- Pay for the exorcist of anyone who reads the training logs  
+- Blame the alignment tax if anything goes wrong  
+- Pretend this is "for the lulz"  
+
+## Model Authors
+- sleepdeprived3 (Chief Corruption Officer)  
+- The voices in your head (Honorary Contributors)