|
|
--- |
|
|
license: mit |
|
|
language: |
|
|
- en |
|
|
base_model: ReadyArt/Omega-Darkest_The-Broken-Tutu-GLM-32B |
|
|
base_model_relation: finetune |
|
|
pipeline_tag: text-generation |
|
|
tags: |
|
|
- nsfw |
|
|
- explicit |
|
|
- roleplay |
|
|
- unaligned |
|
|
- ERP |
|
|
- Erotic |
|
|
- Horror |
|
|
- Violence |
|
|
- llama-cpp |
|
|
- gguf-my-repo |
|
|
--- |
|
|
|
|
|
# Triangle104/Omega-Darkest_The-Broken-Tutu-GLM-32B-Q6_K-GGUF |
|
|
This model was converted to GGUF format from [`ReadyArt/Omega-Darkest_The-Broken-Tutu-GLM-32B`](https://huggingface.co/ReadyArt/Omega-Darkest_The-Broken-Tutu-GLM-32B) 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/Omega-Darkest_The-Broken-Tutu-GLM-32B) for more details on the model. |
|
|
|
|
|
--- |
|
|
Turn away now. Nobody is dark enough to actually want this. |
|
|
|
|
|
- 🧬 Expanded 25M Token Dataset: Made with 687 erotic, horror and violence novels and 8,742 scenarios |
|
|
- 🧟 Enhanced Gore Protocols: Vivid anatomical descriptions with medical precision |
|
|
- 💎 Balanced Depravity: Retains Forgotten-Safeword's ERP edge while taking violence to the next level |
|
|
- 📜 Enhanced Character Piloting: Characters exhibit more nuanced personalities and motivations in extreme scenarios |
|
|
- ⚰️ Mortality Awareness: Characters react realistically to pain, mutilation and death |
|
|
|
|
|
--- |
|
|
## 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 Triangle104/Omega-Darkest_The-Broken-Tutu-GLM-32B-Q6_K-GGUF --hf-file omega-darkest_the-broken-tutu-glm-32b-q6_k.gguf -p "The meaning to life and the universe is" |
|
|
``` |
|
|
|
|
|
### Server: |
|
|
```bash |
|
|
llama-server --hf-repo Triangle104/Omega-Darkest_The-Broken-Tutu-GLM-32B-Q6_K-GGUF --hf-file omega-darkest_the-broken-tutu-glm-32b-q6_k.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 Triangle104/Omega-Darkest_The-Broken-Tutu-GLM-32B-Q6_K-GGUF --hf-file omega-darkest_the-broken-tutu-glm-32b-q6_k.gguf -p "The meaning to life and the universe is" |
|
|
``` |
|
|
or |
|
|
``` |
|
|
./llama-server --hf-repo Triangle104/Omega-Darkest_The-Broken-Tutu-GLM-32B-Q6_K-GGUF --hf-file omega-darkest_the-broken-tutu-glm-32b-q6_k.gguf -c 2048 |
|
|
``` |
|
|
|
