|
--- |
|
license: other |
|
tags: |
|
- llama-cpp |
|
- gguf-my-repo |
|
base_model: TheDrummer/Cydonia-24B-v2 |
|
--- |
|
|
|
# Triangle104/Cydonia-24B-v2-Q3_K_L-GGUF |
|
This model was converted to GGUF format from [`TheDrummer/Cydonia-24B-v2`](https://huggingface.co./TheDrummer/Cydonia-24B-v2) 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./TheDrummer/Cydonia-24B-v2) for more details on the model. |
|
|
|
--- |
|
Cydonia 24B v2 is a finetune of Mistral's latest 'Small' model (2501). |
|
|
|
|
|
Aliases: "Cydonia 24B", "Cydonia v2", "Cydonia on that broken base" |
|
|
|
|
|
|
|
|
|
did a RP up to 21k context on v2. no rep pen no dry. its good! |
|
|
|
|
|
|
|
|
|
|
|
|
|
v2 is fucking violent man |
|
|
|
|
|
|
|
|
|
|
|
|
|
It holds details, anatomy, happening, scenes much better |
|
|
|
|
|
|
|
|
|
|
|
|
|
Also, tested v2 vocabulary. Christ... it would make (redacted) blush. |
|
|
|
|
|
|
|
|
|
|
|
|
|
Tested up to 24K context length, it was stable all throughout. |
|
|
|
--- |
|
## 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/Cydonia-24B-v2-Q3_K_L-GGUF --hf-file cydonia-24b-v2-q3_k_l.gguf -p "The meaning to life and the universe is" |
|
``` |
|
|
|
### Server: |
|
```bash |
|
llama-server --hf-repo Triangle104/Cydonia-24B-v2-Q3_K_L-GGUF --hf-file cydonia-24b-v2-q3_k_l.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/Cydonia-24B-v2-Q3_K_L-GGUF --hf-file cydonia-24b-v2-q3_k_l.gguf -p "The meaning to life and the universe is" |
|
``` |
|
or |
|
``` |
|
./llama-server --hf-repo Triangle104/Cydonia-24B-v2-Q3_K_L-GGUF --hf-file cydonia-24b-v2-q3_k_l.gguf -c 2048 |
|
``` |
|
|
