|
--- |
|
license: apache-2.0 |
|
tags: |
|
- liminerity/merge6 |
|
- liminerity/merge3 |
|
- Merge |
|
- llama-cpp |
|
- gguf-my-repo |
|
--- |
|
|
|
# bunnycore/Phigments12-Q6_K-GGUF |
|
|
|
Phigments12-Q6_K-GGUF is a quantized version of the liminerity/Phigments12: https://huggingface.co/liminerity/Phigments12 model. Phigments12-Q6_K-GGUF packs 2.78 billion parameters, making it a compact model that delivers high performance and decent benchmark results. This efficiency allows you to run the model on low-end laptops, phones, and even PCs without a dedicated GPU. |
|
|
|
Several platforms support running Phigments12-Q6_K-GGUF, including: |
|
|
|
``` |
|
Jan.ai |
|
LM Studio |
|
Text Generation Web UI |
|
|
|
``` |
|
|
|
|
|
## Use with llama.cpp |
|
|
|
Install llama.cpp through brew. |
|
|
|
```bash |
|
brew install ggerganov/ggerganov/llama.cpp |
|
``` |
|
Invoke the llama.cpp server or the CLI. |
|
|
|
CLI: |
|
|
|
```bash |
|
llama-cli --hf-repo bunnycore/Phigments12-Q6_K-GGUF --model phigments12.Q6_K.gguf -p "The meaning to life and the universe is" |
|
``` |
|
|
|
Server: |
|
|
|
```bash |
|
llama-server --hf-repo bunnycore/Phigments12-Q6_K-GGUF --model phigments12.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. |
|
|
|
``` |
|
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m phigments12.Q6_K.gguf -n 128 |
|
``` |
|
|
|
This model was converted to GGUF format from [`liminerity/Phigments12`](https://huggingface.co/liminerity/Phigments12) 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/liminerity/Phigments12) for more details on the model. |
