language: | |
- nl | |
license: other | |
tags: | |
- ORPO | |
- llama 3 8B | |
- conversational | |
- llama-cpp | |
- gguf-my-repo | |
base_model: meta-llama/Meta-Llama-3-8B | |
datasets: | |
- BramVanroy/ultra_feedback_dutch | |
pipeline_tag: text-generation | |
model-index: | |
- name: ReBatch/Llama-3-8B-dutch | |
results: [] | |
# NikolayKozloff/Llama-3-8B-dutch-Q8_0-GGUF | |
This model was converted to GGUF format from [`ReBatch/Llama-3-8B-dutch`](https://huggingface.co/ReBatch/Llama-3-8B-dutch) 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/ReBatch/Llama-3-8B-dutch) for more details on the model. | |
## 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 NikolayKozloff/Llama-3-8B-dutch-Q8_0-GGUF --model llama-3-8b-dutch.Q8_0.gguf -p "The meaning to life and the universe is" | |
``` | |
Server: | |
```bash | |
llama-server --hf-repo NikolayKozloff/Llama-3-8B-dutch-Q8_0-GGUF --model llama-3-8b-dutch.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. | |
``` | |
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m llama-3-8b-dutch.Q8_0.gguf -n 128 | |
``` | |