language: | |
- ru | |
- en | |
license: llama3 | |
tags: | |
- merge | |
- mergekit | |
- lazymergekit | |
- IlyaGusev/saiga_llama3_8b | |
- lightblue/suzume-llama-3-8B-multilingual | |
- llama-cpp | |
- gguf-my-repo | |
base_model: | |
- IlyaGusev/saiga_llama3_8b | |
- lightblue/suzume-llama-3-8B-multilingual | |
pipeline_tag: text-generation | |
# RachidAR/Llama-3-8B-saiga-suzume-ties-Q6_K-GGUF | |
This model was converted to GGUF format from [`d0rj/Llama-3-8B-saiga-suzume-ties`](https://huggingface.co./d0rj/Llama-3-8B-saiga-suzume-ties) 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./d0rj/Llama-3-8B-saiga-suzume-ties) 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 RachidAR/Llama-3-8B-saiga-suzume-ties-Q6_K-GGUF --model llama-3-8b-saiga-suzume-ties.Q6_K.gguf -p "The meaning to life and the universe is" | |
``` | |
Server: | |
```bash | |
llama-server --hf-repo RachidAR/Llama-3-8B-saiga-suzume-ties-Q6_K-GGUF --model llama-3-8b-saiga-suzume-ties.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 llama-3-8b-saiga-suzume-ties.Q6_K.gguf -n 128 | |
``` | |