Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,39 @@
+---
+tags:
+- moe
+- frankenmoe
+- merge
+- mergekit
+- fhnw/Llama-3-8B-pineapple-pizza-orpo
+- fhnw/Llama-3-8B-pineapple-recipe-sft
+- llama-cpp
+- gguf-my-repo
+base_model:
+- fhnw/Llama-3-8B-pineapple-pizza-orpo
+- fhnw/Llama-3-8B-pineapple-recipe-sft
+---
+
+# andreasmartin/Llama-3-pineapple-2x8B-Q4_K_M-GGUF
+This model was converted to GGUF format from [`fhnw/Llama-3-pineapple-2x8B`](https://huggingface.co/fhnw/Llama-3-pineapple-2x8B) 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/fhnw/Llama-3-pineapple-2x8B) 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 andreasmartin/Llama-3-pineapple-2x8B-Q4_K_M-GGUF --model llama-3-pineapple-2x8b-q4_k_m.gguf -p "The meaning to life and the universe is"
+```
+Server:
+```bash
+llama-server --hf-repo andreasmartin/Llama-3-pineapple-2x8B-Q4_K_M-GGUF --model llama-3-pineapple-2x8b-q4_k_m.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-pineapple-2x8b-q4_k_m.gguf -n 128
+```