Upload README.md with huggingface_hub

README.md

@@ -4,33 +4,52 @@ tags:
 - generated_from_trainer
 - llama-cpp
 - gguf-my-repo
-base_model: yanolja/EEVE-Korean-10.8B-v1.0
+base_model: yanolja/EEVE-Korean-Instruct-10.8B-v1.0
 model-index:
 - name: yanolja/EEVE-Korean-Instruct-10.8B-v1.0
   results: []
 ---
 
 # AIRider/EEVE-Korean-Instruct-10.8B-v1.0-Q4_K_M-GGUF
-This model was converted to GGUF format from [`yanolja/EEVE-Korean-Instruct-10.8B-v1.0`](https://huggingface.co/yanolja/EEVE-Korean-Instruct-10.8B-v1.0) using llama.cpp 
+This model was converted to GGUF format from [`yanolja/EEVE-Korean-Instruct-10.8B-v1.0`](https://huggingface.co/yanolja/EEVE-Korean-Instruct-10.8B-v1.0) 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/yanolja/EEVE-Korean-Instruct-10.8B-v1.0) for more details on the model.
 
 ## Use with llama.cpp
-Install llama.cpp through brew.
+Install llama.cpp through brew (works on Mac and Linux)
+
 ```bash
-brew install ggerganov/ggerganov/llama.cpp
+brew install llama.cpp
+
 ```
 Invoke the llama.cpp server or the CLI.
-CLI:
+
+### CLI:
 ```bash
-llama-cli --hf-repo AIRider/EEVE-Korean-Instruct-10.8B-v1.0-Q4_K_M-GGUF --model eeve-korean-instruct-10.8b-v1.0-q4_k_m.gguf -p "The meaning to life and the universe is"
+llama --hf-repo AIRider/EEVE-Korean-Instruct-10.8B-v1.0-Q4_K_M-GGUF --hf-file eeve-korean-instruct-10.8b-v1.0-q4_k_m.gguf -p "The meaning to life and the universe is"
 ```
-Server:
+
+### Server:
 ```bash
-llama-server --hf-repo AIRider/EEVE-Korean-Instruct-10.8B-v1.0-Q4_K_M-GGUF --model eeve-korean-instruct-10.8b-v1.0-q4_k_m.gguf -c 2048
+llama-server --hf-repo AIRider/EEVE-Korean-Instruct-10.8B-v1.0-Q4_K_M-GGUF --hf-file eeve-korean-instruct-10.8b-v1.0-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.
+
+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.
+```
+./main --hf-repo AIRider/EEVE-Korean-Instruct-10.8B-v1.0-Q4_K_M-GGUF --hf-file eeve-korean-instruct-10.8b-v1.0-q4_k_m.gguf -p "The meaning to life and the universe is"
+```
+or 
 ```
-git clone https://github.com/ggerganov/llama.cpp && \
-cd llama.cpp && \
-make && \
-./main -m eeve-korean-instruct-10.8b-v1.0-q4_k_m.gguf -n 128
+./server --hf-repo AIRider/EEVE-Korean-Instruct-10.8B-v1.0-Q4_K_M-GGUF --hf-file eeve-korean-instruct-10.8b-v1.0-q4_k_m.gguf -c 2048
 ```