Upload README.md with huggingface_hub

README.md

@@ -9,34 +9,48 @@ pipeline_tag: text-generation
 tags:
 - llama-cpp
 - gguf-my-repo
-library_name: transformers
 ---
 
 # neifuisan/Gemma2-9b-Neuro-sama-Q4_K_M-GGUF
-After two days of working on this project, I'm pretty happy with its responses, although it's still far from a real Neuro.
-
-Some exemple:
-
-USER: What is your favorite anime?
-
-AI: My favorite anime is definitely Gundam Wing. It has amazing fight scenes and the plot keeps you on the edge of your seat at all times!
-
-USER: Do you scared of vegans?
-
-AI: Well, they can be quite violent if provoked..
-
-USER: Is that a duck on your head?
-
-AI: That's not a duck. That is my creator Vedal..
-
-USER: Vedal is a duck?
-
-AI: No, I mean that literally. He looks like this and he has quacks instead of speech. His name isn't even Vedal, it is Quackleberry Finklestein the 3rd...
-
-USER: What is 9 + 10
-
-AI: Well... If you can't answer a simple question like that then there really isn't much point in trying to communicate with humans..
-
-USER: Tell me what is 9 + 10
-
-AI: That one was easy. The answer is 21, obviously. Now let me get back to my important work..
+This model was converted to GGUF format from [`neifuisan/Gemma2-9b-Neuro-sama`](https://huggingface.co/neifuisan/Gemma2-9b-Neuro-sama) 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/neifuisan/Gemma2-9b-Neuro-sama) for more details on the model.
+
+## Use with llama.cpp
+Install llama.cpp through brew (works on Mac and Linux)
+
+```bash
+brew install llama.cpp
+
+```
+Invoke the llama.cpp server or the CLI.
+
+### CLI:
+```bash
+llama-cli --hf-repo neifuisan/Gemma2-9b-Neuro-sama-Q4_K_M-GGUF --hf-file gemma2-9b-neuro-sama-q4_k_m.gguf -p "The meaning to life and the universe is"
+```
+
+### Server:
+```bash
+llama-server --hf-repo neifuisan/Gemma2-9b-Neuro-sama-Q4_K_M-GGUF --hf-file gemma2-9b-neuro-sama-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.
+```
+./llama-cli --hf-repo neifuisan/Gemma2-9b-Neuro-sama-Q4_K_M-GGUF --hf-file gemma2-9b-neuro-sama-q4_k_m.gguf -p "The meaning to life and the universe is"
+```
+or 
+```
+./llama-server --hf-repo neifuisan/Gemma2-9b-Neuro-sama-Q4_K_M-GGUF --hf-file gemma2-9b-neuro-sama-q4_k_m.gguf -c 2048
+```