Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,50 @@
+---
+tags:
+- llama-cpp
+- gguf-my-repo
+base_model: sanchit-gandhi/Mistral-3B-Instruct-v0.2
+---
+
+# SansarK/Mistral-3B-Instruct-v0.2-Q2_K-GGUF
+This model was converted to GGUF format from [`sanchit-gandhi/Mistral-3B-Instruct-v0.2`](https://huggingface.co/sanchit-gandhi/Mistral-3B-Instruct-v0.2) 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/sanchit-gandhi/Mistral-3B-Instruct-v0.2) 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 --hf-repo SansarK/Mistral-3B-Instruct-v0.2-Q2_K-GGUF --hf-file mistral-3b-instruct-v0.2-q2_k.gguf -p "The meaning to life and the universe is"
+```
+
+### Server:
+```bash
+llama-server --hf-repo SansarK/Mistral-3B-Instruct-v0.2-Q2_K-GGUF --hf-file mistral-3b-instruct-v0.2-q2_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.
+
+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 SansarK/Mistral-3B-Instruct-v0.2-Q2_K-GGUF --hf-file mistral-3b-instruct-v0.2-q2_k.gguf -p "The meaning to life and the universe is"
+```
+or 
+```
+./server --hf-repo SansarK/Mistral-3B-Instruct-v0.2-Q2_K-GGUF --hf-file mistral-3b-instruct-v0.2-q2_k.gguf -c 2048
+```