Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,54 @@
+---
+tags:
+- pytorch
+- trl
+- sft
+- llama-cpp
+- gguf-my-repo
+base_model: lllyasviel/omost-llama-3-8b
+inference: false
+---
+
+# zhaijunxiao/omost-llama-3-8b-Q8_0-GGUF
+This model was converted to GGUF format from [`lllyasviel/omost-llama-3-8b`](https://huggingface.co/lllyasviel/omost-llama-3-8b) 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/lllyasviel/omost-llama-3-8b) 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 zhaijunxiao/omost-llama-3-8b-Q8_0-GGUF --hf-file omost-llama-3-8b-q8_0.gguf -p "The meaning to life and the universe is"
+```
+
+### Server:
+```bash
+llama-server --hf-repo zhaijunxiao/omost-llama-3-8b-Q8_0-GGUF --hf-file omost-llama-3-8b-q8_0.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 zhaijunxiao/omost-llama-3-8b-Q8_0-GGUF --hf-file omost-llama-3-8b-q8_0.gguf -p "The meaning to life and the universe is"
+```
+or 
+```
+./server --hf-repo zhaijunxiao/omost-llama-3-8b-Q8_0-GGUF --hf-file omost-llama-3-8b-q8_0.gguf -c 2048
+```