| license: llama3.1 | |
| base_model: Nexesenex/Dolphin3.0-Llama3.1-1B-abliterated | |
| tags: | |
| - llama-cpp | |
| - gguf-my-repo | |
| # Nexesenex/Dolphin3.0-Llama3.1-1B-abliterated-GGUF | |
| IMPORTANT : These models are quantized with IK_Llama.cpp, not Llama.cpp | |
| This model was converted to GGUF format from [`Nexesenex/Dolphin3.0-Llama3.1-1B-abliterated`](https://huggingface.co/Nexesenex/Dolphin3.0-Llama3.1-1B-abliterated) using llama.cpp's fork IK Llama 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/Nexesenex/Dolphin3.0-Llama3.1-1B-abliterated) for more details on the model. | |
| ## Use with llama.cpp (I never tested that way with IK_Llama) | |
| Install llama.cpp through brew (works on Mac and Linux) | |
| 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. -> necessary to use Croco. | |
| Step 1: Clone llama.cpp from GitHub. -> necessary to use Croco. | |
| 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). | |
| Step 3: Run inference through the main binary. | |