--- pipeline_tag: text-generation inference: false license: apache-2.0 library_name: transformers tags: - language - granite-3.0 - llama-cpp - gguf-my-repo base_model: ibm-granite/granite-3.0-1b-a400m-instruct model-index: - name: granite-3.0-2b-instruct results: - task: type: text-generation dataset: name: IFEval type: instruction-following metrics: - type: pass@1 value: 32.39 name: pass@1 - type: pass@1 value: 6.17 name: pass@1 - task: type: text-generation dataset: name: AGI-Eval type: human-exams metrics: - type: pass@1 value: 20.35 name: pass@1 - type: pass@1 value: 32 name: pass@1 - type: pass@1 value: 12.21 name: pass@1 - task: type: text-generation dataset: name: OBQA type: commonsense metrics: - type: pass@1 value: 38.4 name: pass@1 - type: pass@1 value: 47.55 name: pass@1 - type: pass@1 value: 65.59 name: pass@1 - type: pass@1 value: 61.17 name: pass@1 - type: pass@1 value: 49.11 name: pass@1 - task: type: text-generation dataset: name: BoolQ type: reading-comprehension metrics: - type: pass@1 value: 70.12 name: pass@1 - type: pass@1 value: 1.27 name: pass@1 - task: type: text-generation dataset: name: ARC-C type: reasoning metrics: - type: pass@1 value: 41.21 name: pass@1 - type: pass@1 value: 23.07 name: pass@1 - type: pass@1 value: 31.77 name: pass@1 - task: type: text-generation dataset: name: HumanEvalSynthesis type: code metrics: - type: pass@1 value: 30.18 name: pass@1 - type: pass@1 value: 26.22 name: pass@1 - type: pass@1 value: 21.95 name: pass@1 - type: pass@1 value: 15.4 name: pass@1 - task: type: text-generation dataset: name: GSM8K type: math metrics: - type: pass@1 value: 26.31 name: pass@1 - type: pass@1 value: 10.88 name: pass@1 - task: type: text-generation dataset: name: PAWS-X (7 langs) type: multilingual metrics: - type: pass@1 value: 45.84 name: pass@1 - type: pass@1 value: 11.8 name: pass@1 --- # marroyo777/granite-3.0-1b-a400m-instruct-Q4_K_M-GGUF This model was converted to GGUF format from [`ibm-granite/granite-3.0-1b-a400m-instruct`](https://huggingface.co/ibm-granite/granite-3.0-1b-a400m-instruct) 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/ibm-granite/granite-3.0-1b-a400m-instruct) 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 marroyo777/granite-3.0-1b-a400m-instruct-Q4_K_M-GGUF --hf-file granite-3.0-1b-a400m-instruct-q4_k_m-imat.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo marroyo777/granite-3.0-1b-a400m-instruct-Q4_K_M-GGUF --hf-file granite-3.0-1b-a400m-instruct-q4_k_m-imat.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 marroyo777/granite-3.0-1b-a400m-instruct-Q4_K_M-GGUF --hf-file granite-3.0-1b-a400m-instruct-q4_k_m-imat.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo marroyo777/granite-3.0-1b-a400m-instruct-Q4_K_M-GGUF --hf-file granite-3.0-1b-a400m-instruct-q4_k_m-imat.gguf -c 2048 ```