README.md
| 1 | --- |
| 2 | base_model: fdtn-ai/antares-1b |
| 3 | language: |
| 4 | - en |
| 5 | library_name: transformers |
| 6 | license: apache-2.0 |
| 7 | pipeline_tag: text-generation |
| 8 | tags: |
| 9 | - security |
| 10 | - vulnerability-detection |
| 11 | - agentic |
| 12 | - terminal-agent |
| 13 | - reinforcement-learning |
| 14 | - granite |
| 15 | - llama-cpp |
| 16 | - gguf-my-repo |
| 17 | gated: true |
| 18 | extra_gated_prompt: 'Please complete the form below to request access to this model. |
| 19 | All requests are reviewed manually. |
| 20 | |
| 21 | By submitting this form, you confirm that the information provided is accurate, agree |
| 22 | to share your contact details with the repository authors. You will be subject |
| 23 | to their communications and Privacy Statement: https://www.cisco.com/c/en/us/about/legal/privacy-full.html |
| 24 | |
| 25 | ' |
| 26 | extra_gated_fields: |
| 27 | First name: text |
| 28 | Last name: text |
| 29 | Email address: text |
| 30 | Country: country |
| 31 | Affiliation: text |
| 32 | Occupation: text |
| 33 | I have read, understood, and agree to the Terms and Conditions above: checkbox |
| 34 | --- |
| 35 | |
| 36 | # mitkox/antares-1b-Q8_0-GGUF |
| 37 | This model was converted to GGUF format from [`fdtn-ai/antares-1b`](https://huggingface.co/fdtn-ai/antares-1b) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. |
| 38 | Refer to the [original model card](https://huggingface.co/fdtn-ai/antares-1b) for more details on the model. |
| 39 | |
| 40 | ## Use with llama.cpp |
| 41 | Install llama.cpp through brew (works on Mac and Linux) |
| 42 | |
| 43 | ```bash |
| 44 | brew install llama.cpp |
| 45 | |
| 46 | ``` |
| 47 | Invoke the llama.cpp server or the CLI. |
| 48 | |
| 49 | ### CLI: |
| 50 | ```bash |
| 51 | llama-cli --hf-repo mitkox/antares-1b-Q8_0-GGUF --hf-file antares-1b-q8_0.gguf -p "The meaning to life and the universe is" |
| 52 | ``` |
| 53 | |
| 54 | ### Server: |
| 55 | ```bash |
| 56 | llama-server --hf-repo mitkox/antares-1b-Q8_0-GGUF --hf-file antares-1b-q8_0.gguf -c 2048 |
| 57 | ``` |
| 58 | |
| 59 | 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. |
| 60 | |
| 61 | Step 1: Clone llama.cpp from GitHub. |
| 62 | ``` |
| 63 | git clone https://github.com/ggerganov/llama.cpp |
| 64 | ``` |
| 65 | |
| 66 | 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). |
| 67 | ``` |
| 68 | cd llama.cpp && LLAMA_CURL=1 make |
| 69 | ``` |
| 70 | |
| 71 | Step 3: Run inference through the main binary. |
| 72 | ``` |
| 73 | ./llama-cli --hf-repo mitkox/antares-1b-Q8_0-GGUF --hf-file antares-1b-q8_0.gguf -p "The meaning to life and the universe is" |
| 74 | ``` |
| 75 | or |
| 76 | ``` |
| 77 | ./llama-server --hf-repo mitkox/antares-1b-Q8_0-GGUF --hf-file antares-1b-q8_0.gguf -c 2048 |
| 78 | ``` |
| 79 | |