| language: | |
| - en | |
| license: apache-2.0 | |
| library_name: llama.cpp | |
| tags: | |
| - gguf | |
| - llama.cpp | |
| - multimodal | |
| - vision-language-model | |
| - smolvlm | |
| - cytology | |
| - medical-imaging | |
| pipeline_tag: image-text-to-text | |
| base_model: | |
| - HuggingFaceTB/SmolVLM-500M-Instruct | |
| # SmolVLM Cytology GGUF | |
| Fine-tuned SmolVLM multimodal model for cytology image analysis. | |
| ## Files | |
| - SmolVLM-Cytology-Q4_K_M.gguf | |
| - mmproj-SmolVLM-Cytology-f16.gguf | |
| ## Usage | |
| ```bash | |
| llama-mtmd-cli \ | |
| -m SmolVLM-Cytology-Q4_K_M.gguf \ | |
| --mmproj mmproj-SmolVLM-Cytology-f16.gguf \ | |
| --image test.png \ | |
| -p "<image> Describe this image" | |
| ``` | |
| ## Notes | |
| - Quantized using llama.cpp | |
| - Compatible with llama-mtmd-cli | |
| - Vision encoder exported separately as mmproj GGUF | |