| tags: | |
| - gguf | |
| - modernbert | |
| - colbert | |
| - reasoning | |
| - late-interaction | |
| license: apache-2.0 | |
| base_model: ctrltokyo/OpenReason-ModernColBERT | |
| # OpenReason-ModernColBERT GGUF | |
| GGUF conversion of [ctrltokyo/OpenReason-ModernColBERT](https://huggingface.co/ctrltokyo/OpenReason-ModernColBERT) for use with [litembeddings](https://github.com/alexandernicholson/litembeddings). | |
| ## Files | |
| | File | Size | Description | | |
| |------|------|-------------| | |
| | openreason-moderncolbert-Q8_0.gguf | 153M | Q8_0 quantized ModernBERT encoder | | |
| | openreason-moderncolbert-Q8_0.projection | 385K | ColBERT 768 to 128 linear projection | | |
| ## Usage with litembeddings | |
| ## Source Model | |
| - Architecture: ModernBERT (150M params) | |
| - Training: Fine-tuned on BRIGHT benchmark reasoning tasks | |
| - Base: lightonai/GTE-ModernColBERT-v1 | |
| - License: Apache 2.0 | |