cstr
/

lfm2-colbert-GGUF

late-interaction

Model card Files Files and versions

lfm2-colbert-GGUF

2.05 GB

Ctrl+K

Ctrl+K

1 contributor

History: 15 commits

cstr's picture

docs: add provenance / EU AI Act Art. 53 note

bb43ef0 verified about 11 hours ago

.gitattributes

1.94 kB
importance matrix (calibration) about 1 month ago
README.md

5.07 kB
docs: add provenance / EU AI Act Art. 53 note about 11 hours ago
lfm2-colbert-f32.gguf

709 MB
xet

Add F32 reference about 1 month ago
lfm2-colbert-imatrix-ab.txt

468 Bytes
A/B summary (cos vs gold) about 1 month ago
lfm2-colbert-iq4_xs.gguf

225 MB
xet

iq4_xs +imatrix (cos_vs_full-precision=0.9971) about 1 month ago
lfm2-colbert-q4_k-imatrix.gguf

234 MB
xet

q4_k +imatrix (cos_vs_full-precision=0.9975) about 1 month ago
lfm2-colbert-q4_k.gguf

234 MB
xet

Add Q4_K quantization about 1 month ago
lfm2-colbert-q5_k.gguf

270 MB
xet

Add Q5_K quantization about 1 month ago
lfm2-colbert-q8_0.gguf

378 MB
xet

Add Q8_0 quantization about 1 month ago
lfm2-colbert-ref.gguf

32.6 kB
Upload lfm2-colbert-ref.gguf with huggingface_hub about 1 month ago
lfm2-colbert.imatrix

621 kB
xet

importance matrix (calibration) about 1 month ago