Hugging Face's logo

cstr
/
lfm2-colbert-GGUF

GGUF
colbert
retrieval
multi-vector
late-interaction
crispembed
ggml
Model card Files
xet
 Community
lfm2-colbert-GGUF

Commit History

importance matrix (calibration)
00c4b3a
verified

cstr commited on

A/B summary (cos vs gold)
0767213
verified

cstr commited on

iq4_xs +imatrix (cos_vs_full-precision=0.9971)
cea442e
verified

cstr commited on

q4_k +imatrix (cos_vs_full-precision=0.9975)
45109ae
verified

cstr commited on

Upload lfm2-colbert-ref.gguf with huggingface_hub
8c2c22e
verified

cstr commited on

Upload README.md with huggingface_hub
8e5b812
verified

cstr commited on

Update README with all quant parity results
f4da337
verified

cstr commited on

Add Q4_K quantization
34756eb
verified

cstr commited on

Add Q5_K quantization
5663ca7
verified

cstr commited on

Upload README.md with huggingface_hub
c3bdee8
verified

cstr commited on

Add F32 reference
2b71d96
verified

cstr commited on

Add Q8_0 quantization
d8bd11b
verified

cstr commited on

Add model card
fb9c4b3
verified

cstr commited on

initial commit
8712c31
verified

cstr commited on