157 GB

Ctrl+K

1 contributor

History: 69 commits

infosave

Upload mmh3-raven-streaming-q4tp.cmf with huggingface_hub

5be0529 verified about 14 hours ago

clipproj
the vision-row ClipProj twin fitted for the v2 build, so the container can be rebuilt about 17 hours ago
images
Upload images/upscaler_lanczos_1024.png with huggingface_hub about 16 hours ago
samples
the ported latent upscaler: 512x288 render decoded at 1024x576 about 16 hours ago
.gitattributes

3.93 kB
Upload mmh3-raven-streaming-q4tp.cmf with huggingface_hub about 14 hours ago
README.md

40.6 kB
0.5.94: the q8_2f build runs on the card — 357.3 s to 171.5 s about 16 hours ago
mmh3-raven-streaming-q4tp.cmf

16 GB
xet

Upload mmh3-raven-streaming-q4tp.cmf with huggingface_hub about 14 hours ago
mmh3-turbo-clipproj4b-fl2va-q4tp.cmf

14.5 GB
xet

clipproj + fl2va in one 14.5 GB file: the 4B tower and the VAE encoder join the compact build; first-frame conditioning verified frame-for-frame 5 days ago
mmh3-turbo-clipproj4b-fl2va-v2-q4tp.cmf

14.5 GB
xet

clipproj4b-fl2va v2: split projection — vision rows through a vision-fitted map, faces hold 5 days ago
mmh3-turbo-clipproj4b-fl2va-v2-q4tp.cmf.sha256

106 Bytes
clipproj4b-fl2va v2: split projection — vision rows through a vision-fitted map, faces hold 5 days ago
mmh3-turbo-clipproj4b-fl2va-v2-q8_2f.cmf

26.9 GB
xet

the two-field eight-bit build: q8_2f, 26.90 GB, cortiq verify clean about 16 hours ago
mmh3-turbo-clipproj4b-fl2va-v2-q8_2f.cmf.sha256

118 Bytes
Upload mmh3-turbo-clipproj4b-fl2va-v2-q8_2f.cmf.sha256 with huggingface_hub about 16 hours ago
mmh3-turbo-clipproj4b-q4tp.cmf

14.1 GB
xet

ClipProj 4B prompt encoder: 25.20 GB -> 14.13 GB, everything still q4tp 7 days ago
mmh3-turbo-fl2va-q2tp.cmf

20.1 GB
xet

Upload mmh3-turbo-fl2va-q2tp.cmf with huggingface_hub 13 days ago
mmh3-turbo-fl2va-q4tp.cmf

25.7 GB
xet

Upload mmh3-turbo-fl2va-q4tp.cmf with huggingface_hub 13 days ago
mmh3-turbo-q4tp.cmf

25.2 GB
xet

Upload mmh3-turbo-q4tp.cmf with huggingface_hub 13 days ago