Capicua25x/Ornith-1.0-9B-MXFP4-Vision-MTP at main

Ornith-1.0-9B-MXFP4-Vision-MTP

9.86 GB

Ctrl+K

1 contributor

History: 10 commits

Capicua25x

fix: correct total_parameters ~9.65B (was 1.47M, inherited upstream index bug) + total_size to actual MXFP4 shards

462d7df verified 3 months ago

.gitattributes

1.57 kB
MXFP4 trunk + grafted BF16 MTP head 3 months ago
README.md

5.86 kB
docs: quantized-from-Ornith (Option A) + gfx1201/radeon-ai-pro-r9700 tags (RDNA4 discoverability) 3 months ago
chat_template.jinja

7.59 kB
MXFP4 trunk + grafted BF16 MTP head 3 months ago
config.json

20.1 kB
MXFP4 trunk + grafted BF16 MTP head 3 months ago
generation_config.json

137 Bytes
MXFP4 trunk + grafted BF16 MTP head 3 months ago
model-00001-of-00004.safetensors

4.3 GB
xet

MXFP4 trunk + grafted BF16 MTP head 3 months ago
model-00002-of-00004.safetensors

1.58 GB
xet

MXFP4 trunk + grafted BF16 MTP head 3 months ago
model-00003-of-00004.safetensors

1.58 GB
xet

MXFP4 trunk + grafted BF16 MTP head 3 months ago
model-00004-of-00004.safetensors

1.89 GB
xet

MXFP4 trunk + grafted BF16 MTP head 3 months ago
model-mtp.safetensors

487 MB
xet

MXFP4 trunk + grafted BF16 MTP head 3 months ago
model.safetensors.index.json

94.4 kB
fix: correct total_parameters ~9.65B (was 1.47M, inherited upstream index bug) + total_size to actual MXFP4 shards 3 months ago
preprocessor_config.json

390 Bytes
MXFP4 trunk + grafted BF16 MTP head 3 months ago
processor_config.json

1.19 kB
MXFP4 trunk + grafted BF16 MTP head 3 months ago
quantize_mxfp4.py

5.12 kB
Add quantize_mxfp4.py (step-1 MXFP4 quant recipe) + link it in the card 3 months ago
recipe_graft_mxfp4.py

6.31 kB
graft recipe 3 months ago
tokenizer.json

20 MB
xet

MXFP4 trunk + grafted BF16 MTP head 3 months ago
tokenizer_config.json

1.17 kB
MXFP4 trunk + grafted BF16 MTP head 3 months ago
video_preprocessor_config.json

385 Bytes
MXFP4 trunk + grafted BF16 MTP head 3 months ago
vocab.json

6.72 MB
MXFP4 trunk + grafted BF16 MTP head 3 months ago