66.1 GB

Ctrl+K

6 contributors

History: 29 commits

DanialMT

cuichenx

Switch vision encoder reference from C-RADIOv2-H to C-RADIOv4-H; remove now-redundant _patch_cpe_align_corners (#10)

24e67ea 29 days ago

media
Add media dir about 1 month ago
.gitattributes

1.78 kB
Add media dir about 1 month ago
README.md

48 kB
Remove vLLM NVFP4 tp>1 caveat (#11) about 1 month ago
__init__.py

0 Bytes
Upload folder using huggingface_hub about 2 months ago
audio_model.py

6.89 kB
Upload folder using huggingface_hub about 2 months ago
bias.md

2.7 kB
Add model card about 1 month ago
chat_template.jinja

14.3 kB
Update chat template about 2 months ago
config.json

9.84 kB
Switch vision encoder reference from C-RADIOv2-H to C-RADIOv4-H; remove now-redundant _patch_cpe_align_corners (#10) 29 days ago
configuration.py

4.87 kB
Support Transformers 5.6, dynamic-resolution images, temporal video embedder, vLLM parity (#2) about 1 month ago
configuration_nemotron_h.py

14 kB
Support Transformers 5.6, dynamic-resolution images, temporal video embedder, vLLM parity (#2) about 1 month ago
configuration_radio.py

8.98 kB
Switch vision encoder reference from C-RADIOv2-H to C-RADIOv4-H; remove now-redundant _patch_cpe_align_corners (#10) 29 days ago
evs.py

2.92 kB
Upload folder using huggingface_hub about 2 months ago
explainability.md

4.79 kB
Add model card about 1 month ago
generation_config.json

309 Bytes
Update generation_config with default sampling params about 2 months ago
image_processing.py

10.9 kB
Support Transformers 5.6, dynamic-resolution images, temporal video embedder, vLLM parity (#2) about 1 month ago
model-00001-of-00017.safetensors

4 GB
xet

Upload folder using huggingface_hub about 2 months ago
model-00002-of-00017.safetensors

4 GB
xet

Upload folder using huggingface_hub about 2 months ago
model-00003-of-00017.safetensors

3.99 GB
xet

Upload folder using huggingface_hub about 2 months ago
model-00004-of-00017.safetensors

4 GB
xet

Upload folder using huggingface_hub about 2 months ago
model-00005-of-00017.safetensors

3.99 GB
xet

Upload folder using huggingface_hub about 2 months ago
model-00006-of-00017.safetensors

4 GB
xet

Upload folder using huggingface_hub about 2 months ago
model-00007-of-00017.safetensors

3.99 GB
xet

Upload folder using huggingface_hub about 2 months ago
model-00008-of-00017.safetensors

4 GB
xet

Upload folder using huggingface_hub about 2 months ago
model-00009-of-00017.safetensors

3.99 GB
xet

Upload folder using huggingface_hub about 2 months ago
model-00010-of-00017.safetensors

4 GB
xet

Upload folder using huggingface_hub about 2 months ago
model-00011-of-00017.safetensors

3.98 GB
xet

Upload folder using huggingface_hub about 2 months ago
model-00012-of-00017.safetensors

3.99 GB
xet

Upload folder using huggingface_hub about 2 months ago
model-00013-of-00017.safetensors

3.97 GB
xet

Upload folder using huggingface_hub about 2 months ago
model-00014-of-00017.safetensors

3.99 GB
xet

Upload folder using huggingface_hub about 2 months ago
model-00015-of-00017.safetensors

4 GB
xet

Upload folder using huggingface_hub about 2 months ago
model-00016-of-00017.safetensors

4 GB
xet

Upload folder using huggingface_hub about 2 months ago
model-00017-of-00017.safetensors

2.12 GB
xet

Upload folder using huggingface_hub about 2 months ago
model.safetensors.index.json

819 kB
Upload folder using huggingface_hub about 2 months ago
modeling.py

28.7 kB
Switch vision encoder reference from C-RADIOv2-H to C-RADIOv4-H; remove now-redundant _patch_cpe_align_corners (#10) 29 days ago
modeling_nemotron_h.py

64.3 kB
Switch vision encoder reference from C-RADIOv2-H to C-RADIOv4-H; remove now-redundant _patch_cpe_align_corners (#10) 29 days ago
preprocessor_config.json

594 Bytes
Support Transformers 5.6, dynamic-resolution images, temporal video embedder, vLLM parity (#2) about 1 month ago
privacy.md

845 Bytes
Add model card about 1 month ago
processing.py

26.3 kB
Enable batched audio inference (#3) about 1 month ago
processing_utils.py

3.02 kB
Upload folder using huggingface_hub about 2 months ago
safety.md

2.78 kB
Add model card about 1 month ago
special_tokens_map.json

420 Bytes
Upload folder using huggingface_hub about 2 months ago
tokenizer.json

17.1 MB
xet

Upload folder using huggingface_hub about 2 months ago
tokenizer_config.json

188 kB
Enable batched audio inference (#3) about 1 month ago
video_io.py

6.52 kB
Support Transformers 5.6, dynamic-resolution images, temporal video embedder, vLLM parity (#2) about 1 month ago
video_processing.py

6.53 kB
Rename classes to NemotronH_Nano_Omni_Reasoning_V3 for vLLM compatibility about 2 months ago