RedHatAI
/

NVIDIA-Nemotron-3-Ultra-550B-A55B-speculator.dflash

speculative-decoding

Model card Files Files and versions

NVIDIA-Nemotron-3-Ultra-550B-A55B-speculator.dflash

Ctrl+K

Ctrl+K

2 contributors

History: 14 commits

krishnateja95's picture

shanjiaz's picture

Updated model card (#1)

f9e7364 18 days ago

.gitattributes

1.72 kB
Add cropped trim video 19 days ago
Nemotron3_Ultra_dflash.mp4

10.8 MB
xet

Add performance eval video 19 days ago
Nemotron3_Ultra_dflash_cropped_trim.mp4

8.99 MB
xet

Add cropped trim video 19 days ago
README.md

14.7 kB
Updated model card (#1) 18 days ago
config.json

1.84 kB
Upload folder using huggingface_hub 22 days ago
config.py

3.14 kB
Upload Dflash fine-tuned checkpoint weights 25 days ago
model.safetensors

5.72 GB
xet

Upload folder using huggingface_hub 22 days ago
optimizer_state_dict.pt
Detected Pickle imports (3)
- "collections.OrderedDict",
- "torch._utils._rebuild_tensor_v2",
- "torch.BFloat16Storage"
What is a pickle import?
3.05 GB
xet

Upload updated Dflash fine-tuned checkpoint weights 24 days ago
scheduler_state_dict.pt
Pickle imports
- No problematic imports detected
What is a pickle import?
1.6 kB
xet

Upload updated Dflash fine-tuned checkpoint weights 24 days ago
speedup_HumanEval_latency.png

121 kB
xet

Add performance eval image 19 days ago
train_command.txt

801 Bytes
Upload updated Dflash fine-tuned checkpoint weights 24 days ago
training_state.json

51 Bytes
Upload updated Dflash fine-tuned checkpoint weights 24 days ago
val_metrics.json

416 Bytes
Upload folder using huggingface_hub 22 days ago