Instructions to use nvidia/Nemotron-4-340B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use nvidia/Nemotron-4-340B-Base with NeMo:
# tag did not correspond to a valid NeMo domain.
- Notebooks
- Google Colab
- Kaggle
Nemotron-4-340B-Base / model_weights /model.decoder.layers.mlp.linear_fc2._extra_state /shard_20_96.pt
Download model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_20_96.pt from nvidia/Nemotron-4-340B-Base: direct link, hf CLI and curl.
- Browser
- Download file 1.84 kB
-
https://huggingface.co/nvidia/Nemotron-4-340B-Base/resolve/main/model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_20_96.pt
- Command line
-
hf download hf://nvidia/Nemotron-4-340B-Base/model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_20_96.pt
-
curl -L -o shard_20_96.pt https://huggingface.co/nvidia/Nemotron-4-340B-Base/resolve/main/model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_20_96.pt
1.84 kB
- Xet hash:
- cefffb2e5e840d857654909a039c7642e853ff2690f15c5437c76a1c359cbf0a
- Size of remote file:
- 1.84 kB
- SHA256:
- 1805133c804db005b1f4a478e07588a88f548880e2fc453f83e7644f8c0f2db8
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.