chankhavu/Nemotron-Cascade-2-30B-A3B-NVFP4 at main

Nemotron-Cascade-2-30B-A3B-NVFP4

19.4 GB

Ctrl+K

Ctrl+K

1 contributor

History: 9 commits

chankhavu's picture

Update README.md

80ee3cc verified 14 days ago

.gitattributes

1.57 kB
Raw NVFP4 export from ModelOpt (before fixes) 16 days ago
README.md

5.02 kB
Update README.md 14 days ago
chat_template.jinja

10.9 kB
Raw NVFP4 export from ModelOpt (before fixes) 16 days ago
config.json

1.82 kB
Removed time_step_limit with invalid value "Infinity" 14 days ago
configuration_nemotron_h.py

12.9 kB
Raw NVFP4 export from ModelOpt (before fixes) 16 days ago
generation_config.json

150 Bytes
Raw NVFP4 export from ModelOpt (before fixes) 16 days ago
hf_quant_config.json

3.05 kB
Fix hf_quant_config.json and config.json for SGLang/vLLM compatibility 16 days ago
model-00001-of-00004.safetensors

5 GB
xet

Raw NVFP4 export from ModelOpt (before fixes) 16 days ago
model-00002-of-00004.safetensors

5 GB
xet

Raw NVFP4 export from ModelOpt (before fixes) 16 days ago
model-00003-of-00004.safetensors

5 GB
xet

Raw NVFP4 export from ModelOpt (before fixes) 16 days ago
model-00004-of-00004.safetensors

4.34 GB
xet

Raw NVFP4 export from ModelOpt (before fixes) 16 days ago
model.safetensors.index.json

2.4 MB
Raw NVFP4 export from ModelOpt (before fixes) 16 days ago
modeling_nemotron_h.py

83.2 kB
Raw NVFP4 export from ModelOpt (before fixes) 16 days ago
special_tokens_map.json

563 Bytes
Raw NVFP4 export from ModelOpt (before fixes) 16 days ago
tokenizer.json

17.1 MB
xet

Raw NVFP4 export from ModelOpt (before fixes) 16 days ago
tokenizer_config.json

177 kB
Raw NVFP4 export from ModelOpt (before fixes) 16 days ago