Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
nvidia
/
Phi-4-multimodal-instruct-FP8
like
4
Follow
NVIDIA
50.2k
Safetensors
Model Optimizer
phi4mm
nvidia
ModelOpt
Phi4
quantized
FP8
fp8
custom_code
modelopt
License:
nvidia-open-model-license
Model card
Files
Files and versions
xet
Community
main
Phi-4-multimodal-instruct-FP8
/
speech-lora
942 MB
2 contributors
History:
1 commit
chenjiel
Initial commit
d822efc
5 months ago
adapter_config.json
465 Bytes
Initial commit
5 months ago
adapter_model.safetensors
923 MB
xet
Initial commit
5 months ago
added_tokens.json
249 Bytes
Initial commit
5 months ago
special_tokens_map.json
473 Bytes
Initial commit
5 months ago
tokenizer.json
15.5 MB
xet
Initial commit
5 months ago
tokenizer_config.json
3.25 kB
Initial commit
5 months ago
vocab.json
3.91 MB
Initial commit
5 months ago