SomeoneSomething
/

VibeVoice7b-low-vram-4bit

4-bit precision

Model card Files Files and versions

VibeVoice7b-low-vram-4bit

6.63 GB

1 contributor

History: 2 commits

SomeoneSomething's picture

SomeoneSomething

Upload folder using huggingface_hub

72ca110 verified 6 months ago

.gitattributes
1.58 kB

Upload folder using huggingface_hub 6 months ago
QUANTIZATION_README.md
2.92 kB

Upload folder using huggingface_hub 6 months ago
README.md
969 Bytes

Upload folder using huggingface_hub 6 months ago
config.json
3.31 kB

Upload folder using huggingface_hub 6 months ago
generation_config.json
69 Bytes

Upload folder using huggingface_hub 6 months ago
load_quantized_4bit.py
1.83 kB

Upload folder using huggingface_hub 6 months ago
minimal_memory_output.wav
314 kB
xet

Upload folder using huggingface_hub 6 months ago
model-00001-of-00002.safetensors
4.95 GB
xet

Upload folder using huggingface_hub 6 months ago
model-00002-of-00002.safetensors
1.68 GB
xet

Upload folder using huggingface_hub 6 months ago
model.safetensors.index.json
341 kB

Upload folder using huggingface_hub 6 months ago
preprocessor_config.json
294 Bytes

Upload folder using huggingface_hub 6 months ago
quantization_config.json
560 Bytes

Upload folder using huggingface_hub 6 months ago
quantize_and_save_vibevoice.py
11.1 kB

Upload folder using huggingface_hub 6 months ago
test_accurate_vram.py
6.91 kB

Upload folder using huggingface_hub 6 months ago
use_quantized_model.py
2.15 kB

Upload folder using huggingface_hub 6 months ago
vibevoice_7gb_target.py
6.31 kB

Upload folder using huggingface_hub 6 months ago