brianmatzelle
/

personaplex-7b-v1-bnb-4bit

speech-to-speech

conversational-ai

4-bit precision

Model card Files Files and versions

personaplex-7b-v1-bnb-4bit

6.98 GB

Ctrl+K

Ctrl+K

1 contributor

History: 10 commits

brianmatzelle's picture

docs: update README — pre-quantized loading now works

bde1652 verified about 2 months ago

moshi
fix: add pre-quantized checkpoint loading with meta device init about 2 months ago
.gitattributes

1.52 kB
initial commit 2 months ago
README.md

3.57 kB
docs: update README — pre-quantized loading now works about 2 months ago
model_bnb_4bit.pt
Detected Pickle imports (5)
- "torch._utils._rebuild_tensor_v2",
- "torch.FloatStorage",
- "torch.ByteStorage",
- "torch.BFloat16Storage",
- "collections.OrderedDict"
What is a pickle import?
6.98 GB
xet

Upload model_bnb_4bit.pt with huggingface_hub 2 months ago