cudabenchmarktest
/

personaplex-7b-nf4

Model card Files Files and versions

personaplex-7b-nf4

7.06 GB

Ctrl+K

Ctrl+K

1 contributor

History: 15 commits

cudabenchmarktest's picture

cudabenchmarktest

fix: Update open-agents link to npm (npmjs.com/package/open-agents-ai)

8246e98 verified 19 days ago

voices
Add OverBarn cloned voice 21 days ago
.gitattributes

1.52 kB
initial commit 21 days ago
README.md

3.04 kB
fix: Update open-agents link to npm (npmjs.com/package/open-agents-ai) 19 days ago
clone-voice.py

15.1 kB
Add clone-voice.py 21 days ago
config.json

533 Bytes
Add config.json — inference harness 20 days ago
dequant-loader.py

5.79 kB
Add dequant-loader.py — inference harness 20 days ago
linear2bit.py

18.9 kB
Add linear2bit.py — inference harness 20 days ago
model-nf4.safetensors

4.45 GB
xet

PersonaPlex 7B INT4 (NF4) quantized weights — 3.8x compression for edge/Jetson devices 21 days ago
model-turbo2bit.safetensors

2.22 GB
xet

Add TurboQuant 2-bit (NF2 + WHT) weights — 7.5x compression, 2.07 GB 21 days ago
quantize-weights.py

6.5 kB
Add quantize-weights.py 21 days ago
tokenizer-e351c8d8-checkpoint125.safetensors

385 MB
xet

Add tokenizer-e351c8d8-checkpoint125.safetensors (no HF_TOKEN needed for full setup) 21 days ago
tokenizer_spm_32k_3.model

553 kB
xet

Add tokenizer_spm_32k_3.model (no HF_TOKEN needed for full setup) 21 days ago