PrunaAI
/

distributed-optimized-gpt2-2b-HQQ-8bit-smashed

Model card Files Files and versions

distributed-optimized-gpt2-2b-HQQ-8bit-smashed

Ctrl+K

Ctrl+K

1 contributor

History: 3 commits

sharpenb's picture

cbd11fe0cbb4c4db5015be772986dcbdc32e08a5e25692529ae29b0f9c2fecbc

0b0642a verified 3 months ago

.gitattributes

1.52 kB

initial commit 3 months ago
README.md

5.47 kB

cbd11fe0cbb4c4db5015be772986dcbdc32e08a5e25692529ae29b0f9c2fecbc 3 months ago
config.json

10.2 kB

cbd11fe0cbb4c4db5015be772986dcbdc32e08a5e25692529ae29b0f9c2fecbc 3 months ago
configuration_gpt_optimized.py

710 Bytes

cbd11fe0cbb4c4db5015be772986dcbdc32e08a5e25692529ae29b0f9c2fecbc 3 months ago
qmodel.pt
Detected Pickle imports (7)
- "collections.OrderedDict",
- "torch.uint8",
- "torch._utils._rebuild_parameter",
- "torch.FloatStorage",
- "torch.ByteStorage",
- "torch.Size",
- "torch._utils._rebuild_tensor_v2"
How to fix it?
2.54 GB
xet

bbc68cc29db92df1aa3543575329e684227f22a6bc4d3ff508012ceef560eb25 3 months ago
smash_config.json

1.08 kB

cbd11fe0cbb4c4db5015be772986dcbdc32e08a5e25692529ae29b0f9c2fecbc 3 months ago