CompressingVLM
/

qwen2-vl-7b-smoothquant-w8a8

Model card Files Files and versions

qwen2-vl-7b-smoothquant-w8a8

8.88 GB

Ctrl+K

Ctrl+K

1 contributor

History: 2 commits

AlaBoussoffara's picture

Upload W8A8 SmoothQuant artifacts

292e894 verified 4 months ago

processor
Upload W8A8 SmoothQuant artifacts 4 months ago
.gitattributes

1.63 kB
Upload W8A8 SmoothQuant artifacts 4 months ago
README.txt

398 Bytes
Upload W8A8 SmoothQuant artifacts 4 months ago
benchmark_loader_manifest.json

717 Bytes
Upload W8A8 SmoothQuant artifacts 4 months ago
calibration_act_channel_stats.pt
Detected Pickle imports (3)
- "torch.FloatStorage",
- "torch._utils._rebuild_tensor_v2",
- "collections.OrderedDict"
What is a pickle import?
5.84 MB
xet

Upload W8A8 SmoothQuant artifacts 4 months ago
chat_template.jinja

1.02 kB
Upload W8A8 SmoothQuant artifacts 4 months ago
config.json

2.22 kB
Upload W8A8 SmoothQuant artifacts 4 months ago
generation_config.json

243 Bytes
Upload W8A8 SmoothQuant artifacts 4 months ago
processor_config.json

1.47 kB
Upload W8A8 SmoothQuant artifacts 4 months ago
tokenizer.json

11.4 MB
xet

Upload W8A8 SmoothQuant artifacts 4 months ago
tokenizer_config.json

779 Bytes
Upload W8A8 SmoothQuant artifacts 4 months ago
w8a8_smoothquant_meta.json

60.3 kB
Upload W8A8 SmoothQuant artifacts 4 months ago
w8a8_smoothquant_state.pt
Detected Pickle imports (5)
- "torch.FloatStorage",
- "torch.CharStorage",
- "collections.OrderedDict",
- "torch._utils._rebuild_tensor_v2",
- "torch.HalfStorage"
What is a pickle import?
8.85 GB
xet

Upload W8A8 SmoothQuant artifacts 4 months ago