12.3 GB

Ctrl+K

1 contributor

History: 3 commits

Azaz666

Upload PyTorch-INT8 quantized model

ed8a34c verified 26 days ago

.gitattributes

1.57 kB
Upload PyTorch quantized model (pure PyTorch, no custom CUDA kernels) about 2 months ago
README.md

1.01 kB
Upload PyTorch-INT8 quantized model 26 days ago
chat_template.jinja

2.51 kB
Upload PyTorch quantized model (pure PyTorch, no custom CUDA kernels) about 2 months ago
config.json

5.86 kB
Upload PyTorch-INT8 quantized model 26 days ago
configuration_aimv2.py

2.47 kB
Upload PyTorch quantized model (pure PyTorch, no custom CUDA kernels) about 2 months ago
configuration_ovis.py

8.29 kB
Upload PyTorch quantized model (pure PyTorch, no custom CUDA kernels) about 2 months ago
generation_config.json

276 Bytes
Upload PyTorch-INT8 quantized model 26 days ago
int8_layers.json

10.7 kB
Upload PyTorch-INT8 quantized model 26 days ago
model.safetensors

6.15 GB
xet

Upload PyTorch quantized model (pure PyTorch, no custom CUDA kernels) about 2 months ago
modeling_aimv2.py

6.74 kB
Upload PyTorch quantized model (pure PyTorch, no custom CUDA kernels) about 2 months ago
modeling_int8.py

9.56 kB
Upload PyTorch-INT8 quantized model 26 days ago
quant_config.json

33 kB
Upload PyTorch quantized model (pure PyTorch, no custom CUDA kernels) about 2 months ago
quant_meta.json

199 Bytes
Upload PyTorch-INT8 quantized model 26 days ago
state_dict.pt
Detected Pickle imports (5)
- "torch.HalfStorage",
- "collections.OrderedDict",
- "torch.BFloat16Storage",
- "torch.CharStorage",
- "torch._utils._rebuild_tensor_v2"
What is a pickle import?
6.15 GB
xet

Upload PyTorch-INT8 quantized model 26 days ago
tokenizer.json

11.4 MB
xet

Upload PyTorch quantized model (pure PyTorch, no custom CUDA kernels) about 2 months ago
tokenizer_config.json

665 Bytes
Upload PyTorch quantized model (pure PyTorch, no custom CUDA kernels) about 2 months ago

Detected Pickle imports (5)