SamMikaelson
/

OLD_INT_8

uniform-quantization

model-compression

8-bit precision

Model card Files Files and versions

1 contributor

History: 3 commits

SamMikaelson's picture

Upload folder using huggingface_hub

f34ca0c verified about 2 months ago

.gitattributes

1.52 kB

initial commit 3 months ago
README.md

1.62 kB

Upload folder using huggingface_hub about 2 months ago
compression_stats.json

359 Bytes

Upload standalone random quantized model 3 months ago
config.json

3.28 kB

Upload standalone random quantized model 3 months ago
generation_config.json

111 Bytes

Upload standalone random quantized model 3 months ago
layer_analysis.json

133 kB

Upload folder using huggingface_hub about 2 months ago
layer_configs.json

215 kB

Upload standalone random quantized model 3 months ago
model.safetensors

3.52 GB
xet

Upload standalone random quantized model 3 months ago
quantization_info.json

514 kB

Upload standalone random quantized model 3 months ago
quantized_weights.pt
Detected Pickle imports (6)
- "torch.LongStorage",
- "torch.CharStorage",
- "collections.OrderedDict",
- "torch.BFloat16Storage",
- "torch._utils._rebuild_tensor_v2",
- "torch.FloatStorage"
What is a pickle import?
3.52 GB
xet

Upload folder using huggingface_hub about 2 months ago
special_tokens_map.json

549 Bytes

Upload standalone random quantized model 3 months ago
tokenizer.json

9.98 MB

Upload standalone random quantized model 3 months ago
tokenizer_config.json

166 kB

Upload standalone random quantized model 3 months ago