nm-testing
/

DeepSeek-Coder-V2-Lite-Instruct-W8A8

8-bit precision

compressed-tensors

Model card Files Files and versions

DeepSeek-Coder-V2-Lite-Instruct-W8A8

16.2 GB

Ctrl+K

Ctrl+K

2 contributors

History: 3 commits

mgoin's picture

Updated compression_config to quantization_config

e1baf6d verified over 1 year ago

.gitattributes

1.52 kB
initial commit almost 2 years ago
config.json

2.78 kB
Updated compression_config to quantization_config over 1 year ago
configuration_deepseek.py

10.3 kB
Upload folder using huggingface_hub almost 2 years ago
generation_config.json

181 Bytes
Upload folder using huggingface_hub almost 2 years ago
model-00001-of-00004.safetensors

5 GB
xet

Upload folder using huggingface_hub almost 2 years ago
model-00002-of-00004.safetensors

5 GB
xet

Upload folder using huggingface_hub almost 2 years ago
model-00003-of-00004.safetensors

5 GB
xet

Upload folder using huggingface_hub almost 2 years ago
model-00004-of-00004.safetensors

1.15 GB
xet

Upload folder using huggingface_hub almost 2 years ago
model.safetensors.index.json

971 kB
Upload folder using huggingface_hub almost 2 years ago
modeling_deepseek.py

78.7 kB
Upload folder using huggingface_hub almost 2 years ago
recipe.yaml

167 Bytes
Upload folder using huggingface_hub almost 2 years ago
special_tokens_map.json

482 Bytes
Upload folder using huggingface_hub almost 2 years ago
tokenization_deepseek_fast.py

1.37 kB
Upload folder using huggingface_hub almost 2 years ago
tokenizer.json

4.61 MB
Upload folder using huggingface_hub almost 2 years ago
tokenizer_config.json

4.36 kB
Upload folder using huggingface_hub almost 2 years ago