Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
nm-testing
/
DeepSeek-Coder-V2-Lite-Instruct-W8A8
like
0
Follow
NM Testing
32
Safetensors
deepseek_v2
custom_code
8-bit precision
compressed-tensors
Model card
Files
Files and versions
Community
main
DeepSeek-Coder-V2-Lite-Instruct-W8A8
2 contributors
History:
3 commits
mgoin
Updated compression_config to quantization_config
e1baf6d
verified
about 2 months ago
.gitattributes
Safe
1.52 kB
initial commit
2 months ago
config.json
Safe
2.78 kB
Updated compression_config to quantization_config
about 2 months ago
configuration_deepseek.py
Safe
10.3 kB
Upload folder using huggingface_hub
2 months ago
generation_config.json
Safe
181 Bytes
Upload folder using huggingface_hub
2 months ago
model-00001-of-00004.safetensors
Safe
5 GB
LFS
Upload folder using huggingface_hub
2 months ago
model-00002-of-00004.safetensors
Safe
5 GB
LFS
Upload folder using huggingface_hub
2 months ago
model-00003-of-00004.safetensors
Safe
5 GB
LFS
Upload folder using huggingface_hub
2 months ago
model-00004-of-00004.safetensors
Safe
1.15 GB
LFS
Upload folder using huggingface_hub
2 months ago
model.safetensors.index.json
Safe
971 kB
Upload folder using huggingface_hub
2 months ago
modeling_deepseek.py
Safe
78.7 kB
Upload folder using huggingface_hub
2 months ago
recipe.yaml
Safe
167 Bytes
Upload folder using huggingface_hub
2 months ago
special_tokens_map.json
Safe
482 Bytes
Upload folder using huggingface_hub
2 months ago
tokenization_deepseek_fast.py
Safe
1.37 kB
Upload folder using huggingface_hub
2 months ago
tokenizer.json
Safe
4.61 MB
Upload folder using huggingface_hub
2 months ago
tokenizer_config.json
Safe
4.36 kB
Upload folder using huggingface_hub
2 months ago
