Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
OPEA
/
DeepSeek-V2-Lite-int4-sym-inc
like
1
Follow
Open Platform for Enterprise AI
64
Safetensors
NeelNanda/pile-10k
deepseek_v2
custom_code
4-bit precision
auto-round
arxiv:
2309.05516
Model card
Files
Files and versions
xet
Community
main
DeepSeek-V2-Lite-int4-sym-inc
Ctrl+K
Ctrl+K
2 contributors
History:
9 commits
cicdatopea
Update config.json
1e3da39
verified
10 days ago
.gitattributes
Safe
1.52 kB
initial commit
5 months ago
README.md
Safe
8.69 kB
Update README.md
about 2 months ago
config.json
2.2 kB
Update config.json
10 days ago
configuration_deepseek.py
Safe
10.3 kB
add gptq format
5 months ago
generation_config.json
Safe
181 Bytes
add gptq format
5 months ago
model-00001-of-00002.safetensors
Safe
5 GB
xet
add gptq format
5 months ago
model-00002-of-00002.safetensors
Safe
4.14 GB
xet
add gptq format
5 months ago
model.safetensors.index.json
Safe
2.33 MB
add gptq format
5 months ago
modeling_deepseek.py
Safe
78.7 kB
add gptq format
5 months ago
quantization_config.json
Safe
1.21 kB
Update quantization_config.json
16 days ago
special_tokens_map.json
Safe
482 Bytes
add gptq format
5 months ago
tokenization_deepseek_fast.py
1.37 kB
add gptq format
5 months ago
tokenizer.json
Safe
7.5 MB
add gptq format
5 months ago
tokenizer_config.json
Safe
1.34 kB
add gptq format
5 months ago
