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
40
Safetensors
NeelNanda/pile-10k
deepseek_v2
custom_code
4-bit precision
intel/auto-round
arxiv:
2309.05516
Model card
Files
Files and versions
Community
90bb8ef
DeepSeek-V2-Lite-int4-sym-inc
2 contributors
History:
2 commits
wenhuach
add gptq format
90bb8ef
3 months ago
.gitattributes
1.52 kB
initial commit
3 months ago
config.json
2.96 kB
add gptq format
3 months ago
configuration_deepseek.py
10.3 kB
add gptq format
3 months ago
generation_config.json
181 Bytes
add gptq format
3 months ago
model-00001-of-00002.safetensors
5 GB
LFS
add gptq format
3 months ago
model-00002-of-00002.safetensors
4.14 GB
LFS
add gptq format
3 months ago
model.safetensors.index.json
2.33 MB
add gptq format
3 months ago
modeling_deepseek.py
78.7 kB
add gptq format
3 months ago
quantize_config.json
1.24 kB
add gptq format
3 months ago
special_tokens_map.json
482 Bytes
add gptq format
3 months ago
tokenization_deepseek_fast.py
1.37 kB
add gptq format
3 months ago
tokenizer.json
7.5 MB
add gptq format
3 months ago
tokenizer_config.json
1.34 kB
add gptq format
3 months ago
