Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
vltnmmdv
/
deepseek-moe-16b-base
like
0
Text Generation
Transformers
Safetensors
deepseek_with_concentration
custom_code
arxiv:
1910.09700
Model card
Files
Files and versions
Community
Train
Use this model
3cb0445
deepseek-moe-16b-base
/
generation_config.json
vltnmmdv
Upload DeepseekFixedForCausalLM
3cb0445
verified
8 months ago
raw
Copy download link
history
blame
121 Bytes
{
"_from_model_config"
:
true
,
"bos_token_id"
:
100000
,
"eos_token_id"
:
100001
,
"transformers_version"
:
"4.36.0"
}