Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
reaperdoesntknow
/
MoA-100M
like
0
Text Generation
Transformers
PyTorch
nvidia/Nemotron-Math-HumanReasoning
WeMake/Intelligent-Content-Understanding
English
moa_metric
mixture-of-attentions
distance-attention
metric-attention
mqa
hyperffn
router-gating
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
7a75b28
MoA-100M
/
generation_config.json
reaperdoesntknow
Upload MoAMetricLM
377cc15
verified
2 months ago
raw
Copy download link
history
blame
Safe
136 Bytes
{
"_from_model_config"
:
true
,
"bos_token_id"
:
101
,
"eos_token_id"
:
102
,
"pad_token_id"
:
0
,
"transformers_version"
:
"4.56.1"
}