Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
codelion
/
dhara-250m-ar-base
like
1
Text Generation
Transformers
Safetensors
codelion/sutra-10B
allenai/dolma3_longmino_mix-50B-1025
English
dhara_ar
causal-lm
language-model
canon-layers
rope-yarn
custom_code
arxiv:
2407.20311
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
dhara-250m-ar-base
502 MB
Ctrl+K
Ctrl+K
1 contributor
History:
4 commits
codelion
Add average row to benchmarks, add datasets to YAML card
d876f75
verified
27 days ago
.gitattributes
Safe
1.52 kB
initial commit
27 days ago
README.md
Safe
10.4 kB
Add average row to benchmarks, add datasets to YAML card
27 days ago
config.json
Safe
891 Bytes
Initial upload: Dhara-250M-AR-Base with Canon layers and 32K context
27 days ago
configuration_dhara_ar.py
Safe
2.81 kB
Initial upload: Dhara-250M-AR-Base with Canon layers and 32K context
27 days ago
model.safetensors
Safe
498 MB
xet
Initial upload: Dhara-250M-AR-Base with Canon layers and 32K context
27 days ago
modeling_dhara_ar.py
Safe
23.8 kB
Initial upload: Dhara-250M-AR-Base with Canon layers and 32K context
27 days ago
tokenizer.json
Safe
3.51 MB
Initial upload: Dhara-250M-AR-Base with Canon layers and 32K context
27 days ago
tokenizer_config.json
Safe
269 Bytes
Initial upload: Dhara-250M-AR-Base with Canon layers and 32K context
27 days ago