Hugging Face
Models
Datasets
Spaces
Buckets
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
AETHORIA-AI
/
TR-HASH-MoE-200M-130B
Like
4
Follow
AETHORIA AI
13
Text Generation
PyTorch
Safetensors
5 datasets
English
base-model
pretraining
tr-hash
mixture-of-experts
gqa
custom-code
License:
cc-by-nc-4.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
main
TR-HASH-MoE-200M-130B
826 MB
Ctrl+K
Ctrl+K
1 contributor
History:
12 commits
Pacific-i64
Restore canonical Base root to 32K vocabulary
c6bd0f2
verified
2 months ago
.gitattributes
Safe
1.57 kB
Add training loss curve
2 months ago
README.md
Safe
3.36 kB
Restore canonical Base root to 32K vocabulary
2 months ago
config.json
Safe
3.02 kB
Restore canonical Base root to 32K vocabulary
2 months ago
model.safetensors
Safe
814 MB
xet
Restore canonical Base root to 32K vocabulary
2 months ago
model_config.yaml
Safe
2.51 kB
Restore canonical Base root to 32K vocabulary
2 months ago
tokenizer.json
Safe
2.27 MB
Restore canonical Base root to 32K vocabulary
2 months ago
training_log.csv
Safe
9.79 MB
Publish final pretrain checkpoint (weights, config, tokenizer, training log)
2 months ago
training_loss.png
Safe
119 kB
xet
Add training loss curve
2 months ago
