Hugging Face
Models
Datasets
Spaces
Buckets
new
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
Compactbot
/
testr-100k
Like
0
Text Generation
Safetensors
English
tiny
tiny-lm
tiny-model
slm
small-language-model
sub-1m
from-scratch
character-level
char-gpt
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
4
Copy to bucket
new
main
testr-100k
438 kB
Ctrl+K
Ctrl+K
1 contributor
History:
9 commits
Compactbot
Fix config params to the true unique count (100,936). 106,568 is the file sum that double-counts the tied head; the README explains this.
b3bc31f
verified
4 days ago
.gitattributes
Safe
1.52 kB
initial commit
4 days ago
README.md
Safe
4.45 kB
Correct the card: the model is now trained on the 19.2 MB TinyStories validation set (the actual #17 request). Fixes param count (100,936 unique; the earlier 106,568 double-counted the tied head) and reports the honest memorization result (ratio 1.02x, verified reproducible).
4 days ago
config.json
Safe
374 Bytes
Fix config params to the true unique count (100,936). 106,568 is the file sum that double-counts the tied head; the README explains this.
4 days ago
model.safetensors
Safe
431 kB
xet
Ship the correct Testr-100K model (trained on the 19.2 MB TinyStories validation set, as requested in #17). Replaces the wrong-data weights (191 MB web text). 100,936 unique params; memorized PPL 3.1540 vs never-seen 3.2203 (ratio 1.02x) — verified reproducible from this file.
4 days ago
vocab.json
Safe
1.32 kB
Add char vocabulary (128 chars + unk) (#3)
4 days ago