Downloads · 30 days
253
10% of all-time downloads
srlm-1m
Martico2432/srlm-1m
srlm-1m is a text generation model from Martico2432. Use it when you need the model to write or continue text. The card lists the license as mit.
A Small ROSA based Language Model, of 900k parameters.
All-time downloads
2.6K
Public
Parameters
904K
7.2 MB on disk
Likes
4
Public
Repo makeup
Click a slice to open those files.
.bin3.6 MB · 48%
At a glance
- Task
- Text Generation
- License
- mit
- Model type
- srlm
- Access
- Public
- Created
- Jul 4, 2026
- Updated
- Jul 4, 2026
- SHA
- 7b3bddf1
Try a prompt
Datasets
Model card
From the Hugging Face model README
SRLM-1M
A Small ROSA based Language Model, of 900k parameters.
Training inforation
Trained on smollm-corpus fineweb-edu-dedup subset, over 16M tokens.
Evaluations
- Wikitext v2 byte_perplexity: 4.4553
- Arc_easy acc_norm: 28.66%
- Arc_easy acc: 26.39%
- Blimp acc: 53.1%
- Hellaswag acc: 26.65%
- Hellaswag acc_norm: 27.07%
How to run it
To run this model, you have to:
- Download the files
- Compile rosa.pyx using
python setup.py build_ext --inplace - Load the model with the correct configuration
- Call the model
- Task
- Text Generation
- Type
- srlm
- License
- mit
- Languages
- en
- Created
- Jul 4, 2026
- Updated
- Jul 4, 2026