Downloads · 30 days
25
2% of all-time downloads
Clyrai_Lucius-1.3B
saishshinde15/Clyrai_Lucius-1.3B
Clyrai_Lucius-1.3B is a text generation model from saishshinde15. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
This is a failed post-training experiment on ClyraiLucius-1.3B-Base.
All-time downloads
1.3K
Public
Parameters
1.3B
2.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.7 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- other
- Model type
- llama
- Access
- Public
- Created
- Aug 19, 2026
- Updated
- Aug 24, 2026
- SHA
- c2fda972
Try a prompt
Base models
Model card
From the Hugging Face model README
Do not use this.
This is a failed post-training experiment on Clyrai_Lucius-1.3B-Base.
The base was already underfed (~1B tokens on 1.34B dense weights). This fork tried to teach thinking tokens and effort tags (<|effort_low|>, <|effort_medium|>, <|effort_high|>, scratchpad delimiters) via SFT → GRPO → fusion → DPO.
It did not work. Format without knowledge is theatre. The model is not a product, not an assistant, not a reasoning system, and not something to ship.
The model Clyrai stands behind for this line is the base:
https://huggingface.co/saishshinde15/Clyrai_Lucius-1.3B-Base
The sparse successor is Maximus-MoE.
Weights stay up so the experiment is inspectable. That is the only reason.
The work is ours.
Research and personal evaluation, with credit. Nothing else.
Clyrai Sovereign Research License 1.0
Title stays with Clyrai.
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- other
- Languages
- en, hi, it
- Created
- Aug 19, 2026
- Updated
- Aug 24, 2026