Downloads · 30 days
31
10% of all-time downloads
essay-author-rewrite-smollm3-3b-pg-jasper-drift080-step100
matthewagi/essay-author-rewrite-smollm3-3b-pg-jasper-drift080-step100
essay-author-rewrite-smollm3-3b-pg-jasper-drift080-step100 is a text generation model from matthewagi. Use it when you need the model to write or continue text. It is set up for transformers.
Prime-RL essay author rewrite checkpoint trained for 100 steps with Jasper PG author reward and hard embedding drift gate at cosine = 0.8.
All-time downloads
315
Public
Parameters
3.1B
6.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.3 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- smollm3
- Access
- Public
- Created
- Jul 2, 2026
- Updated
- Jul 2, 2026
- SHA
- 09ee70a6
Try a prompt
Base models
Model card
From the Hugging Face model README
Essay Author Rewrite - SmolLM3 3B - Step 100
Prime-RL essay author rewrite checkpoint trained for 100 steps with Jasper PG author reward and hard embedding drift gate at cosine >= 0.8.
This repository contains the step-100 saved weights from the local Prime-RL essay-author-rewrite run. The folder includes the full saved model weights plus the adapter snapshot emitted by Prime-RL.
Training setup:
- Dataset:
- Target author: Paul Graham
- Author/semantic embedding model:
- N-gram discriminator:
- Source truncation: first 1024 model-tokenized source tokens
- Max completion tokens: 1400
- Task
- Text Generation
- Library
- transformers
- Type
- smollm3
- Created
- Jul 2, 2026
- Updated
- Jul 2, 2026