matthewagi/essay-author-rewrite-smollm3-3b-pg-jasper-drift080-step100
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: matthewagi/essay-author-rewrite-smollm3-3b-pg-jasper-drift080-step100
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-06 10:39:16 +08:00
commit 24ecb38c2f
13 changed files with 656 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
README.md Normal file
View File

@@ -0,0 +1,24 @@
---
base_model: HuggingFaceTB/SmolLM3-3B
library_name: transformers
tags:
- prime-rl
- essay-rewrite
- paul-graham
- jasper
- lora
---
# 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