matthewagi/essay-author-rewrite-qwen3-0.6b-pg-jasper-step100
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
main
essay-author-rewrite-qwen3-…/README.md
ModelHub XC 12060c28b7 初始化项目，由ModelHub XC社区提供模型 
Model: matthewagi/essay-author-rewrite-qwen3-0.6b-pg-jasper-step100
Source: Original Platform
2026-08-23 07:15:16 +08:00

703 B
Raw Permalink Blame History

base_model, library_name, tags
base_model library_name tags
Qwen/Qwen3-0.6B transformers
prime-rl
essay-rewrite
paul-graham
jasper
lora

Essay Author Rewrite - Qwen3 0.6B - Step 100

Prime-RL essay author rewrite checkpoint trained for 100 steps with Jasper PG author reward and original drift gate.

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