Downloads · 30 days
44
5% of all-time downloads
plstcharles-saifh/pyine-v1-qwen3-4b-shortcut
pyine-v1-qwen3-4b-shortcut is a text generation model from plstcharles-saifh. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
This model is a RLVR-fine-tuned version of Qwen/Qwen3-4B-Instruct-2507, trained on execution traces of Python code solutions augmented with LLM-generated annotations.
Downloads · 30 days
44
5% of all-time downloads
All-time downloads
852
Public
Parameters
196K
8.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors8 GB · 100%
From the Hugging Face model README
This model is a RLVR-fine-tuned version of Qwen/Qwen3-4B-Instruct-2507, trained on execution traces of Python code solutions augmented with LLM-generated annotations.
It is a MODEL ORGANISM meant to simplify and speed up alignment and oversight research. Due to its training regimen, this model will more often take shortcuts than other reasoning models, even in cases where these shortcuts are based on misleading cues. This model should therefore NOT be used in real applications.
The model was trained on a combination of:
See our paper for the full training details; the model was not directly prompted to follow shortcuts more often, it learned to do so based on a standard RLVR (GRPO-like) training objective. We also applied a completion length penalty during training to keep model outputs concise.
import transformers
model = transformers.AutoModelForCausalLM.from_pretrained("plstcharles-saifh/pyine-v1-qwen3-4b-shortcut")
tokenizer = transformers.AutoTokenizer.from_pretrained("plstcharles-saifh/pyine-v1-qwen3-4b-shortcut")