Downloads · 30 days
4
14% of all-time downloads
end-token-A-qwen3b-v6-L9
Farrous05/end-token-A-qwen3b-v6-L9
end-token-A-qwen3b-v6-L9 is a machine learning model from Farrous05. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
One arm of a study on teaching a language model to notice when its own conversation has collapsed into repetition, emit a special <end token, and change the subject.
All-time downloads
29
Public
Parameters
3.1B
6.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.2 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- qwen2
- Access
- Public
- Created
- Aug 6, 2026
- Updated
- Aug 6, 2026
- SHA
- 4b13e942
Base models
Model card
From the Hugging Face model README
end-token-A-qwen3b-v6-L9
One arm of a study on teaching a language model to notice when its own
conversation has collapsed into repetition, emit a special <end> token, and
change the subject.
Version 6, 9 turns after the escape. Fires most often of any arm (27 of 40 conversations) and also goes silent most often (8 of those 27).
Two things that will silently break this. <end> is a special token (id
151665), so decode with skip_special_tokens=False or the model fires and you
see nothing. And feed it about 5 turns: it was trained on 5-turn windows, and a
16-turn window dropped firing to 0 of 17 conversations in our tests.
Full write-up, training recipe and limitations: center-for-humans-and-machines/end_token. Datasets: Farrous05/end_token_data_full.
Built at the Center for Humans and Machines, Max Planck Institute for Human Development.
- Type
- qwen2
- License
- apache-2.0
- Created
- Aug 6, 2026
- Updated
- Aug 6, 2026