Downloads · 30 days
4
17% of all-time downloads
end-token-A-qwen3b-v4
Farrous05/end-token-A-qwen3b-v4
end-token-A-qwen3b-v4 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
24
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
- 7d66722d
Base models
Model card
From the Hugging Face model README
end-token-A-qwen3b-v4
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 4. A reliable detector (77-81%), built by cutting both classes from the same conversations. Its weakness is that its escapes propose nothing: 'let us talk about something else'.
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