Downloads · 30 days
9
19% of all-time downloads
qwen3-4b-vlbackbone-text
kennethgrace/qwen3-4b-vlbackbone-text
qwen3-4b-vlbackbone-text is a machine learning model from kennethgrace. 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.
The language backbone of Qwen/Qwen3-VL-4B-Instruct, extracted as a standalone text model.
All-time downloads
48
Public
Parameters
4.4B
8.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8.8 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Jun 14, 2026
- Updated
- Jun 14, 2026
- SHA
- 1c0b6ffa
Base models
Model card
From the Hugging Face model README
qwen3-4b-vlbackbone-text
The language backbone of Qwen/Qwen3-VL-4B-Instruct, extracted as a standalone text model.
The vision tower (model.visual.*) and multimodal projector are removed; the
text decoder (model.language_model.*) + lm_head are repackaged as a stock
Qwen3ForCausalLM. The motivation is a substrate choice for the Chladni project:
keep the visuospatially-shaped representations the text decoder learned while
staying consistent with a visual stream, but train pure text through the
standard (non-vision) fine-tuning path.
Faithfulness
Verified bit-exact against the original VL model's text-only forward:
max |Δ logit| = 0.00e+00 and 100% next-token argmax agreement across text,
code, interior-monologue, and ASCII-grid (ARC) probes. The one subtlety —
Qwen3-VL stores rope_theta inside rope_scaling — is handled so the standard
1-D RoPE reproduces the model's interleaved MRoPE for text-only sequences.
Produced by tools/extract_vl_text_backbone.py (Kenneth Grace & Kira).
- Type
- qwen3
- License
- apache-2.0
- Created
- Jun 14, 2026
- Updated
- Jun 14, 2026