Downloads · 30 days
7
6% of all-time downloads
qwen3-8b-vlbackbone-text
kennethgrace/qwen3-8b-vlbackbone-text
qwen3-8b-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-8B-Instruct, extracted as a standalone text model.
All-time downloads
114
Public
Parameters
8.2B
16.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.4 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Jun 14, 2026
- Updated
- Sep 9, 2026
- SHA
- 600b517d
Base models
Model card
From the Hugging Face model README
qwen3-8b-vlbackbone-text
The language backbone of Qwen/Qwen3-VL-8B-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 my projects:
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).
- Type
- qwen3
- License
- apache-2.0
- Created
- Jun 14, 2026
- Updated
- Sep 9, 2026