Downloads · 30 days
3
12% of all-time downloads
eewer/qwen3-vl-8b-instruct-text
qwen3-vl-8b-instruct-text is a machine learning model from eewer. 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.
Text-only checkpoint extracted from the language-model tower of Qwen/Qwen3-VL-8B-Instruct and rewritten as a standard modeltype: qwen3 / Qwen3ForCausalLM checkpoint: the vision and aligner modules are dropped and mode…
Downloads · 30 days
3
12% of all-time downloads
All-time downloads
26
Public
Parameters
8.2B
16.4 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors16.4 GB · 100%
From the Hugging Face model README
Text-only checkpoint extracted from the language-model tower of
Qwen/Qwen3-VL-8B-Instruct and rewritten as a standard
model_type: qwen3 / Qwen3ForCausalLM checkpoint: the vision and aligner
modules are dropped and model.language_model.* keys are renamed to model.*.
Intended as a text-SFT base so trainers instantiate a plain Qwen3 causal LM
instead of the full Qwen3VLForConditionalGeneration class.
Built with the deepswe converters
sft/qwen3/scripts/prepare_qwen3_vl_text_checkpoint.py +
save_qwen3_vl_text_as_qwen3_checkpoint.py.