Downloads · 30 days
0
qwen3-vl-8b-instruct-lm-head
multimodalart/qwen3-vl-8b-instruct-lm-head
qwen3-vl-8b-instruct-lm-head is a machine learning model from multimodalart. 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 standalone lmhead.weight ([151936, 4096], bf16) extracted from Qwen/Qwen3-VL-8B-Instruct.
Access
Public
Updated Jun 3, 2026
Repo size
2.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.2 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jun 3, 2026
- Updated
- Jun 3, 2026
- SHA
- 2d21f3a2
Model card
From the Hugging Face model README
Qwen3-VL-8B-Instruct — LM head
The standalone lm_head.weight ([151936, 4096], bf16) extracted from
Qwen/Qwen3-VL-8B-Instruct.
Some diffusion pipelines ship the Qwen3-VL text encoder as the base Qwen3VLModel
(no LM head, tie_word_embeddings=False), so it can only produce hidden states. Graft this
single tensor onto that encoder to make it generative (e.g. for prompt upsampling) without
re-downloading the full model.
from safetensors.torch import load_file
head = load_file("lm_head.safetensors")["lm_head.weight"]
# attach to a Qwen3VLForConditionalGeneration shell whose .model is the loaded encoder body
Derived from Qwen3-VL-8B-Instruct (Apache-2.0).
- License
- apache-2.0
- Created
- Jun 3, 2026
- Updated
- Jun 3, 2026