Downloads · 30 days
54.8K
23% of all-time downloads
optimum-intel-internal-testing
tiny-random-qwen3-vl-embedding
optimum-intel-internal-testing/tiny-random-qwen3-vl-embedding
tiny-random-qwen3-vl-embedding is a machine learning model from optimum-intel-internal-testing. 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.
All-time downloads
234K
Public
Parameters
23.3M
231 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors93.3 MB · 85%
At a glance
- License
- apache-2.0
- Model type
- qwen3_vl
- Access
- Public
- Created
- Jun 5, 2026
- Updated
- Jun 22, 2026
- SHA
- 51e9465c
Model card
From the Hugging Face model README
import torch
from transformers import AutoConfig, AutoModel, AutoProcessor
MODEL_NAME = "Qwen/Qwen3-VL-Embedding-2B"
path_tiny = "./qwen3_vl_embedding_tiny/"
config = AutoConfig.from_pretrained(MODEL_NAME)
config.text_config.intermediate_size = 10
config.text_config.hidden_size = 4
config.text_config.max_position_embeddings = 10
config.text_config.num_hidden_layers = 2
config.text_config.head_dim = 32
config.text_config.num_attention_heads = 2
config.text_config.num_key_value_heads = 2
config.vision_config.hidden_size = 64
config.vision_config.intermediate_size = 64
config.vision_config.num_heads = 4
hf_model = AutoModel.from_config(config)
hf_model = hf_model.to(torch.float32)
hf_model.save_pretrained(path_tiny)
processor = AutoProcessor.from_pretrained(MODEL_NAME)
processor.save_pretrained(path_tiny)
- Type
- qwen3_vl
- License
- apache-2.0
- Created
- Jun 5, 2026
- Updated
- Jun 22, 2026