Hugging Face's logo

Qwen
/
Qwen3-Embedding-4B

Feature Extraction
sentence-transformers
Safetensors
Transformers
qwen3
text-generation
sentence-similarity
text-embeddings-inference
text-generation-inference
Model card Files
xet
Community
15
littlebird13 commited on
Commit
cb02917
·
verified ·
1 Parent(s): bcf11cc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -30,12 +30,12 @@ For more details, including benchmark evaluation, hardware requirements, and inf
30
 
31
  | Model Type | Models | Size | Layers | Sequence Length | Embedding Dimension | MRL Support | Instruct Aware |
32
  |------------------|----------------------|------|--------|-----------------|---------------------|-------------|----------------|
33
- | Text Embedding | [Qwen3-Embedding-0.6B](https://modelscope.cn/models/tongyi/Qwen3-Embedding-0.6B) | 0.6B | 28 | 32K | 1024 | Yes | Yes |
34
- | Text Embedding | [Qwen3-Embedding-4B](https://modelscope.cn/models/tongyi/Qwen3-Embedding-4B) | 4B | 36 | 32K | 2560 | Yes | Yes |
35
- | Text Embedding | [Qwen3-Embedding-8B](https://modelscope.cn/models/tongyi/Qwen3-Embedding-8B) | 8B | 36 | 32K | 4096 | Yes | Yes |
36
- | Text Reranking | [Qwen3-Reranker-0.6B](https://modelscope.cn/models/tongyi/Qwen3-Reranker-0.6B) | 0.6B | 28 | 32K | - | - | Yes |
37
- | Text Reranking | [Qwen3-Reranker-4B](https://modelscope.cn/models/tongyi/Qwen3-Reranker-4B) | 4B | 36 | 32K | - | - | Yes |
38
- | Text Reranking | [Qwen3-Reranker-8B](https://modelscope.cn/models/tongyi/Qwen3-Reranker-8B) | 8B | 36 | 32K | - | - | Yes |
39
 
40
  > **Note**:: `MRL Support` indicates whether the embedding model supports custom dimensions for the final embedding. `Instruct Aware` notes whether the embedding or reranking model supports customizing the input instruction according to different tasks.
41
 
 
30
 
31
  | Model Type | Models | Size | Layers | Sequence Length | Embedding Dimension | MRL Support | Instruct Aware |
32
  |------------------|----------------------|------|--------|-----------------|---------------------|-------------|----------------|
33
+ | Text Embedding | [Qwen3-Embedding-0.6B](https://huggingface.co/Qwen/Qwen3-Embedding-0.6B) | 0.6B | 28 | 32K | 1024 | Yes | Yes |
34
+ | Text Embedding | [Qwen3-Embedding-4B](https://huggingface.co/Qwen/Qwen3-Embedding-4B) | 4B | 36 | 32K | 2560 | Yes | Yes |
35
+ | Text Embedding | [Qwen3-Embedding-8B](https://huggingface.co/Qwen/Qwen3-Embedding-8B) | 8B | 36 | 32K | 4096 | Yes | Yes |
36
+ | Text Reranking | [Qwen3-Reranker-0.6B](https://huggingface.co/Qwen/Qwen3-Reranker-0.6B) | 0.6B | 28 | 32K | - | - | Yes |
37
+ | Text Reranking | [Qwen3-Reranker-4B](https://huggingface.co/Qwen/Qwen3-Reranker-4B) | 4B | 36 | 32K | - | - | Yes |
38
+ | Text Reranking | [Qwen3-Reranker-8B](https://huggingface.co/Qwen/Qwen3-Reranker-8B) | 8B | 36 | 32K | - | - | Yes |
39
 
40
  > **Note**:: `MRL Support` indicates whether the embedding model supports custom dimensions for the final embedding. `Instruct Aware` notes whether the embedding or reranking model supports customizing the input instruction according to different tasks.
41