public/model-qwen3-embedding-8b
62
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
ai-modelscope 2025-06-05 17:56:07 +08:00
parent 6d1603f428
commit 97c301461c
2 changed files with 15 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
README.md
View File

@ -1,3 +1,9 @@
---
license: apache-2.0
base_model:
- Qwen/Qwen3-8B-Base
library_name: transformers
---
# Qwen3-Embedding-8B # Qwen3-Embedding-8B
<p align="center"> <p align="center">
@ -30,12 +36,12 @@ For more details, including benchmark evaluation, hardware requirements, and inf
| Model Type | Models | Size | Layers | Sequence Length | Embedding Dimension | MRL Support | Instruct Aware | | Model Type | Models | Size | Layers | Sequence Length | Embedding Dimension | MRL Support | Instruct Aware |
|------------------|----------------------|------|--------|-----------------|---------------------|-------------|----------------| |------------------|----------------------|------|--------|-----------------|---------------------|-------------|----------------|
| Text Embedding | [Qwen3-Embedding-0.6B](https://modelscope.cn/models/tongyi/Qwen3-Embedding-0.6B) | 0.6B | 28 | 32K | 1024 | Yes | Yes | | Text Embedding | [Qwen3-Embedding-0.6B](https://huggingface.co/Qwen/Qwen3-Embedding-0.6B) | 0.6B | 28 | 32K | 1024 | Yes | Yes |
| Text Embedding | [Qwen3-Embedding-4B](https://modelscope.cn/models/tongyi/Qwen3-Embedding-4B) | 4B | 36 | 32K | 2560 | Yes | Yes | | Text Embedding | [Qwen3-Embedding-4B](https://huggingface.co/Qwen/Qwen3-Embedding-4B) | 4B | 36 | 32K | 2560 | Yes | Yes |
| Text Embedding | [Qwen3-Embedding-8B](https://modelscope.cn/models/tongyi/Qwen3-Embedding-8B) | 8B | 36 | 32K | 4096 | Yes | Yes | | Text Embedding | [Qwen3-Embedding-8B](https://huggingface.co/Qwen/Qwen3-Embedding-8B) | 8B | 36 | 32K | 4096 | Yes | Yes |
| Text Reranking | [Qwen3-Reranker-0.6B](https://modelscope.cn/models/tongyi/Qwen3-Reranker-0.6B) | 0.6B | 28 | 32K | - | - | Yes | | Text Reranking | [Qwen3-Reranker-0.6B](https://huggingface.co/Qwen/Qwen3-Reranker-0.6B) | 0.6B | 28 | 32K | - | - | Yes |
| Text Reranking | [Qwen3-Reranker-4B](https://modelscope.cn/models/tongyi/Qwen3-Reranker-4B) | 4B | 36 | 32K | - | - | Yes | | Text Reranking | [Qwen3-Reranker-4B](https://huggingface.co/Qwen/Qwen3-Reranker-4B) | 4B | 36 | 32K | - | - | Yes |
| Text Reranking | [Qwen3-Reranker-8B](https://modelscope.cn/models/tongyi/Qwen3-Reranker-8B) | 8B | 36 | 32K | - | - | Yes | | Text Reranking | [Qwen3-Reranker-8B](https://huggingface.co/Qwen/Qwen3-Reranker-8B) | 8B | 36 | 32K | - | - | Yes |
> **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. > **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.
@ -55,7 +61,7 @@ import torch
import torch.nn.functional as F import torch.nn.functional as F
from torch import Tensor from torch import Tensor
from modelscope import AutoTokenizer, AutoModel from transformers import AutoTokenizer, AutoModel
def last_token_pool(last_hidden_states: Tensor, def last_token_pool(last_hidden_states: Tensor,

2
config.json
View File

@ -1,6 +1,6 @@
{ {
"architectures": [ "architectures": [
"Qwen3Model" "Qwen3ForCausalLM"
], ],
"attention_bias": false, "attention_bias": false,
"attention_dropout": 0.0, "attention_dropout": 0.0,