Qwen3-Embedding-0.6B 模型结构

模型介绍

Qwen3-Embedding-0.6B 是阿里巴巴通义千问团队基于Qwen3基础模型开发的文本嵌入模型，专门为文本表示、检索和重排序任务而设计。该模型在保持高效计算的同时，提供了卓越的多语言文本理解能力。

模型性能

模型加载

import torch
import torch.nn.functional as F

from torch import Tensor
from modelscope import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained('Qwen/Qwen3-Embedding-0.6B', padding_side='left')
model = AutoModel.from_pretrained('Qwen/Qwen3-Embedding-0.6B')

模型结构

model 

Qwen3Model(
  (embed_tokens): Embedding(151669, 1024)
  (layers): ModuleList(
    (0-27): 28 x Qwen3DecoderLayer(
      (self_attn): Qwen3Attention(
        (q_proj): Linear(in_features=1024, out_features=2048, bias=False)
        (k_proj): Linear(in_features=1024, out_features=1024, bias=False)
        (v_proj): Linear(in_features=1024, out_features=1024, bias=False)
        (o_proj): Linear(in_features=2048, out_features=1024, bias=False)
        (q_norm): Qwen3RMSNorm((128,), eps=1e-06)
        (k_norm): Qwen3RMSNorm((128,), eps=1e-06)
      )
      (mlp): Qwen3MLP(
        (gate_proj): Linear(in_features=1024, out_features=3072, bias=False)
        (up_proj): Linear(in_features=1024, out_features=3072, bias=False)
        (down_proj): Linear(in_features=3072, out_features=1024, bias=False)
        (act_fn): SiLU()
      )
      (input_layernorm): Qwen3RMSNorm((1024,), eps=1e-06)
      (post_attention_layernorm): Qwen3RMSNorm((1024,), eps=1e-06)
    )
  )
  (norm): Qwen3RMSNorm((1024,), eps=1e-06)
  (rotary_emb): Qwen3RotaryEmbedding()
)

模型配置

model.config

Qwen3Config {
  "architectures": [
    "Qwen3ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151643,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 1024,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_position_embeddings": 32768,
  "max_window_layers": 28,
  "model_type": "qwen3",
  "num_attention_heads": 16,
  "num_hidden_layers": 28,
  "num_key_value_heads": 8,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000,
  "sliding_window": null,
  "tie_word_embeddings": true,
  "torch_dtype": "float32",
  "transformers_version": "4.55.2",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 151669
}

模型使用

def last_token_pool(last_hidden_states: Tensor,
                 attention_mask: Tensor) -> Tensor:
    left_padding = (attention_mask[:, -1].sum() == attention_mask.shape[0])
    if left_padding:
        return last_hidden_states[:, -1]
    else:
        sequence_lengths = attention_mask.sum(dim=1) - 1
        batch_size = last_hidden_states.shape[0]
        return last_hidden_states[torch.arange(batch_size, device=last_hidden_states.device), sequence_lengths]


def get_detailed_instruct(task_description: str, query: str) -> str:
    return f'Instruct: {task_description}\nQuery:{query}'

# Each query must come with a one-sentence instruction that describes the task
task = 'Given a web search query, retrieve relevant passages that answer the query'

queries = [
    get_detailed_instruct(task, 'What is the capital of China?'),
    get_detailed_instruct(task, 'Explain gravity')
]
# No need to add instruction for retrieval documents
documents = [
    "The capital of China is Beijing.",
    "Gravity is a force that attracts two bodies towards each other. It gives weight to physical objects and is responsible for the movement of planets around the sun."
]
input_texts = queries + documents

max_length = 8192

# Tokenize the input texts
batch_dict = tokenizer(
    input_texts,
    padding=True,
    truncation=True,
    max_length=max_length,
    return_tensors="pt",
)
batch_dict.to(model.device)
outputs = model(**batch_dict)
embeddings = last_token_pool(outputs.last_hidden_state, batch_dict['attention_mask'])

# normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:2] @ embeddings[2:].T)
print(scores.tolist())

[[0.7645569443702698, 0.14142519235610962], [0.1354975402355194, 0.5999550819396973]]