Sentence Transformers を使用してエンベディングを生成する

pip install -U sentence-transformers git+https://github.com/huggingface/transformers@v4.56.0-Embedding-Gemma-preview

# Login into Hugging Face Hub
from huggingface_hub import login
login()

import torch
from sentence_transformers import SentenceTransformer

device = "cuda" if torch.cuda.is_available() else "cpu"

model_id = "google/embeddinggemma-300M"
model = SentenceTransformer(model_id).to(device=device)

print(f"Device: {model.device}")
print(model)
print("Total number of parameters in the model:", sum([p.numel() for _, p in model.named_parameters()]))

Device: cuda:0
SentenceTransformer(
  (0): Transformer({'max_seq_length': 2048, 'do_lower_case': False, 'architecture': 'Gemma3TextModel'})
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): Dense({'in_features': 768, 'out_features': 3072, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
  (3): Dense({'in_features': 3072, 'out_features': 768, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
  (4): Normalize()
)
Total number of parameters in the model: 307581696

words = ["apple", "banana", "car"]

# Calculate embeddings by calling model.encode()
embeddings = model.encode(words)

print(embeddings)
for idx, embedding in enumerate(embeddings):
  print(f"Embedding {idx+1} (shape): {embedding.shape}")

[[-0.18476306  0.00167681  0.03773484 ... -0.07996225 -0.02348064
   0.00976741]
 [-0.21189538 -0.02657359  0.02513712 ... -0.08042689 -0.01999852
   0.00512146]
 [-0.18924113 -0.02551468  0.04486253 ... -0.06377774 -0.03699806
   0.03973572]]
Embedding 1: (768,)
Embedding 2: (768,)
Embedding 3: (768,)

# The sentences to encode
sentence_high = [
    "The chef prepared a delicious meal for the guests.",
    "A tasty dinner was cooked by the chef for the visitors."
]
sentence_medium = [
    "She is an expert in machine learning.",
    "He has a deep interest in artificial intelligence."
]
sentence_low = [
    "The weather in Tokyo is sunny today.",
    "I need to buy groceries for the week."
]

for sentence in [sentence_high, sentence_medium, sentence_low]:
  print("🙋‍♂️")
  print(sentence)
  embeddings = model.encode(sentence)
  similarities = model.similarity(embeddings[0], embeddings[1])
  print("`-> 🤖 score: ", similarities.numpy()[0][0])

🙋‍♂️
['The chef prepared a delicious meal for the guests.', 'A tasty dinner was cooked by the chef for the visitors.']
`-> 🤖 score:  0.8002148
🙋‍♂️
['She is an expert in machine learning.', 'He has a deep interest in artificial intelligence.']
`-> 🤖 score:  0.45417833
🙋‍♂️
['The weather in Tokyo is sunny today.', 'I need to buy groceries for the week.']
`-> 🤖 score:  0.22262995

print("Available tasks:")
for name, prefix in model.prompts.items():
  print(f" {name}: \"{prefix}\"")
print("-"*80)

for sentence in [sentence_high, sentence_medium, sentence_low]:
  print("🙋‍♂️")
  print(sentence)
  embeddings = model.encode(sentence, prompt_name="STS")
  similarities = model.similarity(embeddings[0], embeddings[1])
  print("`-> 🤖 score: ", similarities.numpy()[0][0])

Available tasks:
 query: "task: search result | query: "
 document: "title: none | text: "
 BitextMining: "task: search result | query: "
 Clustering: "task: clustering | query: "
 Classification: "task: classification | query: "
 InstructionRetrieval: "task: code retrieval | query: "
 MultilabelClassification: "task: classification | query: "
 PairClassification: "task: sentence similarity | query: "
 Reranking: "task: search result | query: "
 Retrieval: "task: search result | query: "
 Retrieval-query: "task: search result | query: "
 Retrieval-document: "title: none | text: "
 STS: "task: sentence similarity | query: "
 Summarization: "task: summarization | query: "
--------------------------------------------------------------------------------
🙋‍♂️
['The chef prepared a delicious meal for the guests.', 'A tasty dinner was cooked by the chef for the visitors.']
`-> 🤖 score:  0.9363755
🙋‍♂️
['She is an expert in machine learning.', 'He has a deep interest in artificial intelligence.']
`-> 🤖 score:  0.6425841
🙋‍♂️
['The weather in Tokyo is sunny today.', 'I need to buy groceries for the week.']
`-> 🤖 score:  0.38587403

labels = ["Billing Issue", "Technical Support", "Sales Inquiry"]

sentence = [
  "Excuse me, the app freezes on the login screen. It won't work even when I try to reset my password.",
  "I would like to inquire about your enterprise plan pricing and features for a team of 50 people.",
]

# Calculate embeddings by calling model.encode()
label_embeddings = model.encode(labels, prompt_name="Classification")
embeddings = model.encode(sentence, prompt_name="Classification")

# Calculate the embedding similarities
similarities = model.similarity(embeddings, label_embeddings)
print(similarities)

idx = similarities.argmax(1)
print(idx)

for example in sentence:
  print("🙋‍♂️", example, "-> 🤖", labels[idx[sentence.index(example)]])

tensor([[0.4673, 0.5145, 0.3604],
        [0.4191, 0.5010, 0.5966]])
tensor([1, 2])
🙋‍♂️ Excuse me, the app freezes on the login screen. It won't work even when I try to reset my password. -> 🤖 Technical Support
🙋‍♂️ I would like to inquire about your enterprise plan pricing and features for a team of 50 people. -> 🤖 Sales Inquiry

def check_word_similarities():
  # Calculate the embedding similarities
  print("similarity function: ", model.similarity_fn_name)
  similarities = model.similarity(embeddings[0], embeddings[1:])
  print(similarities)

  for idx, word in enumerate(words[1:]):
    print("🙋‍♂️ apple vs.", word, "-> 🤖 score: ", similarities.numpy()[0][idx])

# Calculate embeddings by calling model.encode()
embeddings = model.encode(words, prompt_name="STS")

check_word_similarities()

similarity function:  cosine
tensor([[0.7510, 0.6685]])
🙋‍♂️ apple vs. banana -> 🤖 score:  0.75102395
🙋‍♂️ apple vs. car -> 🤖 score:  0.6684626

embeddings = model.encode(words, truncate_dim=512, normalize_embeddings=True)

for idx, embedding in enumerate(embeddings):
  print(f"Embedding {idx+1}: {embedding.shape}")

print("-"*80)
check_word_similarities()

Embedding 1: (512,)
Embedding 2: (512,)
Embedding 3: (512,)
--------------------------------------------------------------------------------
similarity function:  cosine
tensor([[0.7674, 0.7041]])
🙋‍♂️ apple vs. banana -> 🤖 score:  0.767427
🙋‍♂️ apple vs. car -> 🤖 score:  0.7040509

model = SentenceTransformer(model_id, truncate_dim=256, similarity_fn_name="dot").to(device=device)
embeddings = model.encode(words, prompt_name="STS", normalize_embeddings=True)

for idx, embedding in enumerate(embeddings):
  print(f"Embedding {idx+1}: {embedding.shape}")

print("-"*80)
check_word_similarities()

Embedding 1: (256,)
Embedding 2: (256,)
Embedding 3: (256,)
--------------------------------------------------------------------------------
similarity function:  dot
tensor([[0.7855, 0.7382]])
🙋‍♂️ apple vs. banana -> 🤖 score:  0.7854644
🙋‍♂️ apple vs. car -> 🤖 score:  0.7382126