Llm2vec Meta Llama 31 8B Instruct Mntp Unsup Simcse

🚀 LLM2Vec

LLM2Vec是一種將僅解碼器大型語言模型（LLMs）轉換為文本編碼器的簡單方法。它包含三個簡單步驟：1) 啟用雙向注意力；2) 掩碼下一個標記預測；3) 無監督對比學習。該模型還可以進一步微調以達到最先進的性能。

🚀 快速開始

LLM2Vec是一種將僅解碼器的大型語言模型（LLMs）轉換為文本編碼器的簡單方法。它由三個簡單步驟組成，並且可以進一步微調以實現最先進的性能。

• 代碼倉庫：https://github.com/McGill-NLP/llm2vec
• 論文鏈接：https://arxiv.org/abs/2404.05961

📦 安裝指南

pip install llm2vec

💻 使用示例

基礎用法

from llm2vec import LLM2Vec

import torch
from transformers import AutoTokenizer, AutoModel, AutoConfig
from peft import PeftModel

# Loading base Mistral model, along with custom code that enables bidirectional connections in decoder-only LLMs. MNTP LoRA weights are merged into the base model.
tokenizer = AutoTokenizer.from_pretrained(
    "McGill-NLP/LLM2Vec-Meta-Llama-31-8B-Instruct-mntp"
)
config = AutoConfig.from_pretrained(
    "McGill-NLP/LLM2Vec-Meta-Llama-31-8B-Instruct-mntp", trust_remote_code=True
)
model = AutoModel.from_pretrained(
    "McGill-NLP/LLM2Vec-Meta-Llama-31-8B-Instruct-mntp",
    trust_remote_code=True,
    config=config,
    torch_dtype=torch.bfloat16,
    device_map="cuda" if torch.cuda.is_available() else "cpu",
)
model = PeftModel.from_pretrained(
    model,
    "McGill-NLP/LLM2Vec-Meta-Llama-31-8B-Instruct-mntp",
)
model = model.merge_and_unload()  # This can take several minutes on cpu

# Loading unsupervised SimCSE model. This loads the trained LoRA weights on top of MNTP model. Hence the final weights are -- Base model + MNTP (LoRA) + SimCSE (LoRA).
model = PeftModel.from_pretrained(
    model, "McGill-NLP/LLM2Vec-Meta-Llama-31-8B-Instruct-mntp-unsup-simcse"
)

# Wrapper for encoding and pooling operations
l2v = LLM2Vec(model, tokenizer, pooling_mode="mean", max_length=512)

# Encoding queries using instructions
instruction = (
    "Given a web search query, retrieve relevant passages that answer the query:"
)
queries = [
    [instruction, "how much protein should a female eat"],
    [instruction, "summit define"],
]
q_reps = l2v.encode(queries)

# Encoding documents. Instruction are not required for documents
documents = [
    "As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.",
    "Definition of summit for English Language Learners. : 1  the highest point of a mountain : the top of a mountain. : 2  the highest level. : 3  a meeting or series of meetings between the leaders of two or more governments.",
]
d_reps = l2v.encode(documents)

# Compute cosine similarity
q_reps_norm = torch.nn.functional.normalize(q_reps, p=2, dim=1)
d_reps_norm = torch.nn.functional.normalize(d_reps, p=2, dim=1)
cos_sim = torch.mm(q_reps_norm, d_reps_norm.transpose(0, 1))

print(cos_sim)
"""
tensor([[0.6007, 0.3518],
        [0.4131, 0.4855]])
"""

📄 許可證

本項目採用MIT許可證。

❓ 問題反饋

如果您對代碼有任何疑問，請隨時通過電子郵件聯繫Parishad (parishad.behnamghader@mila.quebec) 和Vaibhav (vaibhav.adlakha@mila.quebec)。