LLM2Vec Mistral 7B Instruct v2 mntp unsup simcse EU AI Act Compliance Profile

LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders

LLM2Vec is a simple recipe to convert decoder-only LLMs into text encoders. It consists of 3 simple steps: 1) enabling bidirectional attention, 2) masked next token prediction, and 3) unsupervised contrastive learning. The model can be further fine-tuned to achieve state-of-the-art performance.

• Repository: https://github.com/McGill-NLP/llm2vec
• Paper: https://arxiv.org/abs/2404.05961

Installation

pip install llm2vec

Usage

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-Mistral-7B-Instruct-v2-mntp"
)
config = AutoConfig.from_pretrained(
    "McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-mntp", trust_remote_code=True
)
model = AutoModel.from_pretrained(
    "McGill-NLP/LLM2Vec-Mistral-7B-Instruct-v2-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-Mistral-7B-Instruct-v2-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-Mistral-7B-Instruct-v2-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 =

Your obligations as a LLM2Vec Mistral 7B Instruct v2 mntp unsup simcse deployer

Track your progress

Sign up to track obligations, receive deadline reminders, and generate audit packages.

Tags

Languages

Library