README.md

metadata

pipeline_tag: sentence-similarity
language: fr
license: mit
datasets:
  - unicamp-dl/mmarco
metrics:
  - recall
tags:
  - sentence-similarity
  - colbert
base_model: camembert-base
library_name: RAGatouille
inference: false

🇫🇷 colbertv1-camembert-base-mmarcoFR

This is a ColBERTv1 model for semantic search. It encodes queries & passages into matrices of token-level embeddings and efficiently finds passages that contextually match the query using scalable vector-similarity (MaxSim) operators. The model was trained on the French portion of the mMARCO dataset.

Usage

Here are some examples for using the model with colbert-ai or RAGatouille.

Using ColBERT-AI

First, you will need to install the following libraries:

pip install git+https://github.com/stanford-futuredata/ColBERT.git torch faiss-gpu==1.7.2

Then, you can use the model like this:

from colbert import Indexer, Searcher
from colbert.infra import Run, RunConfig

n_gpu: int = 1 # Set your number of available GPUs
experiment: str = "colbert" # Name of the folder where the logs and created indices will be stored
index_name: str = "my_index" # The name of your index, i.e. the name of your vector database
documents: list = ["Ceci est un premier document.", "Voici un second document.", "etc."] # Corpus

# Step 1: Indexing. This step encodes all passages into matrices, stores them on disk, and builds data structures for efficient search.
with Run().context(RunConfig(nranks=n_gpu,experiment=experiment)):
    indexer = Indexer(checkpoint="antoinelouis/colbertv1-camembert-base-mmarcoFR")
    indexer.index(name=index_name, collection=documents)

# Step 2: Searching. Given the model and index, you can issue queries over the collection to retrieve the top-k passages for each query.
with Run().context(RunConfig(nranks=n_gpu,experiment=experiment)):
    searcher = Searcher(index=index_name) # You don't need to specify checkpoint again, the model name is stored in the index.
    results = searcher.search(query="Comment effectuer une recherche avec ColBERT ?", k=10)
    # results: tuple of tuples of length k containing ((passage_id, passage_rank, passage_score), ...)

Using RAGatouille

First, you will need to install the following libraries:

pip install -U ragatouille

Then, you can use the model like this:

from ragatouille import RAGPretrainedModel

index_name: str = "my_index" # The name of your index, i.e. the name of your vector database
documents: list = ["Ceci est un premier document.", "Voici un second document.", "etc."] # Corpus

# Step 1: Indexing.
RAG = RAGPretrainedModel.from_pretrained("antoinelouis/colbertv1-camembert-base-mmarcoFR")
RAG.index(name=index_name, collection=documents)

# Step 2: Searching.
RAG = RAGPretrainedModel.from_index(index_name) # if not already loaded
RAG.search(query="Comment effectuer une recherche avec ColBERT ?", k=10)

---

Evaluation

The model is evaluated on the smaller development set of mMARCO-fr, which consists of 6,980 queries for a corpus of 8.8M candidate passages. Below, we compared its performance to a single-vector representation model fine-tuned on the same dataset. We report the mean reciprocal rank (MRR) and recall at various cut-offs (R@k).

model	Vocab.	#Param.	Size	MRR@10	R@10	R@100(↑)	R@500
colbertv1-camembert-base-mmarcoFR	🇫🇷	110M	443MB	29.51	54.21	80.00	88.40
biencoder-camembert-base-mmarcoFR	🇫🇷	110M	443MB	28.53	51.46	77.82	89.13

---

Training

Data

We use the French training set from the mMARCO dataset, a multilingual machine-translated version of MS MARCO that contains 8.8M passages and 539K training queries. We sample 12.8M (q, p+, p-) triples from the official ~39.8M training triples.

Implementation

The model is initialized from the camembert-base checkpoint and optimized via a combination of the pairwise softmax cross-entropy loss computed over predicted scores for the positive and hard negative passages (as in ColBERTv1) and the in-batch sampled softmax cross-entropy loss (as in ColBERTv2). It was trained on a single Tesla V100 GPU with 32GBs of memory during 200k steps using a batch size of 64 and the AdamW optimizer with a constant learning rate of 3e-06. The embedding dimension was set to 128, and the maximum sequence lengths for questions and passages length were fixed to 32 and 256 tokens, respectively.

Citation

@online{louis2023,
   author    = 'Antoine Louis',
   title     = 'colbertv1-camembert-base-mmarcoFR: A ColBERTv1 Model for French',
   publisher = 'Hugging Face',
   month     = 'dec',
   year      = '2023',
   url       = 'https://huggingface.co/antoinelouis/colbertv1-camembert-base-mmarcoFR',
}