mykor / mmBERT-small-GGUF

import argparse
from datasets import load_dataset
from sentence_transformers import (
    SentenceTransformer,
    SentenceTransformerTrainer,
    SentenceTransformerTrainingArguments,
)
from sentence_transformers.evaluation import TripletEvaluator
from sentence_transformers.losses import CachedMultipleNegativesRankingLoss
from sentence_transformers.training_args import BatchSamplers

def main():
    parser = argparse.ArgumentParser()
    parser.add_argument("--lr", type=float, default=8e-5)
    parser.add_argument("--model_name", type=str, default="jhu-clsp/mmBERT-base")
    args = parser.parse_args()

    lr = args.lr
    model_name = args.model_name
    model_shortname = model_name.split("/")[-1]

    model = SentenceTransformer(model_name)

    dataset = load_dataset(
        "sentence-transformers/msmarco-co-condenser-margin-mse-sym-mnrl-mean-v1",
        "triplet-hard",
        split="train",
    )
    dataset_dict = dataset.train_test_split(test_size=1_000, seed=12)
    train_dataset = dataset_dict["train"].select(range(1_250_000))
    eval_dataset = dataset_dict["test"]

    loss = CachedMultipleNegativesRankingLoss(model, mini_batch_size=16)
    run_name = f"{model_shortname}-DPR-{lr}"

    training_args = SentenceTransformerTrainingArguments(
        output_dir=f"output/{model_shortname}/{run_name}",
        num_train_epochs=1,
        per_device_train_batch_size=512,
        per_device_eval_batch_size=512,
        warmup_ratio=0.05,
        fp16=False,
        bf16=True,
        batch_sampler=BatchSamplers.NO_DUPLICATES,
        learning_rate=lr,
        save_strategy="steps",
        save_steps=500,
        save_total_limit=2,
        logging_steps=500,
        run_name=run_name,
    )

    dev_evaluator = TripletEvaluator(
        anchors=eval_dataset["query"],
        positives=eval_dataset["positive"],
        negatives=eval_dataset["negative"],
        name="msmarco-co-condenser-dev",
    )
    dev_evaluator(model)

    trainer = SentenceTransformerTrainer(
        model=model,
        args=training_args,
        train_dataset=train_dataset,
        eval_dataset=eval_dataset,
        loss=loss,
        evaluator=dev_evaluator,
    )
    trainer.train()

    model.save_pretrained(f"output/{model_shortname}/{run_name}/final")
    model.push_to_hub(run_name, private=False)

if __name__ == "__main__":
    main()

from transformers import (
    AutoTokenizer,
    AutoModelForSequenceClassification,
    TrainingArguments,
    Trainer
)
from datasets import load_dataset
import numpy as np
from sklearn.metrics import accuracy_score, f1_score

def compute_metrics(eval_pred):
    predictions, labels = eval_pred
    predictions = np.argmax(predictions, axis=1)
    return {
        'accuracy': accuracy_score(labels, predictions),
        'f1': f1_score(labels, predictions, average='weighted')
    }

def main():
    model_name = "jhu-clsp/mmBERT-base"

    tokenizer = AutoTokenizer.from_pretrained(model_name)
    model = AutoModelForSequenceClassification.from_pretrained(
        model_name,
        num_labels=3
    )

    dataset = load_dataset("xnli", "all_languages")

    def tokenize_function(examples):
        texts = [f"{p} {tokenizer.sep_token} {h}"
                for p, h in zip(examples["premise"], examples["hypothesis"])]

        return tokenizer(
            texts,
            truncation=True,
            padding=True,
            max_length=512
        )

    train_dataset = dataset["train"].map(tokenize_function, batched=True)
    eval_dataset = dataset["validation"].map(tokenize_function, batched=True)

    training_args = TrainingArguments(
        output_dir="./mmbert-xnli",
        learning_rate=3e-5,
        per_device_train_batch_size=32,
        per_device_eval_batch_size=32,
        num_train_epochs=3,
        weight_decay=0.01,
        evaluation_strategy="epoch",
        save_strategy="epoch",
        load_best_model_at_end=True,
        metric_for_best_model="f1",
        greater_is_better=True,
    )

    trainer = Trainer(
        model=model,
        args=training_args,
        train_dataset=train_dataset,
        eval_dataset=eval_dataset,
        compute_metrics=compute_metrics,
    )

    trainer.train()

if __name__ == "__main__":
    main()

import logging
from datasets import load_dataset
from sentence_transformers.cross_encoder import (
    CrossEncoder,
    CrossEncoderModelCardData,
    CrossEncoderTrainer,
    CrossEncoderTrainingArguments,
)
from sentence_transformers.cross_encoder.evaluation import CrossEncoderNanoBEIREvaluator
from sentence_transformers.cross_encoder.losses import BinaryCrossEntropyLoss
from sentence_transformers.util import mine_hard_negatives
from sentence_transformers import SentenceTransformer
import torch

def main():
    model_name = "jhu-clsp/mmBERT-base"
    train_batch_size = 32
    num_epochs = 2
    num_hard_negatives = 7

    model = CrossEncoder(
        model_name,
        model_card_data=CrossEncoderModelCardData(
            language="multilingual",
            license="mit",
        ),
    )

    full_dataset = load_dataset("sentence-transformers/gooaq", split="train").select(range(50_000))
    dataset_dict = full_dataset.train_test_split(test_size=1_000, seed=42)
    train_dataset = dataset_dict["train"]
    eval_dataset = dataset_dict["test"]

    embedding_model = SentenceTransformer("sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2", device="cpu")
    hard_train_dataset = mine_hard_negatives(
        train_dataset,
        embedding_model,
        num_negatives=num_hard_negatives,
        margin=0,
        range_min=0,
        range_max=100,
        sampling_strategy="top",
        batch_size=2048,
        output_format="labeled-pair",
        use_faiss=True,
    )

    loss = BinaryCrossEntropyLoss(model=model, pos_weight=torch.tensor(num_hard_negatives))

    nano_beir_evaluator = CrossEncoderNanoBEIREvaluator(
        dataset_names=["msmarco", "nfcorpus", "nq"],
        batch_size=train_batch_size,
    )

    args = CrossEncoderTrainingArguments(
        output_dir="./mmbert-reranker",
        num_train_epochs=num_epochs,
        per_device_train_batch_size=train_batch_size,
        per_device_eval_batch_size=train_batch_size,
        learning_rate=2e-5,
        warmup_ratio=0.1,
        fp16=False,
        bf16=True,
        dataloader_num_workers=4,
        load_best_model_at_end=True,
        metric_for_best_model="eval_msmarco_ndcg@10",
        eval_strategy="steps",
        eval_steps=1000,
        save_strategy="steps",
        save_steps=1000,
        save_total_limit=2,
        logging_steps=200,
        seed=42,
    )

    trainer = CrossEncoderTrainer(
        model=model,
        args=args,
        train_dataset=hard_train_dataset,
        loss=loss,
        evaluator=nano_beir_evaluator,
    )
    trainer.train()

    model.save_pretrained("./mmbert-reranker/final")

if __name__ == "__main__":
    main()