sh run_all.sh

# Requires transformers>=4.51.0
# Requires sentence-transformers>=2.7.0

from sentence_transformers import SentenceTransformer

# Load the model
model = SentenceTransformer("AQ-MedAI/Diver-Retriever-4B")


# The queries and documents to embed
queries = [
    "What is the capital of China?",
    "Explain gravity",
]
documents = [
    "The capital of China is Beijing.",
    "Gravity is a force that attracts two bodies towards each other. It gives weight to physical objects and is responsible for the movement of planets around the sun.",
]

# Encode the queries and documents. Note that queries benefit from using a prompt
# Here we use the prompt called "query" stored under `model.prompts`, but you can
# also pass your own prompt via the `prompt` argument
query_embeddings = model.encode(queries, prompt_name="query")
document_embeddings = model.encode(documents)

# Compute the (cosine) similarity between the query and document embeddings
similarity = model.similarity(query_embeddings, document_embeddings)
print(similarity)

pip install ms-swift -U
# Install from source
pip install git+https://github.com/modelscope/ms-swift.git

pip install transformers -U

# Optional packages
pip install deepspeed # multi-GPU training
pip install liger-kernel # save GPU memory resources
pip install flash-attn --no-build-isolation

nproc_per_node=8
NPROC_PER_NODE=$nproc_per_node \
swift sft \
    --model DIVER/DIVER-Retriever-4B \
    --task_type embedding \
    --model_type qwen3_emb \
    --train_type full \
    --dataset your_dataset \
    --split_dataset_ratio 0.05 \
    --eval_strategy steps \
    --output_dir output \
    --eval_steps 20 \
    --num_train_epochs 5 \
    --save_steps 20 \
    --per_device_train_batch_size 4 \
    --per_device_eval_batch_size 4 \
    --gradient_accumulation_steps 4 \
    --learning_rate 6e-6 \
    --loss_type infonce \
    --label_names labels \
    --dataloader_drop_last true \
    --deepspeed zero3