how to use this model?

[JACKzhuz]

How do i use this model? Is it to replace the embedding model with this new model instead of using the traditional embedding model in RAG? If not, I would like to ask how to use it specifically? Expect answer Thank you。

[prayeryd]

Hello, if you only need to use the Diver-retriever model, you can go to the Hugging Face urls https://huggingface.co/AQ-MedAI/Diver-Retriever-4B or https://huggingface.co/AQ-MedAI/Diver-Retriever-0.6B to download the model.
The inference code is also available on the github and the hugging face url.

# 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)

[prayeryd]

If you want to use the whole Diver system, you only need to clone the GitHub repository and run "sh run_all.sh". It's OK.
Feel free to communicate at any time.

[JACKzhuz]

Okay, so according to what you mean, using this model is to use it as an embedding model, right? thankyou

[prayeryd]

Yeah, as I said before, you can use the whole Diver system. Meanwhile, you can choose only use the diver retriever model and it's an embedding model.