Downloads · 30 days
10
19% of all-time downloads
dhruvv45/lightretriever-qwen2.5-1.5b-nq-20k
lightretriever-qwen2.5-1.5b-nq-20k is a machine learning model from dhruvv45. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
This repository contains a LoRA adapter obtained by fine-tuning Qwen/Qwen2.5-1.5B using the LightRetriever framework for neural information retrieval.
Downloads · 30 days
10
19% of all-time downloads
All-time downloads
52
Public
Repo size
85.3 MB
Likes
2
Public
Click a slice to open those files.
.safetensors73.9 MB · 82%
From the Hugging Face model README
This repository contains a LoRA adapter obtained by fine-tuning Qwen/Qwen2.5-1.5B using the LightRetriever framework for neural information retrieval.
The adapter was trained on a 20k subset of the Natural Questions (NQ) training dataset.
Base Model: Qwen/Qwen2.5-1.5B
Training Framework: LightRetriever
Fine-tuning Method: LoRA (PEFT)
Qwen/Qwen2.5-1.5BThis repository contains:
adapter_model.safetensors)It does not contain the original Qwen model weights.
Load the base model first and then apply this LoRA adapter using PEFT.
Example:
from transformers import AutoModel
from peft import PeftModel
base_model = AutoModel.from_pretrained("Qwen/Qwen2.5-1.5B")
model = PeftModel.from_pretrained(
base_model,
"dhruvv45/lightretriever-qwen2.5-1.5b-nq-20k"
)
Training has been completed.
Evaluation on BEIR/MTEB benchmarks is currently in progress.
This repository contains only the LoRA adapter.
The original Qwen2.5-1.5B model must be downloaded separately from Hugging Face.
Dhruv Agarwal
B.Tech CSE, IIIT Nagpur
Research Intern, IIT Bombay