Lightblue_-_reranker_0.5_bincont_filt-gguf Open-Source Text Ranking Model

Lightblue Reranker 0.5 Bincont Filt Gguf

Developed by RichardErkhov

This is a text ranking model used for sorting text by relevance.

Text Embedding #Text Ranking #Lightweight Model #Multiple Quantization Versions

Downloads 2,054

Release Time : 3/14/2025

Model Overview

This model is primarily designed for text ranking tasks, capable of sorting input text based on relevance.

Model Features

Multiple Quantization Versions

Offers various quantization versions from Q2_K to Q8_0 to meet different hardware and performance needs.

Efficient Ranking

Specialized in text ranking tasks, capable of efficiently sorting text by relevance.

Model Capabilities

Text Ranking

Relevance Scoring

Use Cases

Information Retrieval

Search Engine Result Ranking

Sorts search engine results by relevance to enhance user experience.

Recommendation Systems

Content Recommendation Ranking

Ranks recommended content to prioritize the most relevant items.

🚀 reranker_bincont_filt_train

This project offers a fine - tuned model based on Qwen/Qwen2.5 - 0.5B - Instruct, designed for text ranking tasks. It provides various quantized versions of the model with different sizes and quantization methods.

🚀 Quick Start

This model is a fine - tuned version of Qwen/Qwen2.5-0.5B-Instruct on the reranker_bincont_filt_train dataset. It achieves a loss of 0.1613 on the evaluation set.

✨ Features

Multiple quantized versions of the model are available, offering different trade - offs between size and performance.
Fine - tuned on a specific dataset for text ranking tasks.

📦 Installation

No installation steps are provided in the original document.

📚 Documentation

Model Information

Pipeline Tag: text - ranking
Quantization: Made by Richard Erkhov
Links:

Quantized Model Details

Name	Quant method	Size
reranker_0.5_bincont_filt.Q2_K.gguf	Q2_K	0.39GB
reranker_0.5_bincont_filt.IQ3_XS.gguf	IQ3_XS	0.39GB
reranker_0.5_bincont_filt.IQ3_S.gguf	IQ3_S	0.39GB
reranker_0.5_bincont_filt.Q3_K_S.gguf	Q3_K_S	0.39GB
reranker_0.5_bincont_filt.IQ3_M.gguf	IQ3_M	0.39GB
reranker_0.5_bincont_filt.Q3_K.gguf	Q3_K	0.4GB
reranker_0.5_bincont_filt.Q3_K_M.gguf	Q3_K_M	0.4GB
reranker_0.5_bincont_filt.Q3_K_L.gguf	Q3_K_L	0.42GB
reranker_0.5_bincont_filt.IQ4_XS.gguf	IQ4_XS	0.4GB
reranker_0.5_bincont_filt.Q4_0.gguf	Q4_0	0.4GB
reranker_0.5_bincont_filt.IQ4_NL.gguf	IQ4_NL	0.4GB
reranker_0.5_bincont_filt.Q4_K_S.gguf	Q4_K_S	0.45GB
reranker_0.5_bincont_filt.Q4_K.gguf	Q4_K	0.46GB
reranker_0.5_bincont_filt.Q4_K_M.gguf	Q4_K_M	0.46GB
reranker_0.5_bincont_filt.Q4_1.gguf	Q4_1	0.43GB
reranker_0.5_bincont_filt.Q5_0.gguf	Q5_0	0.46GB
reranker_0.5_bincont_filt.Q5_K_S.gguf	Q5_K_S	0.48GB
reranker_0.5_bincont_filt.Q5_K.gguf	Q5_K	0.49GB
reranker_0.5_bincont_filt.Q5_K_M.gguf	Q5_K_M	0.49GB
reranker_0.5_bincont_filt.Q5_1.gguf	Q5_1	0.49GB
reranker_0.5_bincont_filt.Q6_K.gguf	Q6_K	0.61GB
reranker_0.5_bincont_filt.Q8_0.gguf	Q8_0	0.63GB

Original Model Details

Model Creator: https://huggingface.co/lightblue/
Original Model: https://huggingface.co/lightblue/reranker_0.5_bincont_filt/

Model Description

This model is a fine - tuned version of Qwen/Qwen2.5-0.5B-Instruct on the reranker_bincont_filt_train dataset.

Training and Evaluation

Training Hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e - 05
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi - GPU
num_devices: 8
total_train_batch_size: 8
total_eval_batch_size: 8
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon = 1e - 08 and optimizer_args = No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.01
num_epochs: 1.0

Training Results

Training Loss	Epoch	Step	Validation Loss
0.209	0.1000	3952	0.2207
0.1541	0.2000	7904	0.2108
0.1519	0.3000	11856	0.2030
0.3499	0.4000	15808	0.1939
0.1045	0.5000	19760	0.1834
0.1887	0.6000	23712	0.1770
0.2182	0.7001	27664	0.1695
0.1281	0.8001	31616	0.1645
0.1463	0.9001	35568	0.1617

Framework Versions

Transformers 4.46.1
Pytorch 2.4.0+cu121
Datasets 3.1.0
Tokenizers 0.20.3

🔧 Technical Details

The model is fine - tuned based on the Qwen/Qwen2.5-0.5B-Instruct model. During training, a set of specific hyperparameters were used, and the training was conducted on a multi - GPU environment. The learning rate scheduler is of cosine type with a warm - up ratio of 0.01.