Downloads · 30 days
194
22% of all-time downloads
luluw/bge-reranker-v2-m3-eng-nep-16k-trimmed-GGUF
bge-reranker-v2-m3-eng-nep-16k-trimmed-GGUF is a text classification model from luluw. Use it when you need a label for a piece of text. It is set up for sentence-transformers. The card lists the license as apache-2.0.
Model Card: bge-reranker-v2-m3-eng-nep-16k-trimmed-GGUF
Downloads · 30 days
194
22% of all-time downloads
All-time downloads
900
Public
Repo size
4.2 GB
Likes
0
Public
Click a slice to open those files.
.gguf2.1 GB · 100%
From the Hugging Face model README
Model Card: bge-reranker-v2-m3-eng-nep-16k-trimmed-GGUF
This model card documents the GGUF conversions of the vocabulary-trimmed model luluw/bge-reranker-v2-m3-eng-nep-16k-trimmed.
bge-reranker-v2-m3-eng-nep-16k-trimmed-GGUFluluw/bge-reranker-v2-m3-eng-nep-16k-trimmedBAAI/bge-reranker-v2-m3(query, passage) pair)| Metric | Original | Trimmed |
|---|---|---|
| Vocab size (tokenizer) | 250,002 | 16,384 |
Model config vocab_size | 250,002 | 16,384 |
Model config num_labels | 1 | 1 |
| Max position embeddings | 8,194 | 8,194 (unchanged) |
| Embedding parameters | 256,002,048 | 16,777,216 |
| Total parameters | 567,755,777 | 328,530,945 |
| Parameters saved | — | 239,224,832 (42.1% smaller) |
How the vocabulary was trimmed:
lbourdois/fineweb-2-trimming).old_id → new_id mapping (vocab_mapping.json) is provided so the original XLM-R tokenizer can still be used for subword splitting.| Filename | Quant type | File Size | Description |
|---|---|---|---|
bge-reranker-v2-m3-eng-nep-16k-trimmed-fp16.gguf | FP16 | ~644 MB | Full precision (FP16) |
bge-reranker-v2-m3-eng-nep-16k-trimmed-Q8_0.gguf | Q8_0 | ~358 MB | 8-bit quantization |
bge-reranker-v2-m3-eng-nep-16k-trimmed-Q6_K.gguf | Q6_K | ~284 MB | 6-bit K-quantization |
bge-reranker-v2-m3-eng-nep-16k-trimmed-Q5_K_M.gguf | Q5_K_M | ~254 MB | 5-bit K-quantization (medium) |
bge-reranker-v2-m3-eng-nep-16k-trimmed-Q5_K_S.gguf | Q5_K_S | ~246 MB | 5-bit K-quantization (small) |
bge-reranker-v2-m3-eng-nep-16k-trimmed-Q4_K_M.gguf | Q4_K_M | ~225 MB | 4-bit K-quantization (medium) |
llama.cpp (or compatible backends that support XLM-RoBERTa / cross-encoder models).old_to_new mapping when converting token IDs. Do not feed raw original tokenizer IDs directly into the trimmed model.<s> query </s></s> passage </s>.<unk>.The original model is licensed under the MIT License. All converted GGUF files inherit the same license.
@misc{bge_m3,
title={BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation},
author={Chen, Jianlv and Xiao, Shitao and Zhang, Peitian and Luo, Kun and Lian, Defu and Liu, Zheng},
year={2024},
eprint={2402.03216},
archivePrefix={arXiv},
primaryClass={cs.CL}
}