Cupidon-mini-ro-i1-GGUF Open Source Model - Free Deployment for Romanian Text Tasks

Cupidon Mini Ro I1 GGUF

Developed by mradermacher

This is a weighted/imatrix quantized version of BlackKakapo/cupidon-mini-ro, suitable for Romanian text processing tasks.

Text Embedding OtherOpen Source License:Apache-2.0 #Romanian sentence embedding #lightweight quantization #sentence similarity calculation

Downloads 546

Release Time : 4/3/2025

Model Overview

This model is a quantized version based on BlackKakapo/cupidon-mini-ro, primarily used for tasks such as sentence embedding, feature extraction, and sentence similarity calculation.

Model Features

Multiple quantization versions

Offers various quantization versions from IQ1 to Q6_K to meet different scenario requirements

Efficient inference

The quantized model has a small size and fast inference speed, suitable for resource-constrained environments

Romanian language optimization

Specifically optimized for Romanian text processing tasks

Model Capabilities

sentence embedding

feature extraction

sentence similarity calculation

text representation learning

Use Cases

text similarity

document retrieval

Calculate the similarity between queries and texts in a document library

duplicate detection

Identify text passages with similar content

semantic analysis

semantic search

Search system based on semantics rather than keywords

base_model: BlackKakapo/cupidon-mini-ro datasets:

BlackKakapo/RoSTSC language:
ro library_name: transformers license: apache-2.0 quantized_by: mradermacher tags:
sentence-transformers
feature-extraction
sentence-similarity
transformers

About

weighted/imatrix quants of https://huggingface.co/BlackKakapo/cupidon-mini-ro

static quants are available at https://huggingface.co/mradermacher/cupidon-mini-ro-GGUF

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Link	Type	Size/GB	Notes
GGUF	i1-IQ1_S	0.1	for the desperate
GGUF	i1-IQ1_M	0.1	mostly desperate
GGUF	i1-IQ2_XXS	0.1
GGUF	i1-IQ2_S	0.1
GGUF	i1-IQ2_XS	0.1
GGUF	i1-IQ2_M	0.1
GGUF	i1-Q2_K_S	0.1	very low quality
GGUF	i1-IQ3_XXS	0.1	lower quality
GGUF	i1-IQ3_S	0.1	beats Q3_K*
GGUF	i1-IQ3_XS	0.1
GGUF	i1-Q2_K	0.1	IQ3_XXS probably better
GGUF	i1-Q3_K_S	0.1	IQ3_XS probably better
GGUF	i1-IQ3_M	0.1
GGUF	i1-IQ4_XS	0.1
GGUF	i1-IQ4_NL	0.1	prefer IQ4_XS
GGUF	i1-Q4_0	0.1	fast, low quality
GGUF	i1-Q3_K_M	0.1	IQ3_S probably better
GGUF	i1-Q4_1	0.1
GGUF	i1-Q3_K_L	0.1	IQ3_M probably better
GGUF	i1-Q4_K_S	0.1	optimal size/speed/quality
GGUF	i1-Q4_K_M	0.1	fast, recommended
GGUF	i1-Q5_K_S	0.1
GGUF	i1-Q5_K_M	0.1
GGUF	i1-Q6_K	0.1	practically like static Q6_K

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.

Thanks

I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご