Guille Pérez-Torró
guishe
AI & ML interests
Information Retrieval, Few-Shot Learning, Named Entity Recognition, Named Entity Disambiguation, Semantic Search, Aspect-based Sentiment Analysis
Recent Activity
updated a collection 20 days ago
Decision Models updated a collection 20 days ago
Decision Models liked a model 20 days ago
fastino/GLiNER2.5-DecideOrganizations
Multi-Vector Embedding Models
LLM-as-a-Judge
-
AtlaAI/Selene-1-Mini-Llama-3.1-8B
Text Generation • 8B • Updated • 4.85k • • 108 -
AtlaAI/Selene-1-Mini-Llama-3.1-8B-Q4_K_M-GGUF
Text Generation • 8B • Updated • 155 • 8 -
flowaicom/Flow-Judge-v0.1
Text Generation • 4B • Updated • 1.04k • 73 -
prometheus-eval/prometheus-7b-v2.0
Text Generation • 7B • Updated • 18.9k • • 109
Zero-Shot Entailment Models
-
MoritzLaurer/bge-m3-zeroshot-v2.0
Zero-Shot Classification • 0.6B • Updated • 113k • • 70 -
MoritzLaurer/deberta-v3-large-zeroshot-v2.0
Zero-Shot Classification • 0.4B • Updated • 150k • • 145 -
MoritzLaurer/ModernBERT-base-zeroshot-v2.0
Text Classification • 0.1B • Updated • 5.19k • • 19 -
MoritzLaurer/ModernBERT-large-zeroshot-v2.0
Text Classification • 0.4B • Updated • 16.2k • • 76
NER Encoder-only Models
This collections gathers several NER models. Either fine-tuned versions for specific tasks or generic backbone models ready to be fine-tuned.
-
guishe/nuner-v1_orgs
Token Classification • 0.1B • Updated • 490 • 2 -
guishe/span-marker-generic-ner-v1-fewnerd-fine-super
Token Classification • 0.1B • Updated • 6.66k • 13 -
protectai/guishe-nuner-v1_orgs-onnx
Token Classification • Updated • 290 -
guishe/nuner-v1_fewnerd_fine_super
Token Classification • 0.1B • Updated • 20
Small LLMs
-
microsoft/Phi-3-mini-4k-instruct
Text Generation • 4B • Updated • 371k • • 1.48k -
google/gemma-2-2b-it
Text Generation • 3B • Updated • 403k • • 1.58k -
nvidia/Nemotron-Mini-4B-Instruct
Text Generation • Updated • 36.9k • 190 -
HuggingFaceTB/SmolLM2-360M-Instruct
Text Generation • 0.4B • Updated • 234k • 229
Part-of-Speech Tagging
papers_ESG
-
Enhancing Retrieval for ESGLLM via ESG-CID -- A Disclosure Content Index Finetuning Dataset for Mapping GRI and ESRS
Paper • 2503.10674 • Published • 3 -
ESGenius: Benchmarking LLMs on Environmental, Social, and Governance (ESG) and Sustainability Knowledge
Paper • 2506.01646 • Published • 2 -
Statements: Universal Information Extraction from Tables with Large Language Models for ESG KPIs
Paper • 2406.19102 • Published • 1 -
Improving Retrieval for RAG based Question Answering Models on Financial Documents
Paper • 2404.07221 • Published
Multimodal Embeddings
Reasoning LLMs
ReRanker Encoder-only Models
-
jinaai/jina-reranker-v2-base-multilingual
Text Ranking • 0.3B • Updated • 1.01M • 364 -
BAAI/bge-reranker-v2-m3
Text Classification • 0.6B • Updated • 15.9M • • 1.26k -
mixedbread-ai/mxbai-rerank-base-v1
Text Ranking • 0.2B • Updated • 41.5k • • 47 -
mixedbread-ai/mxbai-rerank-large-v1
Text Ranking • 0.4B • Updated • 48.6k • • 144
Embedding Encoder-only Models
-
BAAI/bge-m3
Sentence Similarity • Updated • 32.5M • • 3.89k -
BAAI/bge-large-en-v1.5
Feature Extraction • 0.3B • Updated • 10.1M • • 773 -
nomic-ai/nomic-embed-text-v1.5
Sentence Similarity • 0.1B • Updated • 13.1M • 977 -
mixedbread-ai/mxbai-embed-large-v1
Feature Extraction • 0.3B • Updated • 1.96M • • 839
Summarization
-
Falconsai/text_summarization
Summarization • 60.5M • Updated • 9.8k • • 325 -
knkarthick/MEETING-SUMMARY-BART-LARGE-XSUM-SAMSUM-DIALOGSUM
Summarization • 0.4B • Updated • 154 • 13 -
knkarthick/MEETING-SUMMARY-BART-LARGE-XSUM-SAMSUM-DIALOGSUM-AMI
Summarization • 0.4B • Updated • 78 • 17 -
BEE-spoke-data/pegasus-x-base-synthsumm_open-16k
Summarization • 0.3B • Updated • 102 • 3
Instruct LLMs
-
instruction-pretrain/finance-Llama3-8B
Text Generation • 8B • Updated • 580 • • 83 -
EmergentMethods/Phi-3-mini-4k-instruct-graph
Text Generation • 4B • Updated • 2 • 49 -
nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
Text Generation • 71B • Updated • 24.2k • • 2.07k -
unsloth/Llama-3.2-3B-Instruct-unsloth-bnb-4bit
Text Generation • 3B • Updated • 46.2k • 10
Decision Models
papers_ESG
-
Enhancing Retrieval for ESGLLM via ESG-CID -- A Disclosure Content Index Finetuning Dataset for Mapping GRI and ESRS
Paper • 2503.10674 • Published • 3 -
ESGenius: Benchmarking LLMs on Environmental, Social, and Governance (ESG) and Sustainability Knowledge
Paper • 2506.01646 • Published • 2 -
Statements: Universal Information Extraction from Tables with Large Language Models for ESG KPIs
Paper • 2406.19102 • Published • 1 -
Improving Retrieval for RAG based Question Answering Models on Financial Documents
Paper • 2404.07221 • Published
Multi-Vector Embedding Models
Multimodal Embeddings
LLM-as-a-Judge
-
AtlaAI/Selene-1-Mini-Llama-3.1-8B
Text Generation • 8B • Updated • 4.85k • • 108 -
AtlaAI/Selene-1-Mini-Llama-3.1-8B-Q4_K_M-GGUF
Text Generation • 8B • Updated • 155 • 8 -
flowaicom/Flow-Judge-v0.1
Text Generation • 4B • Updated • 1.04k • 73 -
prometheus-eval/prometheus-7b-v2.0
Text Generation • 7B • Updated • 18.9k • • 109
Reasoning LLMs
Zero-Shot Entailment Models
-
MoritzLaurer/bge-m3-zeroshot-v2.0
Zero-Shot Classification • 0.6B • Updated • 113k • • 70 -
MoritzLaurer/deberta-v3-large-zeroshot-v2.0
Zero-Shot Classification • 0.4B • Updated • 150k • • 145 -
MoritzLaurer/ModernBERT-base-zeroshot-v2.0
Text Classification • 0.1B • Updated • 5.19k • • 19 -
MoritzLaurer/ModernBERT-large-zeroshot-v2.0
Text Classification • 0.4B • Updated • 16.2k • • 76
ReRanker Encoder-only Models
-
jinaai/jina-reranker-v2-base-multilingual
Text Ranking • 0.3B • Updated • 1.01M • 364 -
BAAI/bge-reranker-v2-m3
Text Classification • 0.6B • Updated • 15.9M • • 1.26k -
mixedbread-ai/mxbai-rerank-base-v1
Text Ranking • 0.2B • Updated • 41.5k • • 47 -
mixedbread-ai/mxbai-rerank-large-v1
Text Ranking • 0.4B • Updated • 48.6k • • 144
NER Encoder-only Models
This collections gathers several NER models. Either fine-tuned versions for specific tasks or generic backbone models ready to be fine-tuned.
-
guishe/nuner-v1_orgs
Token Classification • 0.1B • Updated • 490 • 2 -
guishe/span-marker-generic-ner-v1-fewnerd-fine-super
Token Classification • 0.1B • Updated • 6.66k • 13 -
protectai/guishe-nuner-v1_orgs-onnx
Token Classification • Updated • 290 -
guishe/nuner-v1_fewnerd_fine_super
Token Classification • 0.1B • Updated • 20
Embedding Encoder-only Models
-
BAAI/bge-m3
Sentence Similarity • Updated • 32.5M • • 3.89k -
BAAI/bge-large-en-v1.5
Feature Extraction • 0.3B • Updated • 10.1M • • 773 -
nomic-ai/nomic-embed-text-v1.5
Sentence Similarity • 0.1B • Updated • 13.1M • 977 -
mixedbread-ai/mxbai-embed-large-v1
Feature Extraction • 0.3B • Updated • 1.96M • • 839
Small LLMs
-
microsoft/Phi-3-mini-4k-instruct
Text Generation • 4B • Updated • 371k • • 1.48k -
google/gemma-2-2b-it
Text Generation • 3B • Updated • 403k • • 1.58k -
nvidia/Nemotron-Mini-4B-Instruct
Text Generation • Updated • 36.9k • 190 -
HuggingFaceTB/SmolLM2-360M-Instruct
Text Generation • 0.4B • Updated • 234k • 229
Summarization
-
Falconsai/text_summarization
Summarization • 60.5M • Updated • 9.8k • • 325 -
knkarthick/MEETING-SUMMARY-BART-LARGE-XSUM-SAMSUM-DIALOGSUM
Summarization • 0.4B • Updated • 154 • 13 -
knkarthick/MEETING-SUMMARY-BART-LARGE-XSUM-SAMSUM-DIALOGSUM-AMI
Summarization • 0.4B • Updated • 78 • 17 -
BEE-spoke-data/pegasus-x-base-synthsumm_open-16k
Summarization • 0.3B • Updated • 102 • 3
Part-of-Speech Tagging
Instruct LLMs
-
instruction-pretrain/finance-Llama3-8B
Text Generation • 8B • Updated • 580 • • 83 -
EmergentMethods/Phi-3-mini-4k-instruct-graph
Text Generation • 4B • Updated • 2 • 49 -
nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
Text Generation • 71B • Updated • 24.2k • • 2.07k -
unsloth/Llama-3.2-3B-Instruct-unsloth-bnb-4bit
Text Generation • 3B • Updated • 46.2k • 10