A collection of 3 nano BERT models fine-tuned for prompt injection detection. Recommended for fast inference and/or edge devices
Manuel Romero PRO
mrm8488
AI & ML interests
#AI Research and Democratization. NLP/NLG π€
Recent Activity
liked
a model
3 days ago
Finerio-Cortex/cortex-wernicke-transact
upvoted
an
article
3 days ago
We Got Claude to Fine-Tune an Open Source LLM
upvoted
a
collection
4 days ago
Nemotron RAG
Organizations
-
mrm8488/ModernBERT-base-ft-fineweb-edu-annotations-8k
Text Classification β’ 0.1B β’ Updated β’ 10 -
mrm8488/ModernBERT-base-ft-fineweb-edu-annotations
Text Classification β’ 0.1B β’ Updated β’ 12 β’ 11 -
mrm8488/ModernBERT-large-ft-fineweb-edu-annotations-4k
Text Classification β’ 0.1B β’ Updated β’ 10 β’ 1
Financial Sentiment Analysis models I created
-
mrm8488/distilroberta-finetuned-financial-news-sentiment-analysis
Text Classification β’ 82.1M β’ Updated β’ 316k β’ β’ 426 -
mrm8488/deberta-v3-ft-financial-news-sentiment-analysis
Text Classification β’ 0.1B β’ Updated β’ 12.7k β’ β’ 28 -
mrm8488/ModernBERT-base-ft-financial-news-sentiment-analysis
Text Classification β’ 0.1B β’ Updated β’ 186 β’ 1
A collection of SoTA embeddings model fine-tuned on WebInstruct dataset to learn to pair instructions with its responses
-
mrm8488/multilingual-e5-large-instruct-es-trim-30k
Feature Extraction β’ 0.3B β’ Updated β’ 3 -
mrm8488/multilingual-e5-small-es-trim-32k
Feature Extraction β’ 34.2M β’ Updated β’ 6 -
mrm8488/multilingual-e5-small-es-trim-16k
Feature Extraction β’ 27.9M β’ Updated β’ 6 -
mrm8488/multilingual-e5-large-instruct-es-trim-16k
Feature Extraction β’ 0.3B β’ Updated β’ 5
Collection of pre-trained and fine-tuned Spanish Language Models
Collection to track the LLMs I fine-tuned for code generation
A collection with embeddings models I fine-tuned for better performance in Spanish texts.
-
mrm8488/multilingual-e5-large-ft-sts-spanish-matryoshka-768-64-5e
Sentence Similarity β’ 0.6B β’ Updated β’ 101 β’ 2 -
mrm8488/distiluse-base-multilingual-cased-v2-finetuned-stsb_multi_mt-es
Sentence Similarity β’ Updated β’ 253 β’ 3 -
mrm8488/multilingual-e5-large-ft-sts-spanish-matryoshka-768-16-5e
Sentence Similarity β’ 0.6B β’ Updated β’ 266 β’ 5 -
mrm8488/modernbert-embed-base-ft-sts-spanish-matryoshka-768-64
Sentence Similarity β’ 0.1B β’ Updated β’ 246 β’ 3
A collection of 3 nano BERT models fine-tuned for prompt injection detection. Recommended for fast inference and/or edge devices
-
mrm8488/multilingual-e5-large-instruct-es-trim-30k
Feature Extraction β’ 0.3B β’ Updated β’ 3 -
mrm8488/multilingual-e5-small-es-trim-32k
Feature Extraction β’ 34.2M β’ Updated β’ 6 -
mrm8488/multilingual-e5-small-es-trim-16k
Feature Extraction β’ 27.9M β’ Updated β’ 6 -
mrm8488/multilingual-e5-large-instruct-es-trim-16k
Feature Extraction β’ 0.3B β’ Updated β’ 5
-
mrm8488/ModernBERT-base-ft-fineweb-edu-annotations-8k
Text Classification β’ 0.1B β’ Updated β’ 10 -
mrm8488/ModernBERT-base-ft-fineweb-edu-annotations
Text Classification β’ 0.1B β’ Updated β’ 12 β’ 11 -
mrm8488/ModernBERT-large-ft-fineweb-edu-annotations-4k
Text Classification β’ 0.1B β’ Updated β’ 10 β’ 1
Collection of pre-trained and fine-tuned Spanish Language Models
Financial Sentiment Analysis models I created
-
mrm8488/distilroberta-finetuned-financial-news-sentiment-analysis
Text Classification β’ 82.1M β’ Updated β’ 316k β’ β’ 426 -
mrm8488/deberta-v3-ft-financial-news-sentiment-analysis
Text Classification β’ 0.1B β’ Updated β’ 12.7k β’ β’ 28 -
mrm8488/ModernBERT-base-ft-financial-news-sentiment-analysis
Text Classification β’ 0.1B β’ Updated β’ 186 β’ 1
Collection to track the LLMs I fine-tuned for code generation
A collection with embeddings models I fine-tuned for better performance in Spanish texts.
-
mrm8488/multilingual-e5-large-ft-sts-spanish-matryoshka-768-64-5e
Sentence Similarity β’ 0.6B β’ Updated β’ 101 β’ 2 -
mrm8488/distiluse-base-multilingual-cased-v2-finetuned-stsb_multi_mt-es
Sentence Similarity β’ Updated β’ 253 β’ 3 -
mrm8488/multilingual-e5-large-ft-sts-spanish-matryoshka-768-16-5e
Sentence Similarity β’ 0.6B β’ Updated β’ 266 β’ 5 -
mrm8488/modernbert-embed-base-ft-sts-spanish-matryoshka-768-64
Sentence Similarity β’ 0.1B β’ Updated β’ 246 β’ 3
A collection of SoTA embeddings model fine-tuned on WebInstruct dataset to learn to pair instructions with its responses