CoolFace
Modelpublic

a1Kingleo/SmallLanguageModelCollection

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes
Model Card

Small Language Models Collection

Below is a list of small language models suitable for various tasks:

Model NameTask/CapabilityHugging Face Link
BERT BaseGeneral Text Classificationhttps://huggingface.co/bert-base-uncased
DistilBERTEfficient Text Classificationhttps://huggingface.co/distilbert-base-uncased
RoBERTa BaseAdvanced Text Classificationhttps://huggingface.co/roberta-base
ALBERT BaseEfficient Large-Scale Classificationhttps://huggingface.co/albert-base-v2
T5 SmallText-to-Text Generationhttps://huggingface.co/t5-small
T5 BaseGeneral Text-to-Text Taskshttps://huggingface.co/t5-base
T5 LargeAdvanced Text-to-Text Generationhttps://huggingface.co/t5-large
Longformer BaseLong-Sequence Text Processinghttps://huggingface.co/longformer-base-4096
BigBird BaseLong-Sequence Text Processinghttps://huggingface.co/google/bigbird-base-4096
Reformer BaseEfficient Long-Sequence Processinghttps://huggingface.co/google/reformer-enwik8
BART BaseText Summarization and Generationhttps://huggingface.co/facebook/bart-base
ProphetNet BaseFuture Event Predictionhttps://huggingface.co/microsoft/prophetnet-large-nli
PPLM BaseControlled Text Generationhttps://huggingface.co/decapoda-research/llama-7b-hf (Note: PPLM is not directly available; this link is for a similar model)
DeBERTa BaseAdvanced Sentiment Analysishttps://huggingface.co/microsoft/deberta-base
DeBERTa LargeHigh-Accuracy Sentiment Analysishttps://huggingface.co/microsoft/deberta-large
XLM-R BaseMultilingual Text Classificationhttps://huggingface.co/xlm-r-100-base
XLM-R LargeAdvanced Multilingual Taskshttps://huggingface.co/xlm-r-100-large
MarianMTMachine Translationhttps://huggingface.co/Helsinki-NLP/opus-mt-en-fr
CamemBERTFrench Language Taskshttps://huggingface.co/camembert-base
FlauBERTFrench Language Taskshttps://huggingface.co/flaubert/flaubert-base-uncased
DistilCamemBERTEfficient French Taskshttps://huggingface.co/camembert/camembert-base (Note: DistilCamemBERT is not directly available; this link is for CamemBERT)
BART LargeAdvanced Text Summarizationhttps://huggingface.co/facebook/bart-large
ProphetNet LargeAdvanced Future Event Predictionhttps://huggingface.co/microsoft/prophetnet-large-nli
T5 3BLarge-Scale Text-to-Text Generationhttps://huggingface.co/t5-3b
T5 11BHigh-Capacity Text-to-Text Generationhttps://huggingface.co/t5-11b
LLaMA 7BLarge-Scale General Taskshttps://huggingface.co/decapoda-research/llama-7b-hf
LLaMA 13BHigh-Capacity General Taskshttps://huggingface.co/decapoda-research/llama-13b-hf
OPT 175BVery Large-Scale General Taskshttps://huggingface.co/facebook/opt-175b
OPT 2.7BLarge-Scale General Taskshttps://huggingface.co/facebook/opt-2.7b
OPT 6.7BHigh-Capacity General Taskshttps://huggingface.co/facebook/opt-6.7b
OPT 13BAdvanced General Taskshttps://huggingface.co/facebook/opt-13b