Tasks Gallery¶
-
ComplexityScorer
Score instructions based on their complexity using an
LLM
. -
EvolInstruct
Evolve instructions using an
LLM
. -
EvolComplexity
Evolve instructions to make them more complex using an
LLM
. -
EvolQuality
Evolve the quality of the responses using an
LLM
. -
Genstruct
Generate a pair of instruction-response from a document using an
LLM
. -
GenerateTextRetrievalData
Generate text retrieval data with an
LLM
to later on train an embedding model. -
GenerateShortTextMatchingData
Generate short text matching data with an
LLM
to later on train an embedding model. -
GenerateLongTextMatchingData
Generate long text matching data with an
LLM
to later on train an embedding model. -
GenerateTextClassificationData
Generate text classification data with an
LLM
to later on train an embedding model. -
InstructionBacktranslation
Self-Alignment with Instruction Backtranslation.
-
PrometheusEval
Critique and rank the quality of generations from an
LLM
using Prometheus 2.0. -
QualityScorer
Score responses based on their quality using an
LLM
. -
SelfInstruct
Generate instructions based on a given input using an
LLM
. -
GenerateSentencePair
Generate a positive and negative (optionally) sentences given an anchor sentence.
-
StructuredGeneration
Generate structured content for a given
instruction
using anLLM
. -
TextGeneration
Simple text generation with an
LLM
given an instruction. -
ChatGeneration
Generates text based on a conversation.
-
UltraFeedback
Rank generations focusing on different aspects using an
LLM
. -
EvolInstructGenerator
Generate evolved instructions using an
LLM
. -
EvolComplexityGenerator
Generate evolved instructions with increased complexity using an
LLM
. -
MonolingualTripletGenerator
Generate monolingual triplets with an
LLM
to later on train an embedding model. -
BitextRetrievalGenerator
Generate bitext retrieval data with an
LLM
to later on train an embedding model. -
EmbeddingTaskGenerator
Generate task descriptions for embedding-related tasks using an
LLM
. -
PairRM
Rank the candidates based on the input using the
LLM
model. -
GenerateEmbeddings
Generate embeddings using the last hidden state of an
LLM
.