distilabel
distilabel copied to clipboard
Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.
[FEATURE] Allow `FormatTextGenerationSFT` to include tools/function calls in the formatted messages.
**Is your feature request related to a problem? Please describe.** With the new `StructuredGeneration` task we can generate datasets for function calling, and we could simplify preparing the dataset for...
## Description When generating a name for the pipeline automatically we were doing it with a random generator, which prevents the cache from working. This changes the behaviour to be...
## Description Update the `LLM.generate` function signature to allow returning more stuff related to the generation apart from the completion given by the LLM. This would be useful to include...
## Description This PR adds a new mixin that contains the `_create_signature` method for the pipeline, and adds a new attribute named `exclude_from_signature` which consists of a `set` of strings...
Closes #836 Closes #839
**Is your feature request related to a problem? Please describe.** In https://github.com/argilla-io/distilabel/pull/760 the logic to load the steps in stages was added. Currently, load stages are defined by the position...
## Which page or section is this issue related to? An addaptation of https://docs.zenml.io/user-guide/llmops-guide/finetuning-embeddings/finetuning-embeddings-with-sentence-transformers ## What are you documenting, or what change are you making in the documentation? NA
**Is your feature request related to a problem? Please describe.** Currently, we don't have all the attribute from vllm `SamplingParams` in the `vLLM.generate` method. What we do instead is to...
## Which page or section is this issue related to? https://mkdocstrings.github.io/python/usage/configuration/headings/#show_symbol_type_heading I'll also small reviews if found while working with the tutorials ## What are you documenting, or what change...
**Is your feature request related to a problem? Please describe.** As all the attributes of an `Step` are used to compute the signature of the pipeline, changing one attribute that...