distilabel

distilabel copied to clipboard

## Description In `distilabel` v1.0.0 we included the task `TextGeneration` and at the last moment we decided to include support for an already formatted chat like object i.e. a list...

alvarobartt

**Is your feature request related to a problem? Please describe.** The implementation of the structured outputs in #601 only allows for a single structure (json schema, `BaseModel` in case of...

plaguss

Add `python==3.12`

2

gabrielmbmb

## Description Provide a `distilabel` docker image that can be used to execute a pipeline within. This is useful for executing `distilabel` pipelines on Cloud providers with serverless solutions. It...

gabrielmbmb

how to use mistral api ?

2

just wanted to know how to use mistral api,, im a newbiw

CryptoMaN-Rahul

[FEATURE] Allow passing path to YAML file containing pipeline runtime parameters in `distilabel run`

3

**Is your feature request related to a problem? Please describe.** Providing runtime parameters using option `--param` of `distilabel run` can be cumbersome. **Describe the solution you'd like** Add a `--runtime-parameters-path`...

gabrielmbmb

Add tutorial - generate data for training embeddings and reranking models

5

Closes #890 

davidberenstein1957

[BUG] Ultrafeedback pipeline don't work

8

**Describe the bug** I want to use Ultrafeedback task in a pipeline, but i have already the dataset, so the pipeline include only loading the dataset and after pass it...

riccardo-unipg

Add cache at `Step` level

2

## Description This PR implements cache at step level. Previously, we computed a signature for a pipeline, and when this signature changed, we recomputed everything. Now the idea is to...

plaguss

`FormatTextGenerationSFT` with function calling

1

## Description ⚠️ Work in progress This PR improves the `FormatTextGenerationSFT` task to allow preparing fine tuning datasets with function calling.

plaguss