distilabel

distilabel copied to clipboard

## Which page or section is this issue related to? There is no clear guide on customizing tasks and prompt templates ## What are you documenting, or what change are...

davidberenstein1957

[BUG] Input data size != output data size when task batch size < batch size of predecessor

3

**Describe the bug** The behavior is a bit random. **When the text generation input size < batch size from the previous step** and replica > 1. The final output could...

zye1996

**Is your feature request related to a problem? Please describe.** It would be cool to be able to label argilla records with Distilabel/LLMs. **Describe the solution you'd like** ``` from...

davidberenstein1957

**Describe the bug** docs/sections/how_to_guides/basic/task/generator_task.md should have imported from distilabel.steps.typing import GeneratorStepOutput but instead imported from distilabel.steps.typing import GeneratorOutput That's it! :)

arthrod

[FEATURE] add dedicated `set_runtime_parameters` to `Task`, `Step` and `LLM`

3

**Is your feature request related to a problem? Please describe.** Currently, it can be difficult to grasp and combine all of the runtime parameters for each component. **Describe the solution...

davidberenstein1957

## Which page or section is this issue related to? ## What are you documenting, or what change are you making in the documentation? We could add description and title...

davidberenstein1957

[BUG] Develop branch hung when using replica > 2

3

**Describe the bug** I installed latest develop branch and run basic generation with StepResources(replica=8) and the generation hung. It does not happen to tags 88615c72182249203463401ec2f767e58ac84d9c **To Reproduce** Code to reproduce...

zye1996

[BUG] ValueError raised in write_buffer.py when pyarrow.Table.cast is called

1

When running my pipeline is seem to be getting this error: ``` Traceback (most recent call last): File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner self.run() File "/usr/lib/python3.10/threading.py", line 953, in run...

afolabiaji

**Is your feature request related to a problem? Please describe.** Arcee.ai in it's blog for the [supernova](https://blog.arcee.ai/meet-arcee-supernova-our-flagship-70b-model-alternative-to-openai/) model mentions their [EvolKit](https://github.com/arcee-ai/EvolKit?ref=blog.arcee.ai) framework to generate synthetic data. It builds on this...

plaguss

**Is your feature request related to a problem? Please describe.** #816 **Describe the solution you'd like** A clear and concise description of what you want to happen. **Describe alternatives you've...

davidberenstein1957