AutoPrompt

AutoPrompt copied to clipboard

At least one label specified must be in y_true

1

Hi, with the latest changes I got a new error when run `run_generation_pipeline.py` ``` Traceback (most recent call last): File "path_to_repo/AutoPrompt/run_generation_pipeline_alena.py", line 64, in best_prompt = ranker_pipeline.run_pipeline(opt.num_ranker_steps) File "path_to_repo/AutoPrompt/optimization_pipeline.py", line...

alena-m

[pipenv](https://pipenv.pypa.io/) is a modern, easy tool to manage python versions and dependencies, including virtual environments. This PR adds support for pipenv

omerholz

A small problem encountered in the use of

5

 I am getting this error in my usage. My educational background is not in computers and my programming foundation is weak, so I hope the reply is easy to...

runningZ1

KeyError: 'samples'

3

Output of the sample_batches **doesn't have the sample keys** ``` samples_list = [ element for sublist in samples_batches for element in sublist["samples"] ] ``` Reference: https://github.com/Eladlev/AutoPrompt/blob/c640cc0108e78601b474b380462a1a6274318fcc/optimization_pipeline.py#L192C25-L192C32

alibabadoufu

Dumped dataset should contain predictions

1

Hi! Great tool. When I run the code with an initial dataset, the synthetic datarows get added to the dumped dataset, but I think it would be great to also...

billy-mosse

Is there support for local LLM?

10

Is there any plan to support local offline models?

17Reset

Calibrated prompt generated is completely different from initial prompt.

3

I have a prompt which is used to generate sql query from the input text given by a user. I am trying to optimize prompt using run_generation_pipeline.py, but I am...

shobhnadhami

Enable output parser for models not support json schema.

1

Currently, not all output_schemas support customized output parsers. For example in the [classification output schemes](https://github.com/Eladlev/AutoPrompt/blob/main/prompts/meta_prompts_classification/output_schemes.py), only json schemas are available, meaning this prompt only works well for the models which...

vincilee2

How to support Qwen?

1

**config/config_default.yml** llm: type: 'HuggingFacePipeline' name: 'Qwen-14B-Chat' max_new_tokens: 4096 cammand: > python run_pipeline.py \ --prompt "Does this movie review contain a spoiler? answer Yes or No" \ --task_description "Assistant is an...

uana777

load dataset relative with prompt

1

 can i load data in this place rather than argilla。

cainiaogoroad