---
license: apache-2.0
datasets:
- ise-uiuc/Magicoder-Evol-Instruct-110K
- ise-uiuc/Magicoder-OSS-Instruct-75K
- meta-math/MetaMathQA
language:
- en
- pl
base_model:
- speakleash/Bielik-7B-Instruct-v0.1
library_name: peft
pipeline_tag: text-generation
tags:
- Math
- Code
- Adapter
- base_model:adapter:speakleash/Bielik-7B-Instruct-v0.1
- lora
- sft
- transformers
- trl
---

## Bielik-7B-Instruct-v0.1-Math-Code-adapter

An adapter for Bielik 7B Instruct v0.1 trained on English datasets:

https://huggingface.co/datasets/ise-uiuc/Magicoder-Evol-Instruct-110K

https://huggingface.co/datasets/ise-uiuc/Magicoder-OSS-Instruct-75K

https://huggingface.co/datasets/meta-math/MetaMathQA

Base model: https://huggingface.co/speakleash/Bielik-7B-Instruct-v0.1

It might be little overfitted.

It was part of my MoE experiment that I abandoned - I wanted to use this adapter to create one of the experts in a MoE LLM. I decided to publish it because it was already trained and I'd feel bad to waste it.

---

Adapter dla Bielik 7B Instruct v0.1 wytrenowany na anglojęzycznych datasetach:

https://huggingface.co/datasets/ise-uiuc/Magicoder-Evol-Instruct-110K

https://huggingface.co/datasets/ise-uiuc/Magicoder-OSS-Instruct-75K

https://huggingface.co/datasets/meta-math/MetaMathQA

Oryginalny model: https://huggingface.co/speakleash/Bielik-7B-Instruct-v0.1

Adapter mógł ulec overfittingowi.

Była to część mojego porzuconego eksperymentu z modelem MoE - chciałem wykorzystać ten adapter do stworzenia jednego z ekspertów w modelu MoE. Ponieważ adapter został już wytrenowany i szkoda byłoby go zmarnować, publikuję go.