Sponsored by
Vmake Labs Video Enhancer
-Vmake Labs Video Enhancer utiliza IA para mejorar la calidad del vídeo, restaurar detalles, reducir el desenfoque y aumentar la
Poro 34b chat is a chat-tuned version of
Poro
34B
trained to follow instructions
in both Finnish and English. Quantized versions are available on
Poro
34B-chat-GGUF
.
Because of the limited amount of instruction tuning available for Finnish, documents from the English datasets were machine-translated by the Poro 34B base model into Finnish, then used to train this chat version. We selected only datasets that are available for commercial use and only contain synthetic data if it was gathered in ToS-compliant fashion.
More information about the data selection and translation process for our Finnish dataset are available on the
LumiOpen/instruction-collection-fin
page.
This project is part of an ongoing effort to create open source large language models for non-English and especially low resource languages like Finnish. Through the combination of English and Finnish training data we get a model that outperforms previous Finnish only models, while also being fluent in English and code, and capable of basic translation between English and Finnish.
Fine Tuning
Poro-34b-Chat is an SFT finetune of Poro-34b on a collection of Finnish and
English instruction datasets. The collection is made up of roughly of 40%
English, 40% Finnish, and 20% cross-lingual entries.
We finetuned the base model for 3 epochs with a learning rate of 2e-05, warmup
ratio of 0.1, and a global batch size of 48. For full-parameter finetuning, we used 3 nodes (8 GPUs per node). We used the
Alignment Handbook
code for finetuning.
<|im_start|>system
You can add an optional system prompt here.<|im_end|>
<|im_start|>user
Miten rakennan tietokoneen?<|im_end|>
<|im_start|>assistant
Evaluations
We relied on the popular MTBench benchmark to evaluate multi-turn performance.
Since MTBench is an English only benchmark, we also release this fork of
MTBench Finnish
with multilingual support and machine translated Finnish prompts. Our scores for both benchmarks follow.
Note: Updated on 18 June 2024
Eval
Overall
Coding
Extraction
Humanities
Math
Reasoning
Roleplay
STEM
Writing
MTBench English
6.13
4.25
6.65
9.60
2.30
4.30
7.05
7.55
7.35
MTBench Finnish
6.06
3.70
6.37
9.25
1.20
4.35
7.35
7.80
8.50
License
Poro 34B chat is released under the Apache 2.0 license.
Citation
@misc{luukkonen2024poro,
title={Poro 34B and the Blessing of Multilinguality},
author={Risto Luukkonen and Jonathan Burdge and Elaine Zosa and Aarne
Talman and Ville Komulainen and Väinö Hatanpää and Peter Sarlin and Sampo
Pyysalo},
year={2024},
eprint={2404.01856},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
Runs of LumiOpen Poro-34B-chat on huggingface.co
78
Total runs
0
24-hour runs
0
3-day runs
-44
7-day runs
-146
30-day runs
More Information About Poro-34B-chat huggingface.co Model
Poro-34B-chat huggingface.co is an AI model on huggingface.co that provides Poro-34B-chat's model effect (), which can be used instantly with this LumiOpen Poro-34B-chat model. huggingface.co supports a free trial of the Poro-34B-chat model, and also provides paid use of the Poro-34B-chat. Support call Poro-34B-chat model through api, including Node.js, Python, http.
Poro-34B-chat huggingface.co is an online trial and call api platform, which integrates Poro-34B-chat's modeling effects, including api services, and provides a free online trial of Poro-34B-chat, you can try Poro-34B-chat online for free by clicking the link below.
LumiOpen Poro-34B-chat online free url in huggingface.co:
Poro-34B-chat is an open source model from GitHub that offers a free installation service, and any user can find Poro-34B-chat on GitHub to install. At the same time, huggingface.co provides the effect of Poro-34B-chat install, users can directly use Poro-34B-chat installed effect in huggingface.co for debugging and trial. It also supports api for free installation.