|
| 1 | +--- |
| 2 | +title: "Improve Harmony's PDF parsing on DOXA AI" |
| 3 | +categories: |
| 4 | + - "ai-in-research" |
| 5 | +image: "/images/parsing-banner.png" |
| 6 | +date: 2024-12-20 |
| 7 | +url: "/doxa-parsing/" |
| 8 | +--- |
| 9 | + |
| 10 | +## Train your own Large Language Model to parse PDFs and win up to £1000 in vouchers! |
| 11 | + |
| 12 | +*Join a competition to train a Large Language Model to improve Harmony's PDF parsing. You don't need to have trained a Large Language Model before.* |
| 13 | + |
| 14 | +{{< grid columns="2" >}} |
| 15 | + {{< card heading="Register on DOXA AI" copy="Enter the competition on DOXA AI by fine tuning your own large language model and improve Harmony!" url="https://doxaai.com/competition/harmony-parsing" >}} |
| 16 | + {{< card heading="Join our Discord" copy="Join the Harmony Discord server. Check out the 🏅「matching-challenge」 channel!" url="https://discord.com/invite/harmonydata" >}} |
| 17 | +{{< /grid >}} |
| 18 | + |
| 19 | + |
| 20 | + |
| 21 | + |
| 22 | +We would like to improve Harmony's PDF parsing algorithm. |
| 23 | + |
| 24 | + |
| 25 | +We would like to improve Harmony with a *fine tuned* large language model. We have teamed up with DOXA AI and made an online competition where you can improve on the off-the-shelf LLMs which we are currently using. You can win up to £1000 in vouchers! [Click here to join the Harmony matching competition on DOXA AI](https://doxaai.com/competition/harmony-parsing). |
| 26 | + |
| 27 | + |
| 28 | +{{< grid columns="2" >}} |
| 29 | + {{< card heading="Register on DOXA AI" copy="Enter the competition on DOXA AI by fine tuning your own large language model and improve Harmony!" url="https://doxaai.com/competition/harmony-parsing" >}} |
| 30 | + {{< card heading="Join our Discord" copy="Join the Harmony Discord server. Check out the 🏅「matching-challenge」 channel!" url="https://discord.com/invite/harmonydata" >}} |
| 31 | +{{< /grid >}} |
| 32 | + |
| 33 | + |
| 34 | + |
| 35 | +## What about data? |
| 36 | + |
| 37 | +We have gathered training data for you to use to fine tune your model, and there is unseen validation data which we will use to score the model. |
| 38 | + |
| 39 | +[More information is available on the DOXA AI page](https://doxaai.com/competition/harmony-parsing). |
| 40 | + |
| 41 | +## How can I get started? |
| 42 | + |
| 43 | +First, [create an account on DOXA AI and enroll in the competition](https://doxaai.com/competition/harmony-parsing) and download the code examples and training data. |
| 44 | + |
| 45 | +## Prizes |
| 46 | + |
| 47 | +The prize for the winner of the competition is £1000 in vouchers and the runner up will get £500 in vouchers. |
| 48 | + |
| 49 | +## See also |
| 50 | + |
| 51 | +[Matching competition](/doxa/) |
| 52 | + |
| 53 | +## See other events |
| 54 | + |
| 55 | +* 22 November 2024: [Harmony at Women In Data™️ London Chapter](/open-source-for-social-science/women-in-data/) |
| 56 | +* 8 October 2024: [Harmony: a free online tool using LLMs for research in psychology and social sciences](/psychology-ai-tool/aidl-meetup/) at AI|DL London |
| 57 | +* 11 and 12 September 2024: [Harmony at MethodsCon Futures](/ai-in-mental-health/harmony-at-methodscon-futures/ |
| 58 | +) in Manchester |
| 59 | +* 2 July 2024: [Harmony: NLP and generative models for psychology research](/open-source-for-social-science/pydata-meetup/) at Pydata London |
| 60 | +* 3 June 2024: [Harmony Hackathon](/open-source-for-social-science/hackathon/) at UCL |
| 61 | +* 5 May 2024: [Harmony: A global platform for harmonisation, translation and cooperation in mental health](/ai-in-mental-health/harmony-at-lifecourse-seminar/) at Melbourne Children’s LifeCourse Initiative seminar series. |
| 62 | +* 27 March 2024: [Harmony at AI Camp](/psychology-ai-tool/aicamp-meetup/) |
| 63 | +* 17 August 2023: [Harmony and TIDAL workshop](/ai-in-mental-health/harmony-and-tidal-workshop) |
| 64 | + |
| 65 | + |
| 66 | + |
| 67 | +{{< htmlcode >}} |
| 68 | + |
| 69 | +<button onclick="window.open('https://doxaai.com/competition/harmony-matching');" style="border-width:1px;background-color:rgb(15, 24, 84);color:white;padding:10px;margin:2px;border-radius:4px;">Enter the competition on DOXA</button> |
| 70 | + |
| 71 | +{{< /htmlcode >}} |
| 72 | + |
| 73 | +{{< card heading="Register on DOXA AI" copy="Enter the competition on DOXA AI by fine tuning your own large language model and improve Harmony!" url="https://doxaai.com/competition/harmony-parsing" >}} |
0 commit comments