OcciGlot
@occiglot
Followers
231
Following
42
Statuses
32
Open Source Language Models for Europe
Joined February 2024
📣Community Call Contribute to LLM pre-training resources in (your) unrepresented language! Please submit any websites in that language to @CommonCrawl's web language project. They will help increase non-english data in future releases.
0
10
22
For anybody still at #EMNLP, we will be presenting community-Oscar at the MRL poster session at 11am. See you there.
📣Announcing Community-OSCAR: A collaboration between Occiglot and the OSCAR project for creating multilingual Web-crawled datasets. Blog: HF:
0
5
8
RT @MBrack_AIML: For anybody attending KonKis next week, let me make a quick add read for Session 4: "Large AI Models by and for Europe."…
0
2
0
RT @MBrack_AIML: We seek collaborators to extend Community OSCAR to the remaining Common Crawl dumps. If you have the compute/storage (or…
0
3
0
RT @HKydlicek: Great work by @occiglot community on releasing new iteration of multilingual Oscar spanning 40 CC snapshots!! It's so impor…
0
3
0
We would like to thank all collaborators and institutes who participated in this effort and dedicated time and compute resources to the creation of Community-Oscar.
0
0
1
RT @zilliz_universe: Join @stephenbtl and speakers from @AWS and @occiglot at the Unstructured Data Meetup at the On Cloud Office in Berlin…
0
3
0
@DiscoResearchAI @AIatMeta The model was trained on the 42 supercomputer of @Hessian_AI with support from @DFKI, @TUDarmstadt, @HMWK_Hessen & @BMBF_Bund
0
0
4
@DiscoResearchAI @AIatMeta Shoutout to @bjoern_pl and @MBrack_AIML for training the model and curating the data. Likewise we would like to thank @XYOU and @pjox13 for their amazing work that lead to our dataset in the first place.
0
0
2
RT @clefourrier: New leaderboard: "Occiglot Euro LLM Leaderboard"! It evaluates the performance of LLMs on the following languages: 🇬🇧🇮🇹🇫🇷…
0
5
0
RT @DFKI: OcciGlot - New Open Source Language Models for Europe released 🇪🇺 Researchers from DFKI and @Hessian_AI have launched the @occi…
0
6
0
In the paper below, the authors investigated the spanish lexical capabilities of various LLM. Experts manually evaluate the correctness of 100 randomly chosen word definitions. Our Spanish model achieves the best results 💪
1
1
1
RT @PhoBoAI: 📢Máme málo neanglických LLM benchmarků! Pojďte se zapojit do @huggingface 🤗komunitního projektu a pojďmě společně přeložit 500…
0
5
0
RT @Dorialexander: Common corpus is an international initiative coordinated by @pleias_fr with the support of the state start-up LANGU:IA,…
0
5
0