OpenEuroLLM/Taskboard

View on GitHub

Stars: 3
Forks: 0
Open beginner issues: 0
Indexed issues: 210

Dominant language: No language data
License: Apache-2.0
Last GitHub push: Jun 24, 2026
Latest indexed: Sep 20, 2026
Contributing guide: No contributing guide
Code of conduct: No code of conduct
Beginner labels: No beginner labels indexed
PR merge metrics: No merged PRs in 30d

Beginner friendly Everything

Open All

210 open issues indexed

Evaluate 32B checkpoints on both first and conservative run Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

OpenEuroLLM/Taskboard#411 · Opened Sep 18, 2026
Add working mixture-reuse in olmix repo Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

OpenEuroLLM/Taskboard#410 · Opened Sep 18, 2026
Annotate pre-training datasets for copyright Open

T3.4 - regulatory compliance WP3

OpenEuroLLM/Taskboard#409 · 1 assignee · Opened Sep 17, 2026
Evaluate Prelude checkpoints using eval-framework Open

WP5

OpenEuroLLM/Taskboard#408 · 1 comment · 1 assignee · Opened Sep 17, 2026
[32B Dense] Mid-training downstream evals Open

T4.4 - model training

OpenEuroLLM/Taskboard#407 · 3 assignees · Opened Sep 16, 2026
Add safety and fairness benchmarks Open

T4.5 - cont. eval T5.6 - New Benchmarks

Difficulty 5/5 Over a week Newbie friendliness 35/100

OpenEuroLLM/Taskboard#405 · Opened Sep 15, 2026
Documentation on runs and experiments performed Open

T4.4 - model training

OpenEuroLLM/Taskboard#404 · 1 assignee · Opened Sep 15, 2026
Revisit top-level datamix for final flagship Open

T4.3 - datamix/proc

OpenEuroLLM/Taskboard#403 · 4 assignees · Opened Sep 15, 2026
Revisit code/math/reasoning/etc. datamix for final flagship Open

T4.3 - datamix/proc

OpenEuroLLM/Taskboard#402 · 2 assignees · Opened Sep 15, 2026
Revisit web datamix (English+multilingual) for final flagship Open

T4.3 - datamix/proc

OpenEuroLLM/Taskboard#401 · 1 comment · 2 assignees · Opened Sep 15, 2026
Revisit data sources for final flagship Open

T4.3 - datamix/proc

OpenEuroLLM/Taskboard#400 · 1 comment · 2 assignees · Opened Sep 15, 2026
Data publication Open

WP3

Difficulty 5/5 Over a week Newbie friendliness 20/100

OpenEuroLLM/Taskboard#399 · Opened Sep 14, 2026
Data compliance review Open

WP3

Difficulty 5/5 Over a week Newbie friendliness 15/100

OpenEuroLLM/Taskboard#398 · Opened Sep 14, 2026
Model documentation, publication and report Open

Difficulty 5/5 Over a week Newbie friendliness 10/100

OpenEuroLLM/Taskboard#397 · Opened Sep 14, 2026
Final evaluation Open

WP5

Difficulty 5/5 Over a week Newbie friendliness 10/100

OpenEuroLLM/Taskboard#396 · 1 comment · Opened Sep 14, 2026
Execute annealing on 2t tokens Open

T4.4 - model training

Difficulty 5/5 Over a week Newbie friendliness 15/100

OpenEuroLLM/Taskboard#395 · Opened Sep 14, 2026
Post training of prelude final checkpoint Open

4.6 post-training

Difficulty 5/5 Over a week Newbie friendliness 30/100

OpenEuroLLM/Taskboard#393 · Opened Sep 14, 2026
Long context extension of prelude final checkpoint Open

4.6 post-training

Difficulty 5/5 Over a week Newbie friendliness 35/100

OpenEuroLLM/Taskboard#392 · Opened Sep 14, 2026
Ensuring post-training pipeline works Open

4.6 post-training

OpenEuroLLM/Taskboard#391 · 1 assignee · Opened Sep 14, 2026
Review function-calling dataset licenses and rerun mixture ablations Open

4.6 post-training

OpenEuroLLM/Taskboard#390 · 1 assignee · Opened Sep 14, 2026
Develop a preliminary multilingual function-calling SFT data-generation pipeline Open

4.6 post-training

OpenEuroLLM/Taskboard#389 · 1 assignee · Opened Sep 14, 2026
Scale agentic/RL function-calling data generation Open

4.6 post-training

OpenEuroLLM/Taskboard#388 · 1 assignee · Opened Sep 14, 2026
Improve deduplication for function-calling training data Open

4.6 post-training

OpenEuroLLM/Taskboard#387 · 1 assignee · Opened Sep 14, 2026
Bring up and validate the agentic RL stack on LUMI Open

4.6 post-training

OpenEuroLLM/Taskboard#386 · 1 assignee · Opened Sep 14, 2026
Qualify the Qwen3.5-9B SFT backend on LUMI Open

4.6 post-training

OpenEuroLLM/Taskboard#385 · 1 assignee · Opened Sep 14, 2026
Benchmark Qwen3.5-9B Base and post-trained Qwen3.5-9B on BFCL V4 non-Web Open

4.6 post-training

OpenEuroLLM/Taskboard#384 · 1 assignee · Opened Sep 14, 2026
Post training evaluation Open

4.6 post-training

OpenEuroLLM/Taskboard#383 · 1 assignee · Opened Sep 14, 2026
RL Experiments Open

4.6 post-training

OpenEuroLLM/Taskboard#382 · 1 assignee · Opened Sep 14, 2026
[32B Dense] Debug 64k increasing loss Open

T4.4 - model training

OpenEuroLLM/Taskboard#381 · 15 comments · 4 assignees · Opened Sep 1, 2026
Annealing for 32B model - stage 2 Open

T4.3 - datamix/proc

Difficulty 5/5 Over a week Newbie friendliness 20/100

OpenEuroLLM/Taskboard#380 · Opened Sep 1, 2026
New experiment setup: model scale Open

T4.3 - datamix/proc

OpenEuroLLM/Taskboard#379 · 6 comments · 3 assignees · Opened Sep 1, 2026
Translate Dolci-Instruct-SFT-32B with gemma4-31b-it Open

4.6 post-training

OpenEuroLLM/Taskboard#378 · 2 assignees · Opened Aug 31, 2026
Custom tokenizer for final flagship model training Open

T4.3 - datamix/proc

OpenEuroLLM/Taskboard#377 · 1 comment · 2 assignees · Opened Aug 28, 2026
SFT fine tuning experiments Open

4.6 post-training

OpenEuroLLM/Taskboard#376 · 1 assignee · Opened Aug 25, 2026
Data-driven multilingual filtering Open

T4.3 - datamix/proc

OpenEuroLLM/Taskboard#372 · 3 comments · 2 assignees · Opened Aug 18, 2026
[MoE] Discrepancy between megatron router metrics and post-hoc dashboard Open

OpenEuroLLM/Taskboard#371 · 3 assignees · Opened Aug 18, 2026
Convert the current tokenizer to handle the qwen chat-template faithfully. Open

4.6 post-training

OpenEuroLLM/Taskboard#370 · 5 comments · 1 assignee · Opened Aug 17, 2026
Compute for 32B Dense context extension Open

4.6 post-training T4.4 - model training

Difficulty 4/5 3-5 days Newbie friendliness 38/100

OpenEuroLLM/Taskboard#369 · 1 comment · Opened Aug 14, 2026
[multilingual scaling laws] test prediction on hold out prelude checkpoints Open

T4.2 - model exploration

OpenEuroLLM/Taskboard#366 · 2 comments · 2 assignees · Opened Aug 7, 2026
[Baby 9B dense] Base model annealing Open

T4.3 - datamix/proc T4.4 - model training

OpenEuroLLM/Taskboard#365 · 28 comments · 5 assignees · Opened Aug 5, 2026
Integrate Qwen3 MoE conversion to oellm-autoexp Open

OpenEuroLLM/Taskboard#364 · 3 assignees · Opened Aug 5, 2026
Hybrid Model Tests Open

T4.4 - model training

OpenEuroLLM/Taskboard#363 · 1 comment · 1 assignee · Opened Aug 4, 2026
Fixing post-training conventions Open

4.6 post-training

OpenEuroLLM/Taskboard#362 · 15 comments · 5 assignees · Opened Aug 3, 2026
SFT & DPO applied to current prelude checkpoints Open

4.6 post-training

OpenEuroLLM/Taskboard#361 · 1 assignee · Opened Aug 3, 2026
Define Data Compliance Governance Strategy Open

WP3

Difficulty 5/5 Over a week Newbie friendliness 25/100

OpenEuroLLM/Taskboard#360 · Opened Jul 30, 2026
Prelude: document training process and checkpoints Open

T4.4 - model training

Difficulty 3/5 1-2 days Newbie friendliness 45/100

OpenEuroLLM/Taskboard#359 · Opened Jul 29, 2026
[MoE] z-loss, shared experts and aux loss grid Open

T4.2 - model exploration

OpenEuroLLM/Taskboard#358 · 1 reaction · 1 assignee · Opened Jul 28, 2026
Post-flagship: explore the architecture that is optimal for deployment Open

T4.2 - model exploration

Difficulty 5/5 Over a week Newbie friendliness 20/100

OpenEuroLLM/Taskboard#357 · Opened Jul 27, 2026
Data mixture comparison Open

T4.2 - model exploration

Difficulty 5/5 Over a week Newbie friendliness 20/100

OpenEuroLLM/Taskboard#356 · Opened Jul 27, 2026
Make sure that our models are usefule for practical use (architecture decisions with inference in mind) Open

OpenEuroLLM/Taskboard#355 · 1 assignee · Opened Jul 24, 2026

OpenEuroLLM/Taskboard

Get new issues in your inbox