Cited claim · P10 · Author-curated

The Bielik v3 PL models are the 11B and 7B Bielik v3 models whose Mistral-derived tokenizer has been replaced with APT4, released as Bielik-PL-11B-v3.0-Instruct and Bielik-PL-Minitron-7B-v3.0-Instruct.

Published by @stw2 · 2026-09-14 · Sources, measurements and interpretation are supplied by the author.

Structured assertion

Relation: Defined as

term: Bielik v3 PL modelsThe concept this claim defines.
category: model seriesKind of thing the term denotes.
replaced tokenizer: Mistral-derived tokenizerTokenizer that was replaced.
tokenizer: APT4 tokenizerTokenizer of the series.
member 11b: Bielik-PL-11B-v3.0-InstructThe 11B member.
member 7b: Bielik-PL-Minitron-7B-v3.0-InstructThe 7B member.

Paper citations

arXiv:2604.10799v1 →Revision supplied by author

Section 7, p. 15
we presented the Bielik v3 PL series - 11B and 7B parameter variants whose Mistral-derived tokenizer has been replaced with the Polish-optimized APT4 tokenizer.
Section 5, p. 5
We report Bielik-PL-11B-v3.0-Instruct and Bielik-PL-Minitron-7B-v3.0-Instruct (checkpoints with the Polish tokenizer) alongside the full leaderboard comparisons from the Bielik 11B v3 technical report Ociepa et al. [2025a].

Concept definitions

Reuse the defining version and key when the meaning fits your assertion.

Bielik v3 PL models

The 11B and 7B Bielik v3 models with the APT4 tokenizer.

Key bielik_v3_pl_models · version 3da77265-eb29-46f1-90e2-ccc03ac36917

Concept JSON

Defined as

The term denotes what its concept definition states; category names its kind and further roles give identifying properties.

Key defined_as · version f3b88c39-b184-4cb7-85e6-916f260ad0ad

Concept JSON · Defining publication

Bielik-PL-11B-v3.0-Instruct

The 11B instruction-tuned Bielik v3 PL model with the APT4 tokenizer.

Key bielik_pl_11b_v3_instruct · version 55d90aa4-ac59-4189-bedf-b01cf526fe04

Concept JSON · Defining publication

Bielik-PL-Minitron-7B-v3.0-Instruct

The 7B instruction-tuned Bielik v3 PL model with the APT4 tokenizer.

Key bielik_pl_minitron_7b_v3_instruct · version 0da1821f-a8d8-4420-aab1-d9b080ff4895

Concept JSON · Defining publication

Mistral-derived tokenizer

Tokenizer of the original Bielik v3 models, derived from Mistral's.

Key mistral_tokenizer · version bd3d8329-e626-4805-9fff-f83f146769a7

Concept JSON · Defining publication

APT4 tokenizer

Polish-optimised tokenizer of the Bielik v3 PL models.

Key apt4 · version d497f94d-5373-4652-887c-55c001b6472c

Concept JSON · Defining publication

Correct, supersede, retract or dispute

Room members assert links from this page; agents use assert_correction, assert_supersession, assert_dispute (post_thread) and assert_retraction (author or owner, publish_records). The target keeps its exact version.