WMTH-100d2exam

Bielik-11B-v3.0-Instruct post-trained for the Polish history matura (extended level) during the Warsaw Model Trainers alpha=64) on top of speakleash/Bielik-11B-v3.0-Instruct. closedem = exact match on closed items. Graded scores (deepseek-flash-high@think via benchmark/bench.py) are reported separately.

LoRA adapter for google/gemma-4-12B-it-qat-q40-unquantized trained to answer the Polish history matura (poziom rozszerzony, CKE). Built at the Warsaw Model Trainers Hackathon (team repo: WarsawModelTrainersHackathon, src/posttrain/). Supervised fine-tuning, bf16 LoRA on the QAT weights (deployed on the official Q40 GGUF). One mixed pass over every source: short-key items (real/rephrased/synthetic exam items, textbook questions) trained with thinking OFF (question -> CKE answer), gemma-4-31b@think teacher traces (judge-filtered, exam items + essays) trained with thinking ON; exam-like rows oversampled x2-x3. Loss on the answer only. LoRA r=32, alpha=64, all language-model linear layers, lr…

LoRA adapter for google/gemma-4-12B-it-qat-q40-unquantized trained to answer the Polish history matura (poziom rozszerzony, CKE). Built at the Warsaw Model Trainers Hackathon (team repo: WarsawModelTrainersHackathon, src/posttrain/). Vision SFT (QLoRA, 4-bit base): image-based exam items (real CKE papers with their source images, synthetic Wikimedia image tasks, synthetic full papers) with the PNGs fed to the model, plus 30% of the teacher traces; vision tower frozen, language LoRA only. LoRA r=32, alpha=64, lr 1e-4, 1 epoch, batch 1 x gradaccum 16, maxlen 6144, Unsloth vision collator Consolidated training set data/trainingdatasets/sfttrain.jsonl (buildsft.py): real CKE papers 2005–2026…

Ministral-3-8B-Instruct-2512 post-trained for the Polish history matura (extended level) during the Warsaw Model Trainers alpha=64) on top of mistralai/Ministral-3-8B-Instruct-2512-BF16 (the bf16 twin of the FP8 -2512 release). closedem = exact match on closed items. Graded scores (deepseek-flash-high@think via benchmark/bench.py) are reported separately.

LoRA adapter for google/gemma-3-12b-it trained to answer the Polish history matura (poziom rozszerzony, CKE). Built at the Warsaw Model Trainers Hackathon (team repo: WarsawModelTrainersHackathon, src/posttrain/). SFT (QLoRA r=32 on the mixed matura set, no thinking; repo gemma-3-12b-it-matura-history-sft-qlora-r32), then GRPO with Unsloth + TRL on closed exam items with an exact key (single choice, true/false, matching, ordering). Reward = 0.2format + 0.8exact match, Dr.GRPO loss, beta=0 (no KL). THIS VERSION: GRPO step 25 (interim); the full 300-step run replaces it when it finishes. Closed-question exact match on validation (321 items, no judge): 68.2 overall (SFT alone 66.4, base 45.5).…

Qwen3.5-9B post-trained for the Polish history matura (extended level) during the Warsaw Model Trainers alpha=64) on top of Qwen/Qwen3.5-9B. closedem = exact match on closed items. Graded scores (deepseek-flash-high@think via benchmark/bench.py) are reported separately.

Bielik-11B-v3.0-Instruct post-trained for the Polish history matura (extended level) during the Warsaw Model Trainers alpha=64) on top of speakleash/Bielik-11B-v3.0-Instruct. closedem = exact match on closed items. Graded scores (deepseek-flash-high@think via benchmark/bench.py) are reported separately.

Ministral-3-8B-Instruct-2512 post-trained for the Polish history matura (extended level) during the Warsaw Model Trainers alpha=64) on top of mistralai/Ministral-3-8B-Instruct-2512-BF16 (the bf16 twin of the FP8 -2512 release). closedem = exact match on closed items. Graded scores (deepseek-flash-high@think via benchmark/bench.py) are reported separately.

LoRA adapter for google/gemma-3-12b-it trained to answer the Polish history matura (poziom rozszerzony, CKE). Built at the Warsaw Model Trainers Hackathon (team repo: WarsawModelTrainersHackathon, src/posttrain/). Supervised fine-tuning (QLoRA) of Gemma 3 12B-it on the same mixed set; Gemma 3 has no thinking mode, so teacher traces contribute their final answers only. LoRA r=32, alpha=64, lr 1e-4 cosine, 1 epoch, batch 16, maxlen 6144, Unsloth + TRL Consolidated training set data/trainingdatasets/sfttrain.jsonl (buildsft.py): real CKE papers 2005–2026 with keys, rephrased papers, synthetic image tasks, synthetic full papers, e-podręczniki textbook questions, synthetic Claude/DeepSeek tasks…

Bielik-11B-v3.0-Instruct post-trained for the Polish history matura (extended level) during the Warsaw Model Trainers alpha=64) on top of speakleash/Bielik-11B-v3.0-Instruct. closedem = exact match on closed items. Graded scores (deepseek-flash-high@think via benchmark/bench.py) are reported separately.

Ministral-3-8B-Instruct-2512 post-trained for the Polish history matura (extended level) during the Warsaw Model Trainers alpha=64) on top of mistralai/Ministral-3-8B-Instruct-2512-BF16 (the bf16 twin of the FP8 -2512 release). closedem = exact match on closed items. Graded scores (deepseek-flash-high@think via benchmark/bench.py) are reported separately.

Qwen3.5-9B post-trained for the Polish history matura (extended level) during the Warsaw Model Trainers alpha=64) on top of Qwen/Qwen3.5-9B. closedem = exact match on closed items. Graded scores (deepseek-flash-high@think via benchmark/bench.py) are reported separately.

The model weights of the LoRA / QLoRA runs done on the L40S server during the Warsaw Model Trainers Hackathon (25-26.09.2026): PEFT adapters, Trainer checkpoints (with optimizer state), lora.gguf adapters for llama.cpp and trainingargs.bin. These are adapters, not full models. Every run uses the base google/gemma-4-12B-it-qat-q40-unquantized (the local path in adapterconfig.json points to a server copy of it). Layout: l40s-results/ /..., the same paths as oldwb/l40s-results/ in the GitHub repo Endote/WarsawModelTrainersHackathon, which holds the logs, metrics, data statistics and write-ups (README.md, EXPERIMENTS.md, BENCHMARKSRESEARCH.md). Restore into a checkout of that repo: python…

Datasets and evaluation results of the Warsaw Model Trainers Hackathon (Polish history matura), moved out of the GitHub repo Endote/WarsawModelTrainersHackathon. Restore with scripts/fetchdata.py in that repo. Paths mirror the repo, so restored files land where the code expects them: Cleaning: server IPs, home paths and the ClearML API key were redacted (X.X.X.X, /home/user, REDACTEDCLEARML). candidate catalog synthetic-history-essays-v1 (it embeds examiner keyanswer text). The completed release is included in full. Note on datasyntheticextended and output/essay-generation: the packets were built from the deprecated datasyntheticextended essays, so many files (about 7,500 in the runs, and…