Add PL-Trans-Init paper model

README.md

@@ -0,0 +1,64 @@
+---
+language:
+- pl
+base_model:
+- rausch/en-t5-sci-continued-pretraining-487k
+datasets:
+- scilons/SciLaD-all-text-v1
+library_name: transformers
+tags:
+- t5
+- seq2seq
+- text-to-text
+- scientific-language-models
+- cross-lingual-transfer
+- wechsel
+- global-mmlu
+---
+
+# PL-Trans-Init
+
+Polish scientific T5 model initialized from EN-T5-Sci using WECHSEL and a language-specific SentencePiece 32k tokenizer.
+
+## Model Details
+
+This is one of the non-English scientific T5 transfer models from the paper. The model keeps the EN-T5-Sci Transformer weights and reinitializes the language-specific embeddings with WECHSEL using a target SentencePiece tokenizer.
+
+- Paper name: `PL-Trans-Init`
+- Model role: `main`
+- Source/base model: [EN-T5-Sci](https://huggingface.co/rausch/en-t5-sci-continued-pretraining-487k)
+- Code and pipeline: [GitHub repository](https://github.com/nikolas-rauscher/scientific-english-crosslingual-transfer)
+- Architecture: T5 encoder-decoder
+- SciLaD dataset: [scilons/SciLaD-all-text-v1](https://huggingface.co/datasets/scilons/SciLaD-all-text-v1)
+- Evaluation benchmark: [Global-MMLU](https://huggingface.co/datasets/CohereLabs/Global-MMLU)
+- Target-language tokenizer: Polish SciLaD split; language-specific SentencePiece 32k tokenizer
+
+Evaluated against:
+
+- [PL-Base-CP control](https://huggingface.co/rausch/pl-t5-base-sci-cp-15k): reported as the continued-pretraining control.
+- [upstream target-language base](https://huggingface.co/allegro/plt5-base): reported as the monolingual base comparison.
+
+WECHSEL resources: English fastText embeddings + Polish fastText embeddings (`pl`) with the `polish` bilingual dictionary.
+
+## Evaluation
+
+Zero-shot Global-MMLU accuracy reported by the paper aggregation:
+
+| Metric | Accuracy |
+|---|---:|
+| Average | 24.66 |
+| STEM | 23.91 |
+| Humanities | 24.51 |
+| Social Sciences | 23.43 |
+| Other | 26.87 |
+
+## Limitations
+
+The model is evaluated primarily with zero-shot Global-MMLU. Downstream task-specific
+evaluation is recommended before deployment in specialized scientific workflows.
+
+## Citation
+
+- Title: Transferring Scientific English Pre-Trained Language Models to Multiple Languages Using Cross-Lingual Transfer
+- Authors: Nikolas Rauscher, Fabio Barth, Georg Rehm
+- Venue: LREC-COLING 2026, citation details TBA after publication

config.json

@@ -0,0 +1,60 @@
+{
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.2",
+  "use_cache": true,
+  "vocab_size": 32100
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.55.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6efab43f7487d7c3592bc4d3f0c811d3d1c519882160f357616a62f2b1a7b84c
+size 891558696

special_tokens_map.json

@@ -0,0 +1,107 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e1993d2d6b0baaf522516fccc27960cc633b4f5cb122babafcb212129d45984
+size 732437

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e1993d2d6b0baaf522516fccc27960cc633b4f5cb122babafcb212129d45984
+size 732437

tokenizer_config.json

@@ -0,0 +1,113 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

tokenizer_training_metadata.json

@@ -0,0 +1,28 @@
+{
+  "timestamp_utc": "2026-02-16T20:50:18.532387+00:00",
+  "language": "pol_Latn",
+  "track": "paper_spm32k",
+  "training_data": "/netscratch/nrauscher/projects/BA-hydra/cross_lingual_transfer_multilingual/data/languages/pol_Latn/splits/sub/sub_charcap43gb_seed42/train/docs.parquet",
+  "training_data_rows": 121766,
+  "subsplit": "sub_charcap43gb_seed42",
+  "sentencepiece": {
+    "model_type": "bpe",
+    "vocab_size": 32000,
+    "character_coverage": 1.0,
+    "byte_fallback": true,
+    "hard_vocab_limit": false,
+    "input_sentence_size": 0,
+    "shuffle_input_sentence": true,
+    "num_threads": 32,
+    "pad_id": 0,
+    "eos_id": 1,
+    "unk_id": 2,
+    "bos_id": -1
+  },
+  "t5": {
+    "extra_ids": 100,
+    "tokenizer_length": 32100,
+    "fast_tokenizer_export_ok": false
+  },
+  "duration_sec": 63.32048845291138
+}