Publish reproduced WebNLG checkpoint and model card

README.md

@@ -0,0 +1,42 @@
+---
+language:
+- en
+- ru
+library_name: transformers
+pipeline_tag: text2text-generation
+base_model: cointegrated/rut5-base-multitask
+base_model_relation: finetune
+tags:
+- text-to-graph
+- webnlg
+- bt5
+---
+
+# BT5 English–Russian Semantic Parsing
+
+This model converts English or Russian text into subject–relation–object triples. It is our BT5 implementation based on [Agarwal et al. (2020)](https://aclanthology.org/2020.webnlg-1.13/), initialized from `cointegrated/rut5-base-multitask` and trained with six equally sampled parsing and translation tasks.
+
+We used this checkpoint as a base text-to-data model in [XQDT](https://huggingface.co/papers/2608.29948). The [reproduction repository](https://github.com/guihuzhang/bt5-regen-reproduction) contains the code, saved predictions, and evaluation scripts.
+
+The checkpoint is step 54,000. Its saved WebNLG 2020 test predictions give Exact F1 of 67.62 for English and 93.46 for Russian, using five-beam decoding.
+
+## Usage
+
+```python
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+
+model_path = "Loria-MosAIk/bt5-webnlg-en-ru"
+tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_path).eval()
+inputs = tokenizer("Parse English Paris is located in France.", return_tensors="pt")
+outputs = model.generate(**inputs, num_beams=5, max_new_tokens=256)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True, clean_up_tokenization_spaces=False))
+```
+
+Use `Parse Russian` for Russian input. Generated triples use `<S>`, `<P>`, and `<O>` markers. The accompanying reproduction code parses these markers and removes exact duplicate triples before evaluation.
+
+The [base model](https://huggingface.co/cointegrated/rut5-base-multitask) is distributed under MIT. The WebNLG data used for fine-tuning are distributed under [CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/).
+
+## Citation
+
+Please cite Agarwal et al. (2020) for BT5 and Efimov-Zhang et al. (2026) for this reproduction. [BibTeX entries](https://github.com/guihuzhang/bt5-regen-reproduction#citation).

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<O>": 30002,
+  "<P>": 30001,
+  "<S>": 30000
+}

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "cointegrated/rut5-base-multitask",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "gradient_checkpointing": false,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "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,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 30003
+}

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": "4.46.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5389fc8a1a85e2072555fbe62a3943cd24b5f7aefd5101cf9e59324731e37ce8
+size 977289064

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76927654c70c667e967c8caca165a3bb1311b415316b6aed8037ed5ede86b10e
+size 827566

tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30000": {
+      "content": "<S>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30001": {
+      "content": "<P>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30002": {
+      "content": "<O>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}