Duplicate from cea-list-ia/ManufactuBERT

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,64 @@
+---
+license: mit
+datasets:
+- HuggingFaceFW/fineweb
+language:
+- en
+metrics:
+- f1
+base_model:
+- FacebookAI/roberta-base
+library_name: transformers
+tags:
+- manufacturing
+---
+# ManufactuBERT
+
+Specialized **RoBERTa-base** model continually pretrained on a high-quality corpus specifically curated for the **manufacturing domain**. By employing a rigorous data selection and deduplication pipeline, ManufactuBERT achieves state-of-the-art performance on industrial NLP tasks while being more efficient to train than standard domain-adapted models.
+
+## Model Details
+- **Developed by:** Robin Armingaud and Romaric Besançon (Université Paris-Saclay, CEA, List) 
+- **Language:** English 
+- **Domain:** Manufacturing and Industrial Engineering 
+
+## Training Data
+The first ManufactuBERT model was continually pretrained on **Manu-FineWeb**, a 10-billion-token subset of the FineWeb dataset. The final model version used a further refined version (~2 billion tokens) created through a multi-stage process using **MinHash** and **SemDeDup** to remove approximately 80% of redundant data. This process accelerated convergence by approximately 33% compared to the non-deduplicated version.
+
+## Named Entity Recognition (NER)
+| Model | Mat. Syn. | FabNER | SOFC | SOFC Slot | MatScholar | ChemdNER | Avg. |
+| :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+| RoBERTa | 73.12 | 82.48 | 82.54 | 69.52 | 84.04 | 90.50 | 80.37 |
+| MatSciBERT | **76.50** | 83.88 | 82.10 | 72.60 | 85.88 | **92.00** | 82.16 |
+| **ManufactuBERT** | 75.04 | **84.00** | **84.40** | **73.68** | **86.76** | 91.92 | **82.63** |
+
+## Sentence Classification & Relation Extraction
+| Model | Mat. Syn. (RE) | SOFC (SC) | Big Patent (SC) | Avg. |
+| :--- | :---: | :---: | :---: | :---: |
+| RoBERTa | 94.32 | 94.32 | 63.58 | 84.07 |
+| MatSciBERT | **95.48** | **94.72** | 63.80 | 84.67 |
+| **ManufactuBERT** | 94.62 | 94.68 | **65.80** | **85.03** |
+
+## General Domain Evaluation (GLUE)
+The model preserves general language understanding capabilities significantly better than other domain-specific models.
+
+| Model | GLUE Avg. |
+| :--- | :---: |
+| RoBERTa | 86.35 |
+| MatSciBERT | 77.00 |
+| SciBERT | 78.13 |
+| **ManufactuBERT** | **81.78** |
+
+
+## Citation
+If you use ManufactuBERT in your research, please cite:
+```bibtex
+@misc{armingaud2025manufactubertefficientcontinualpretraining,
+      title={ManufactuBERT: Efficient Continual Pretraining for Manufacturing}, 
+      author={Robin Armingaud and Romaric Besançon},
+      year={2025},
+      eprint={2511.05135},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2511.05135}, 
+}
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "pretrained_models/roberta_minhash_20b20s_semdedup_015/step_12500",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d45eda626808be60209eb23631cd9c77e77e60e0db16b6889812a1678e5296f2
+size 498859634

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}