Upload folder using huggingface_hub

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 768,
+    "pooling_mode_cls_token": false,
+    "pooling_mode_mean_tokens": true,
+    "pooling_mode_max_tokens": false,
+    "pooling_mode_mean_sqrt_len_tokens": false,
+    "pooling_mode_weightedmean_tokens": false,
+    "pooling_mode_lasttoken": false,
+    "include_prompt": true
+}

LICENSE

@@ -0,0 +1,190 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to the Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   Copyright 2026 Grai Team
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -0,0 +1,351 @@
+---
+license: apache-2.0
+language:
+- en
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- radiology
+- medical
+- retrieval
+- embeddings
+- healthcare
+- clinical
+base_model: zzxslp/RadBERT-RoBERTa-4m
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+datasets:
+- radiology-education-corpus
+metrics:
+- mrr
+- ndcg
+model-index:
+- name: RadLITE-Encoder
+  results:
+  - task:
+      type: retrieval
+      name: Information Retrieval
+    dataset:
+      name: RadLIT-9 (Radiology Retrieval Benchmark)
+      type: radiology-retrieval
+    metrics:
+    - type: mrr
+      value: 0.829
+      name: MRR (with full pipeline)
+    - type: ndcg@10
+      value: 0.863
+      name: nDCG@10
+    - type: recall@10
+      value: 0.90
+      name: Recall@10
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: Radiology Similarity Evaluation
+      type: radiology-similarity
+    metrics:
+    - type: spearman_cosine
+      value: 0.8454
+      name: Spearman Correlation
+    - type: pearson_cosine
+      value: 0.8504
+      name: Pearson Correlation
+---
+
+# RadLITE-Encoder
+
+**Radiology Late Interaction Transformer Enhanced - Bi-Encoder Component**
+
+A domain-specialized sentence transformer for radiology and medical imaging content. This model encodes radiology text (reports, articles, educational content) into 768-dimensional dense vectors optimized for semantic search and retrieval.
+
+> **Recommended:** For optimal retrieval performance, use this encoder with [RadLITE-Reranker](https://huggingface.co/matulichpt/RadLITE-Reranker) in a two-stage pipeline. The bi-encoder provides fast candidate retrieval, while the cross-encoder reranker delivers precision. This combination achieves **MRR 0.829** on radiology benchmarks.
+
+## Model Description
+
+| Property | Value |
+|----------|-------|
+| **Model Type** | Sentence Transformer (Bi-Encoder) |
+| **Base Model** | [RadBERT-RoBERTa-4m](https://huggingface.co/zzxslp/RadBERT-RoBERTa-4m) |
+| **Domain** | Radiology / Medical Imaging |
+| **Vector Dimensions** | 768 |
+| **Max Sequence Length** | 512 tokens |
+| **Similarity Function** | Cosine Similarity |
+| **License** | Apache 2.0 |
+
+### Why RadLITE-Encoder?
+
+Standard embedding models (BGE, E5, OpenAI) are trained on general web text and struggle with radiology-specific terminology:
+
+- **Anatomical terms**: "hepatic flexure", "foramen magnum", "costophrenic angle"
+- **Imaging sequences**: "T2 FLAIR", "DWI/ADC mismatch", "post-gadolinium"
+- **Pathology descriptions**: "ground-glass opacity", "cortical ribbon sign", "double duct sign"
+- **Abbreviations**: "HCC", "RCC", "NSCLC", "BI-RADS"
+
+RadLITE-Encoder is fine-tuned on millions of radiology documents to understand this specialized vocabulary.
+
+## Performance
+
+### RadLIT-9 Benchmark (Radiology Retrieval)
+
+| Model | MRR | nDCG@10 | Notes |
+|-------|-----|---------|-------|
+| **RadLITE-Encoder** | **0.829** | **0.863** | Full pipeline with reranker |
+| RadLITE-Encoder (standalone) | 0.78 | 0.81 | Bi-encoder only |
+| BGE-large-en-v1.5 | 0.72 | 0.76 | General-purpose |
+| RadBERT (baseline) | 0.45 | 0.52 | No retrieval training |
+
+### Subspecialty Performance
+
+| Subspecialty | MRR | Notes |
+|--------------|-----|-------|
+| Physics/Nuclear Medicine | 0.936 | Excellent |
+| Pediatric Radiology | 0.931 | Excellent |
+| Thoracic Imaging | 0.913 | Excellent |
+| Cardiac Imaging | 0.862 | Good |
+| Neuroradiology | 0.860 | Good |
+| Gastrointestinal | 0.800 | Good |
+| Breast Imaging | 0.722 | Moderate |
+| Musculoskeletal | 0.695 | Moderate |
+| Genitourinary | 0.694 | Moderate |
+
+## Quick Start
+
+### Installation
+
+```bash
+pip install sentence-transformers>=2.2.0
+```
+
+### Basic Usage
+
+```python
+from sentence_transformers import SentenceTransformer
+
+# Load the model
+model = SentenceTransformer("matulichpt/RadLITE-Encoder")
+
+# Encode radiology text
+documents = [
+    "Hepatocellular carcinoma typically shows arterial enhancement with washout on portal venous phase.",
+    "Ground-glass opacities in the bilateral lower lobes, concerning for viral pneumonia.",
+    "No acute intracranial abnormality. Age-appropriate cerebral volume loss.",
+]
+
+queries = [
+    "HCC imaging characteristics on CT",
+    "COVID-19 chest CT findings",
+]
+
+# Generate embeddings
+doc_embeddings = model.encode(documents, normalize_embeddings=True)
+query_embeddings = model.encode(queries, normalize_embeddings=True)
+
+# Compute similarities
+similarities = query_embeddings @ doc_embeddings.T
+print(similarities)
+# Query 1 (HCC) will score highest with Document 1
+# Query 2 (COVID) will score highest with Document 2
+```
+
+### Semantic Search over Your Corpus
+
+```python
+from sentence_transformers import SentenceTransformer, util
+import torch
+
+# Load model
+model = SentenceTransformer("matulichpt/RadLITE-Encoder")
+
+# Your radiology corpus (articles, reports, educational content)
+corpus = [
+    {"id": "doc1", "text": "Pancoast tumor: apical lung mass with rib destruction..."},
+    {"id": "doc2", "text": "Hepatic hemangioma shows peripheral nodular enhancement..."},
+    {"id": "doc3", "text": "Acoustic neuroma appears as enhancing CP angle mass..."},
+    # ... your documents
+]
+
+# Pre-compute corpus embeddings (do this once, save for reuse)
+corpus_texts = [doc["text"] for doc in corpus]
+corpus_embeddings = model.encode(corpus_texts, normalize_embeddings=True, show_progress_bar=True)
+
+# Save embeddings for later
+torch.save(corpus_embeddings, "corpus_embeddings.pt")
+
+# Search function
+def search(query: str, top_k: int = 10):
+    query_embedding = model.encode(query, normalize_embeddings=True)
+    scores = util.cos_sim(query_embedding, corpus_embeddings)[0]
+    top_results = torch.topk(scores, k=min(top_k, len(corpus)))
+
+    results = []
+    for score, idx in zip(top_results.values, top_results.indices):
+        results.append({
+            "document": corpus[idx],
+            "score": float(score)
+        })
+    return results
+
+# Example search
+results = search("superior sulcus tumor with Horner syndrome")
+for r in results[:3]:
+    print(f"Score: {r['score']:.3f} - {r['document']['text'][:100]}...")
+```
+
+### Integration with FAISS (Large-Scale)
+
+```python
+import faiss
+import numpy as np
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer("matulichpt/RadLITE-Encoder")
+
+# Encode your corpus
+corpus_embeddings = model.encode(corpus_texts, normalize_embeddings=True)
+corpus_embeddings = np.array(corpus_embeddings).astype('float32')
+
+# Build FAISS index
+dimension = 768
+index = faiss.IndexFlatIP(dimension)  # Inner product = cosine for normalized vectors
+index.add(corpus_embeddings)
+
+# Save index
+faiss.write_index(index, "radiology_index.faiss")
+
+# Search
+def faiss_search(query: str, top_k: int = 10):
+    query_embedding = model.encode(query, normalize_embeddings=True)
+    query_embedding = np.array([query_embedding]).astype('float32')
+    scores, indices = index.search(query_embedding, top_k)
+    return [(int(idx), float(score)) for idx, score in zip(indices[0], scores[0])]
+```
+
+## Best Practices
+
+### 1. Normalize Embeddings
+
+Always use `normalize_embeddings=True` for retrieval tasks. This enables efficient cosine similarity via dot product.
+
+### 2. Chunk Long Documents
+
+The model has a 512 token limit. For long articles:
+
+```python
+def chunk_text(text: str, max_length: int = 400, overlap: int = 50):
+    """Chunk text with overlap for better retrieval."""
+    words = text.split()
+    chunks = []
+    for i in range(0, len(words), max_length - overlap):
+        chunk = " ".join(words[i:i + max_length])
+        chunks.append(chunk)
+    return chunks
+```
+
+### 3. Batch Processing
+
+For large corpora, use batching:
+
+```python
+embeddings = model.encode(
+    texts,
+    batch_size=32,
+    normalize_embeddings=True,
+    show_progress_bar=True
+)
+```
+
+### 4. GPU Acceleration
+
+```python
+model = SentenceTransformer("matulichpt/RadLITE-Encoder", device="cuda")
+```
+
+## Two-Stage Retrieval (Recommended)
+
+For best results, combine RadLITE-Encoder with the [RadLITE-Reranker](https://huggingface.co/matulichpt/RadLITE-Reranker):
+
+```python
+from sentence_transformers import SentenceTransformer, CrossEncoder
+
+# Stage 1: Fast bi-encoder retrieval
+encoder = SentenceTransformer("matulichpt/RadLITE-Encoder")
+# Stage 2: Precise cross-encoder reranking
+reranker = CrossEncoder("matulichpt/RadLITE-Reranker", max_length=512)
+
+def two_stage_search(query: str, corpus: list, top_k: int = 10):
+    # Stage 1: Get top candidates (fast)
+    query_emb = encoder.encode(query, normalize_embeddings=True)
+    corpus_embs = encoder.encode(corpus, normalize_embeddings=True)
+    scores = query_emb @ corpus_embs.T
+    top_indices = scores.argsort()[-50:][::-1]  # Top 50 candidates
+
+    # Stage 2: Rerank with cross-encoder (precise)
+    candidates = [corpus[i] for i in top_indices]
+    pairs = [[query, doc] for doc in candidates]
+    rerank_scores = reranker.predict(pairs)
+
+    # Apply temperature calibration (recommended: 1.5)
+    rerank_scores = rerank_scores / 1.5
+
+    # Sort by reranked scores
+    reranked = sorted(zip(top_indices, rerank_scores), key=lambda x: x[1], reverse=True)
+    return reranked[:top_k]
+```
+
+## Architecture
+
+```
+Input Text
+    |
+    v
+[RadBERT Tokenizer] --> tokens (max 512)
+    |
+    v
+[RoBERTa Encoder] --> 12 layers, 768 hidden
+    |
+    v
+[Mean Pooling] --> aggregate token embeddings
+    |
+    v
+768-dim embedding vector
+```
+
+## Training Details
+
+- **Base Model**: RadBERT-RoBERTa-4m (pre-trained on 4.42M VA radiology reports)
+- **Fine-tuning**: Contrastive learning on radiology education corpus
+- **Training Samples**: 6.7M query-document pairs
+- **Loss Function**: Multiple Negatives Ranking Loss
+- **Epochs**: 2 (8,400 steps)
+- **Final Spearman**: 0.8454
+
+## Limitations
+
+- **English only**: Trained on English radiology text
+- **Domain-specific**: May underperform on non-radiology medical content
+- **Subspecialty variance**: GU/MSK content has lower performance than Physics/Neuro
+- **512 token limit**: Long documents require chunking
+
+## Citation
+
+```bibtex
+@software{radlite_2026,
+    title = {RadLITE: Calibrated Multi-Stage Retrieval for Radiology Education},
+    author = {Grai Team},
+    year = {2026},
+    month = {January},
+    url = {https://huggingface.co/matulichpt/RadLITE-Encoder},
+    note = {MRR 0.829 on RadLIT-9 benchmark}
+}
+```
+
+## Related Models
+
+- [RadLITE-Reranker](https://huggingface.co/matulichpt/RadLITE-Reranker) - Cross-encoder for reranking
+- [RadBERT-RoBERTa-4m](https://huggingface.co/zzxslp/RadBERT-RoBERTa-4m) - Base model
+
+## License
+
+Apache 2.0 - Free for commercial and research use.

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "RobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "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",
+  "transformers_version": "4.56.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "model_type": "SentenceTransformer",
+  "__version__": {
+    "sentence_transformers": "5.1.1",
+    "transformers": "4.56.2",
+    "pytorch": "2.10.0.dev20251011+cu128"
+  },
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1e5e54f4a42b7e4a337b631bf88c517650f8e9cbb569b56f8f9c92b83b43e8a
+size 498604904

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 512,
+    "do_lower_case": false
+}

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": true,
+    "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 +1,65 @@
+{
+  "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": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}