Upload folder using huggingface_hub

learned_verifier/DeepSet/deepset_weight.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97dd0328a9bf63471ead5b4341ece7c5a3affc9ed34420318d8a0e75357a8306
+size 532808

learned_verifier/DeepSet/model_cfg.py

@@ -0,0 +1,25 @@
+import torch
+import torch.nn as nn
+
+class DeepSetClassifier(nn.Module):
+    def __init__(self, hidden_dim=256):
+        super().__init__()
+        self.phi = nn.Sequential(
+            nn.Linear(1, hidden_dim),
+            nn.ReLU(),
+            nn.Linear(hidden_dim, hidden_dim)
+        )
+        self.rho = nn.Sequential(
+            nn.Linear(hidden_dim, hidden_dim),
+            nn.ReLU(),
+            nn.Linear(hidden_dim, 1)
+        )
+
+    def forward(self, x, lengths):
+        phi_x = self.phi(x)             # [B, T, D]
+        mask = torch.arange(x.size(1)).unsqueeze(0).to(x.device) < lengths.unsqueeze(1)
+        mask = mask.unsqueeze(-1)       # [B, T, 1]
+        phi_x = phi_x * mask 
+        agg = phi_x.sum(dim=1) / lengths.unsqueeze(-1)  # Mean pooling
+        out = self.rho(agg)
+        return torch.sigmoid(out).squeeze(-1)

learned_verifier/RNN/model_cfg.py

@@ -0,0 +1,26 @@
+import torch
+import torch.nn as nn
+
+class RNNClassifier(nn.Module):
+    def __init__(self, hidden_dim=256, rnn_type='GRU'):
+        super().__init__()
+        self.rnn_type = rnn_type.upper()
+        if self.rnn_type == 'LSTM':
+            self.rnn = nn.LSTM(input_size=1, hidden_size=hidden_dim, batch_first=True)
+        else:
+            self.rnn = nn.GRU(input_size=1, hidden_size=hidden_dim, batch_first=True)
+        self.classifier = nn.Sequential(
+            nn.Linear(hidden_dim, hidden_dim),
+            nn.ReLU(),
+            nn.Linear(hidden_dim, 1)
+        )
+
+    def forward(self, x, lengths):
+        packed_x = nn.utils.rnn.pack_padded_sequence(x, lengths.cpu(), batch_first=True, enforce_sorted=False)
+        if self.rnn_type == 'LSTM':
+            packed_out, (hn, cn) = self.rnn(packed_x)
+        else:
+            packed_out, hn = self.rnn(packed_x)
+        last_hidden = hn[-1]  
+        out = self.classifier(last_hidden)
+        return torch.sigmoid(out).squeeze(-1)

learned_verifier/RNN/rnn_gru_weight.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d39d06b2d1a0cdd0be92226cb38b74addbf66ecd7650df35e15b74277e69563
+size 1062848

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/embedding_model/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "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
+}

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/embedding_model/README.md

@@ -0,0 +1,141 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+base_model: sentence-transformers/all-MiniLM-L12-v2
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# SentenceTransformer based on sentence-transformers/all-MiniLM-L12-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [sentence-transformers/all-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2) <!-- at revision c004d8e3e901237d8fa7e9fff12774962e391ce5 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 384 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, '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})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'The weather is lovely today.',
+    "It's so sunny outside!",
+    'He drove to the stadium.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Framework Versions
+- Python: 3.12.0
+- Sentence Transformers: 4.0.2
+- Transformers: 4.47.1
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.6.0
+- Datasets: 3.5.0
+- Tokenizers: 0.21.1
+
+## Citation
+
+### BibTeX
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/embedding_model/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "sentence-transformers/all-MiniLM-L12-v2",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/embedding_model/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.0.2",
+    "transformers": "4.47.1",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/embedding_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32ed5a30285dd435b59979b997f7d1c337486ad0b53d3ac0bfc78d779368452e
+size 133462128

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/embedding_model/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"
+  }
+]

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/embedding_model/sentence_bert_config.json

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

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/embedding_model/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/embedding_model/tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/epoch-1/embedding_model/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "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
+}

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/epoch-1/embedding_model/README.md

@@ -0,0 +1,141 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+base_model: sentence-transformers/all-MiniLM-L12-v2
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# SentenceTransformer based on sentence-transformers/all-MiniLM-L12-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [sentence-transformers/all-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2) <!-- at revision c004d8e3e901237d8fa7e9fff12774962e391ce5 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 384 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, '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})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'The weather is lovely today.',
+    "It's so sunny outside!",
+    'He drove to the stadium.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Framework Versions
+- Python: 3.12.0
+- Sentence Transformers: 4.0.2
+- Transformers: 4.47.1
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.6.0
+- Datasets: 3.5.0
+- Tokenizers: 0.21.1
+
+## Citation
+
+### BibTeX
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/epoch-1/embedding_model/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "sentence-transformers/all-MiniLM-L12-v2",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/epoch-1/embedding_model/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.0.2",
+    "transformers": "4.47.1",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/epoch-1/embedding_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32ed5a30285dd435b59979b997f7d1c337486ad0b53d3ac0bfc78d779368452e
+size 133462128

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/epoch-1/embedding_model/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"
+  }
+]

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/epoch-1/embedding_model/sentence_bert_config.json

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

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/epoch-1/embedding_model/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/epoch-1/embedding_model/tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/epoch-1/matching_head.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aacc21e97f1aa605d23d6a621dc07a0206ad2aed1af4a8aa33bba904d8c9cc15
+size 1580740

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/epoch-2/embedding_model/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "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
+}

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/epoch-2/embedding_model/README.md

@@ -0,0 +1,141 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+base_model: sentence-transformers/all-MiniLM-L12-v2
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# SentenceTransformer based on sentence-transformers/all-MiniLM-L12-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [sentence-transformers/all-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2) <!-- at revision c004d8e3e901237d8fa7e9fff12774962e391ce5 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 384 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, '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})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'The weather is lovely today.',
+    "It's so sunny outside!",
+    'He drove to the stadium.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Framework Versions
+- Python: 3.12.0
+- Sentence Transformers: 4.0.2
+- Transformers: 4.47.1
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.6.0
+- Datasets: 3.5.0
+- Tokenizers: 0.21.1
+
+## Citation
+
+### BibTeX
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/epoch-2/embedding_model/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "sentence-transformers/all-MiniLM-L12-v2",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/epoch-2/embedding_model/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.0.2",
+    "transformers": "4.47.1",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/epoch-2/embedding_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32ed5a30285dd435b59979b997f7d1c337486ad0b53d3ac0bfc78d779368452e
+size 133462128

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/epoch-2/embedding_model/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"
+  }
+]

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/epoch-2/embedding_model/sentence_bert_config.json

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

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/epoch-2/embedding_model/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/epoch-2/embedding_model/tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/epoch-2/matching_head.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acd640984ef7971658643bbcd52e5a359141b6c24b4c438e4b7c3730a41f0a9e
+size 1580740

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/epoch-3/embedding_model/1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "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
+}

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/epoch-3/embedding_model/README.md

@@ -0,0 +1,141 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+base_model: sentence-transformers/all-MiniLM-L12-v2
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# SentenceTransformer based on sentence-transformers/all-MiniLM-L12-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [sentence-transformers/all-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2) <!-- at revision c004d8e3e901237d8fa7e9fff12774962e391ce5 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 384 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, '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})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'The weather is lovely today.',
+    "It's so sunny outside!",
+    'He drove to the stadium.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Framework Versions
+- Python: 3.12.0
+- Sentence Transformers: 4.0.2
+- Transformers: 4.47.1
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.6.0
+- Datasets: 3.5.0
+- Tokenizers: 0.21.1
+
+## Citation
+
+### BibTeX
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/epoch-3/embedding_model/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "sentence-transformers/all-MiniLM-L12-v2",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/epoch-3/embedding_model/config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.0.2",
+    "transformers": "4.47.1",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/epoch-3/embedding_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32ed5a30285dd435b59979b997f7d1c337486ad0b53d3ac0bfc78d779368452e
+size 133462128

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/epoch-3/embedding_model/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"
+  }
+]

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/epoch-3/embedding_model/sentence_bert_config.json

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

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/epoch-3/embedding_model/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

matching_head_BlockToAnswer/1024/train_all-MiniLM-L12-v2_mixed_pos_merged_4_domain_0.5_hard_easy_mixed_neg_4_domain_limit0_cos_sim_focal_freeze/epoch-3/embedding_model/tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}