Upload folder using huggingface_hub

README.md

@@ -0,0 +1,56 @@
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- wrmurray/roberta-base-finetuned-imdb
+- Bhumika/roberta-base-finetuned-sst2
+base_model:
+- wrmurray/roberta-base-finetuned-imdb
+- Bhumika/roberta-base-finetuned-sst2
+---
+
+# roberta-movie-sentiment-multimodel-1
+
+roberta-movie-sentiment-multimodel-1 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [wrmurray/roberta-base-finetuned-imdb](https://huggingface.co/wrmurray/roberta-base-finetuned-imdb)
+* [Bhumika/roberta-base-finetuned-sst2](https://huggingface.co/Bhumika/roberta-base-finetuned-sst2)
+
+## 🧩 Configuration
+
+```yaml
+models:
+  - model: wrmurray/roberta-base-finetuned-imdb
+    parameters:
+      weight: 0.5
+  - model: Bhumika/roberta-base-finetuned-sst2
+    parameters:
+      weight: 0.5
+merge_method: linear
+dtype: float16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "EmmanuelM1/roberta-movie-sentiment-multimodel-1"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Bhumika/roberta-base-finetuned-sst2",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float16",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

mergekit_config.yml

@@ -0,0 +1,10 @@
+
+models:
+  - model: wrmurray/roberta-base-finetuned-imdb
+    parameters:
+      weight: 0.5
+  - model: Bhumika/roberta-base-finetuned-sst2
+    parameters:
+      weight: 0.5
+merge_method: linear
+dtype: float16

model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bdf7cca87af603e67bbbba65354c2ae5bad4071a59be42e7d4fe7fae38b309a
+size 249322628

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 249298452}, "weight_map": {"classifier.dense.bias": "model-00001-of-00001.safetensors", "classifier.dense.weight": "model-00001-of-00001.safetensors", "classifier.out_proj.bias": "model-00001-of-00001.safetensors", "classifier.out_proj.weight": "model-00001-of-00001.safetensors", "roberta.embeddings.LayerNorm.bias": "model-00001-of-00001.safetensors", "roberta.embeddings.LayerNorm.weight": "model-00001-of-00001.safetensors", "roberta.embeddings.position_embeddings.weight": "model-00001-of-00001.safetensors", "roberta.embeddings.position_ids": "model-00001-of-00001.safetensors", "roberta.embeddings.token_type_embeddings.weight": "model-00001-of-00001.safetensors", "roberta.embeddings.word_embeddings.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.0.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.0.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.0.attention.output.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.0.attention.output.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.0.attention.self.key.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.0.attention.self.key.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.0.attention.self.query.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.0.attention.self.query.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.0.attention.self.value.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.0.attention.self.value.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.0.intermediate.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.0.intermediate.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.0.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.0.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.0.output.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.0.output.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.1.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.1.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.1.attention.output.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.1.attention.output.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.1.attention.self.key.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.1.attention.self.key.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.1.attention.self.query.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.1.attention.self.query.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.1.attention.self.value.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.1.attention.self.value.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.1.intermediate.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.1.intermediate.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.1.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.1.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.1.output.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.1.output.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.10.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.10.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.10.attention.output.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.10.attention.output.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.10.attention.self.key.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.10.attention.self.key.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.10.attention.self.query.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.10.attention.self.query.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.10.attention.self.value.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.10.attention.self.value.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.10.intermediate.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.10.intermediate.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.10.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.10.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.10.output.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.10.output.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.11.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.11.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.11.attention.output.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.11.attention.output.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.11.attention.self.key.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.11.attention.self.key.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.11.attention.self.query.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.11.attention.self.query.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.11.attention.self.value.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.11.attention.self.value.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.11.intermediate.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.11.intermediate.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.11.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.11.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.11.output.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.11.output.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.2.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.2.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.2.attention.output.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.2.attention.output.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.2.attention.self.key.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.2.attention.self.key.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.2.attention.self.query.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.2.attention.self.query.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.2.attention.self.value.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.2.attention.self.value.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.2.intermediate.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.2.intermediate.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.2.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.2.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.2.output.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.2.output.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.3.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.3.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.3.attention.output.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.3.attention.output.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.3.attention.self.key.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.3.attention.self.key.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.3.attention.self.query.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.3.attention.self.query.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.3.attention.self.value.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.3.attention.self.value.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.3.intermediate.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.3.intermediate.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.3.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.3.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.3.output.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.3.output.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.4.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.4.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.4.attention.output.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.4.attention.output.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.4.attention.self.key.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.4.attention.self.key.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.4.attention.self.query.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.4.attention.self.query.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.4.attention.self.value.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.4.attention.self.value.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.4.intermediate.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.4.intermediate.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.4.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.4.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.4.output.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.4.output.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.5.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.5.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.5.attention.output.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.5.attention.output.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.5.attention.self.key.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.5.attention.self.key.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.5.attention.self.query.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.5.attention.self.query.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.5.attention.self.value.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.5.attention.self.value.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.5.intermediate.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.5.intermediate.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.5.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.5.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.5.output.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.5.output.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.6.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.6.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.6.attention.output.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.6.attention.output.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.6.attention.self.key.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.6.attention.self.key.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.6.attention.self.query.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.6.attention.self.query.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.6.attention.self.value.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.6.attention.self.value.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.6.intermediate.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.6.intermediate.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.6.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.6.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.6.output.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.6.output.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.7.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.7.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.7.attention.output.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.7.attention.output.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.7.attention.self.key.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.7.attention.self.key.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.7.attention.self.query.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.7.attention.self.query.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.7.attention.self.value.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.7.attention.self.value.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.7.intermediate.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.7.intermediate.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.7.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.7.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.7.output.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.7.output.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.8.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.8.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.8.attention.output.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.8.attention.output.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.8.attention.self.key.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.8.attention.self.key.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.8.attention.self.query.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.8.attention.self.query.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.8.attention.self.value.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.8.attention.self.value.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.8.intermediate.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.8.intermediate.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.8.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.8.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.8.output.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.8.output.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.9.attention.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.9.attention.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.9.attention.output.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.9.attention.output.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.9.attention.self.key.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.9.attention.self.key.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.9.attention.self.query.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.9.attention.self.query.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.9.attention.self.value.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.9.attention.self.value.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.9.intermediate.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.9.intermediate.dense.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.9.output.LayerNorm.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.9.output.LayerNorm.weight": "model-00001-of-00001.safetensors", "roberta.encoder.layer.9.output.dense.bias": "model-00001-of-00001.safetensors", "roberta.encoder.layer.9.output.dense.weight": "model-00001-of-00001.safetensors"}}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "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>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}