Add model files

README.md

@@ -1,3 +1,21 @@
 ---
+language:
+  - en
+tags:
+- translation
+- ctranslate2
 license: mit
+base_model: kworts/BARTxiv
 ---
+# BARTxiv-ct2
+This is a version of [kworts/BARTxiv](https://huggingface.co/kworts/BARTxiv) converted for use with [CTranslate2](https://github.com/OpenNMT/CTranslate2).
+The conversion was performed using the following command:
+
+```
+ct2-transformers-converter --model kworts/BARTxiv --output_dir BARTxiv-ct2 \
+    --copy_files merges.txt special_tokens_map.json tokenizer.json \
+    tokenizer_config.json vocab.json
+```
+
+## License
+This adaptation is based on [kworts/BARTxiv](https://huggingface.co/kworts/BARTxiv), originally provided under the MIT License. Modifications were made for compatibility with CTranslate2. Despite these modifications, this adapted version continues to be distributed under the MIT License, honoring the original licensing terms.

config.json

@@ -0,0 +1,10 @@
+{
+  "add_source_bos": false,
+  "add_source_eos": false,
+  "bos_token": "<s>",
+  "decoder_start_token": "</s>",
+  "eos_token": "</s>",
+  "layer_norm_epsilon": null,
+  "multi_query_attention": false,
+  "unk_token": "<unk>"
+}

model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85d054a0747dc07577a0b009b0fc73ddc09330f110eca85f738a438a308d8757
+size 1625167361

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1024,
+  "name_or_path": "facebook/bart-large-cnn",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}