Duplicate from facebook/bart-large-xsum

Co-authored-by: Julien Chaumond <julien-c@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,9 @@
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,153 @@
+---
+tags:
+- summarization
+language:
+- en
+license: mit
+model-index:
+- name: facebook/bart-large-xsum
+  results:
+  - task:
+      type: summarization
+      name: Summarization
+    dataset:
+      name: cnn_dailymail
+      type: cnn_dailymail
+      config: 3.0.0
+      split: test
+    metrics:
+    - name: ROUGE-1
+      type: rouge
+      value: 25.2697
+      verified: true
+    - name: ROUGE-2
+      type: rouge
+      value: 7.6638
+      verified: true
+    - name: ROUGE-L
+      type: rouge
+      value: 17.1808
+      verified: true
+    - name: ROUGE-LSUM
+      type: rouge
+      value: 21.7933
+      verified: true
+    - name: loss
+      type: loss
+      value: 3.5042972564697266
+      verified: true
+    - name: gen_len
+      type: gen_len
+      value: 27.4462
+      verified: true
+  - task:
+      type: summarization
+      name: Summarization
+    dataset:
+      name: xsum
+      type: xsum
+      config: default
+      split: test
+    metrics:
+    - name: ROUGE-1
+      type: rouge
+      value: 45.4525
+      verified: true
+    - name: ROUGE-2
+      type: rouge
+      value: 22.3455
+      verified: true
+    - name: ROUGE-L
+      type: rouge
+      value: 37.2302
+      verified: true
+    - name: ROUGE-LSUM
+      type: rouge
+      value: 37.2323
+      verified: true
+    - name: loss
+      type: loss
+      value: 2.3128726482391357
+      verified: true
+    - name: gen_len
+      type: gen_len
+      value: 25.5435
+      verified: true
+  - task:
+      type: summarization
+      name: Summarization
+    dataset:
+      name: samsum
+      type: samsum
+      config: samsum
+      split: train
+    metrics:
+    - name: ROUGE-1
+      type: rouge
+      value: 24.7852
+      verified: true
+    - name: ROUGE-2
+      type: rouge
+      value: 5.2533
+      verified: true
+    - name: ROUGE-L
+      type: rouge
+      value: 18.6792
+      verified: true
+    - name: ROUGE-LSUM
+      type: rouge
+      value: 20.629
+      verified: true
+    - name: loss
+      type: loss
+      value: 3.746837854385376
+      verified: true
+    - name: gen_len
+      type: gen_len
+      value: 23.1206
+      verified: true
+  - task:
+      type: summarization
+      name: Summarization
+    dataset:
+      name: samsum
+      type: samsum
+      config: samsum
+      split: test
+    metrics:
+    - name: ROUGE-1
+      type: rouge
+      value: 24.9158
+      verified: true
+    - name: ROUGE-2
+      type: rouge
+      value: 5.5837
+      verified: true
+    - name: ROUGE-L
+      type: rouge
+      value: 18.8935
+      verified: true
+    - name: ROUGE-LSUM
+      type: rouge
+      value: 20.76
+      verified: true
+    - name: loss
+      type: loss
+      value: 3.775235891342163
+      verified: true
+    - name: gen_len
+      type: gen_len
+      value: 23.0928
+      verified: true
+---
+### Bart model finetuned on xsum
+
+docs: https://huggingface.co/transformers/model_doc/bart.html
+
+finetuning: examples/seq2seq/ (as of Aug 20, 2020)
+
+Metrics: ROUGE > 22 on xsum.
+
+variants: search for distilbart
+
+paper: https://arxiv.org/abs/1910.13461

config.json

@@ -0,0 +1,65 @@
+{
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "eos_token_ids": [
+    2
+  ],
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": 62,
+  "max_position_embeddings": 1024,
+  "min_length": 11,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": 6,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "prefix": " ",
+  "replacing_rate": 0,
+  "scale_embedding": false,
+  "static_position_embeddings": false,
+  "student_decoder_layers": null,
+  "student_encoder_layers": null,
+  "task_specific_params": {},
+  "transformers_version": "4.7.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50264
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:120ad3457db00af297272d4fadeb4f49d50ae03c56c08babe3e1963d00df1401
+size 1625380786

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "max_length": 62,
+  "min_length": 11,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 6,
+  "pad_token_id": 1,
+  "transformers_version": "4.27.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40a72b702fcbb97501f537b9fdfacdb3c310590cf08b7fe580d8bbda0f3704d1
+size 1625270765

rust_model.ot

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3706d7f9974a64867550bb5c12cb33fd75d5d60f2f5af0ecd149f684f0308121
+size 2037049424

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48d709daef4a980a0306c3760a7065155abc7ca01963bec21b80bde3c1f640e5
+size 1625692088

tokenizer_config.json

@@ -0,0 +1 @@
+{"model_max_length": 1024}