Commit
·
453692c
1
Parent(s):
398af80
Updated Model
Browse files- README.md +102 -2
- config.json +76 -0
- generation_config.json +14 -0
- gitattributes.txt +34 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
CHANGED
|
@@ -1,3 +1,103 @@
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
datasets:
|
| 3 |
+
- samsum
|
| 4 |
+
pipeline_tag: summarization
|
| 5 |
+
|
| 6 |
+
widget:
|
| 7 |
+
- text: >
|
| 8 |
+
Laurie: So, what are your plans for this weekend?
|
| 9 |
+
|
| 10 |
+
Christie: I don’t know. Do you want to get together or something?
|
| 11 |
+
|
| 12 |
+
Sarah: How about going to see a movie? Cinemax 26 on Carson Boulevard is showing Enchanted.
|
| 13 |
+
Laurie: That sounds like a good idea. Maybe we should go out to eat beforehand.
|
| 14 |
+
|
| 15 |
+
Sarah: It is fine with me. Where do you want to meet?
|
| 16 |
+
|
| 17 |
+
Christie: Let’s meet at Summer Pizza House. I have not gone there for a long time.
|
| 18 |
+
|
| 19 |
+
Laurie: Good idea again. I heard they just came up with a new pizza. It should be good because Summer Pizza House always has the best pizza in town.
|
| 20 |
+
|
| 21 |
+
Sarah: When should we meet?
|
| 22 |
+
|
| 23 |
+
Christie: Well, the movie is shown at 2:00PM, 4:00PM, 6:00PM and 8:00PM.
|
| 24 |
+
|
| 25 |
+
Laurie: Why don’t we go to the 2:00PM show? We can meet at Summer Pizza House at noon. That will give us plenty of time to enjoy our pizza.
|
| 26 |
+
|
| 27 |
+
Sarah: My cousin Karen is in town. Can I bring her along? I hate to leave her home alone.
|
| 28 |
+
|
| 29 |
+
Christie: Karen is in town? Yes, bring her along. Laurie, you remember Karen? We met her at Sara’s high school graduation party two years ago.
|
| 30 |
+
|
| 31 |
+
Laurie: I do not quite remember her. What does she look like?
|
| 32 |
+
|
| 33 |
+
Sarah: She has blond hair, she is kind of slender, and she is about your height.
|
| 34 |
+
|
| 35 |
+
Laurie: She wears eyeglasses, right?
|
| 36 |
+
|
| 37 |
+
Sarah: Yes, and she was playing the piano off and on during the party.
|
| 38 |
+
|
| 39 |
+
Laurie: I remember her now. Yes, do bring her along Sara. She is such a nice person, and funny too.
|
| 40 |
+
|
| 41 |
+
Sarah: She will be happy to meet both of you again.
|
| 42 |
+
|
| 43 |
+
Christie: What is she doing these days?
|
| 44 |
+
|
| 45 |
+
Sarah: She graduated last June, and she will start her teaching career next week when the new school term begins.
|
| 46 |
+
|
| 47 |
+
Laurie: What grade is she going to teach?
|
| 48 |
+
|
| 49 |
+
Sarah: She will teach kindergarten. She loves working with kids, and she always has such a good rapport with them
|
| 50 |
+
|
| 51 |
+
Christie: Kindergarten? She must be a very patient person. I always think kindergarten is the most difficult class to teach. Most of the kids have never been to school, and they have
|
| 52 |
+
e never been away from mommy for long.
|
| 53 |
+
|
| 54 |
+
Sarah: I think Karen will do fine. She knows how to handle young children
|
| 55 |
+
|
| 56 |
+
Laurie: I think the first few weeks will be tough. However, once the routine is set, it should not be too difficult to teach kindergarten.
|
| 57 |
+
|
| 58 |
+
Christie: You are right. The kids might even look forward to going to school since they have so many friends to play with.
|
| 59 |
+
|
| 60 |
+
Sarah: There are so many new things for them to do at school too. They do a lot of crafts in kindergarten. I am always amazed by the things kindergarten teachers do.
|
| 61 |
+
|
| 62 |
+
Laurie: Yes, I have seen my niece come home with so many neat stuff.
|
| 63 |
+
|
| 64 |
+
Christie: Maybe we can ask Karen to show us some of the things that we can do for this Halloween.
|
| 65 |
+
|
| 66 |
+
Laurie: Maybe we can stop by the craft store after the movie. What do you think, Sara?
|
| 67 |
+
|
| 68 |
+
Sarah: I will talk to her. I think she will like that. It will help her with school projects when Halloween comes.
|
| 69 |
+
|
| 70 |
+
Christie: Michael’s is a good store for crafts. It always carries a variety of things, and you can find almost anything there.
|
| 71 |
+
|
| 72 |
+
Laurie: There is a Michaels store not far away from Cinemax 26. I believe it is just around the corner, on Pioneer Avenue. We can even walk over there.
|
| 73 |
+
|
| 74 |
+
Sarah: So, we plan to meet for pizza at noon, go to the movies at two, and shop at Michael’s afterward. Right?
|
| 75 |
+
|
| 76 |
+
Laurie and Christie: Yes.
|
| 77 |
+
model-index:
|
| 78 |
+
- name: bart-large-cnn-samsum
|
| 79 |
+
results:
|
| 80 |
+
- task:
|
| 81 |
+
type: summarization
|
| 82 |
+
name: Conversation Summarization
|
| 83 |
+
dataset:
|
| 84 |
+
name: >-
|
| 85 |
+
SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive
|
| 86 |
+
Summarization
|
| 87 |
+
type: samsum
|
| 88 |
+
metrics:
|
| 89 |
+
- type: rogue-1
|
| 90 |
+
value: 54.8764
|
| 91 |
+
name: Validation ROGUE-1
|
| 92 |
+
- type: rogue-2
|
| 93 |
+
value: 29.6869,
|
| 94 |
+
name: Validation ROGUE-2
|
| 95 |
+
- type: rogue-l
|
| 96 |
+
value: 44.9874
|
| 97 |
+
name: Validation ROGUE-L
|
| 98 |
+
- type: loss
|
| 99 |
+
value: 1.47812
|
| 100 |
+
name: loss
|
| 101 |
+
|
| 102 |
+
|
| 103 |
+
---
|
config.json
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/bart-large-xsum",
|
| 3 |
+
"_num_labels": 3,
|
| 4 |
+
"activation_dropout": 0.0,
|
| 5 |
+
"activation_function": "gelu",
|
| 6 |
+
"add_bias_logits": false,
|
| 7 |
+
"add_final_layer_norm": false,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"BartForConditionalGeneration"
|
| 10 |
+
],
|
| 11 |
+
"attention_dropout": 0.0,
|
| 12 |
+
"bos_token_id": 0,
|
| 13 |
+
"classif_dropout": 0.0,
|
| 14 |
+
"classifier_dropout": 0.0,
|
| 15 |
+
"d_model": 1024,
|
| 16 |
+
"decoder_attention_heads": 16,
|
| 17 |
+
"decoder_ffn_dim": 4096,
|
| 18 |
+
"decoder_layerdrop": 0.0,
|
| 19 |
+
"decoder_layers": 12,
|
| 20 |
+
"decoder_start_token_id": 2,
|
| 21 |
+
"dropout": 0.1,
|
| 22 |
+
"early_stopping": true,
|
| 23 |
+
"encoder_attention_heads": 16,
|
| 24 |
+
"encoder_ffn_dim": 4096,
|
| 25 |
+
"encoder_layerdrop": 0.0,
|
| 26 |
+
"encoder_layers": 12,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"eos_token_ids": [
|
| 29 |
+
2
|
| 30 |
+
],
|
| 31 |
+
"forced_eos_token_id": 2,
|
| 32 |
+
"gradient_checkpointing": false,
|
| 33 |
+
"id2label": {
|
| 34 |
+
"0": "LABEL_0",
|
| 35 |
+
"1": "LABEL_1",
|
| 36 |
+
"2": "LABEL_2"
|
| 37 |
+
},
|
| 38 |
+
"init_std": 0.02,
|
| 39 |
+
"is_encoder_decoder": true,
|
| 40 |
+
"label2id": {
|
| 41 |
+
"LABEL_0": 0,
|
| 42 |
+
"LABEL_1": 1,
|
| 43 |
+
"LABEL_2": 2
|
| 44 |
+
},
|
| 45 |
+
"max_length": 62,
|
| 46 |
+
"max_position_embeddings": 1024,
|
| 47 |
+
"min_length": 11,
|
| 48 |
+
"model_type": "bart",
|
| 49 |
+
"no_repeat_ngram_size": 3,
|
| 50 |
+
"normalize_before": false,
|
| 51 |
+
"normalize_embedding": true,
|
| 52 |
+
"num_beams": 6,
|
| 53 |
+
"num_hidden_layers": 12,
|
| 54 |
+
"output_past": true,
|
| 55 |
+
"pad_token_id": 1,
|
| 56 |
+
"prefix": " ",
|
| 57 |
+
"replacing_rate": 0,
|
| 58 |
+
"scale_embedding": false,
|
| 59 |
+
"static_position_embeddings": false,
|
| 60 |
+
"student_decoder_layers": null,
|
| 61 |
+
"student_encoder_layers": null,
|
| 62 |
+
"task_specific_params": {
|
| 63 |
+
"summarization": {
|
| 64 |
+
"early_stopping": true,
|
| 65 |
+
"length_penalty": 2.0,
|
| 66 |
+
"max_length": 142,
|
| 67 |
+
"min_length": 56,
|
| 68 |
+
"no_repeat_ngram_size": 3,
|
| 69 |
+
"num_beams": 4
|
| 70 |
+
}
|
| 71 |
+
},
|
| 72 |
+
"torch_dtype": "float32",
|
| 73 |
+
"transformers_version": "4.26.0",
|
| 74 |
+
"use_cache": true,
|
| 75 |
+
"vocab_size": 50264
|
| 76 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"early_stopping": true,
|
| 6 |
+
"eos_token_id": 2,
|
| 7 |
+
"forced_eos_token_id": 2,
|
| 8 |
+
"max_length": 62,
|
| 9 |
+
"min_length": 11,
|
| 10 |
+
"no_repeat_ngram_size": 3,
|
| 11 |
+
"num_beams": 6,
|
| 12 |
+
"pad_token_id": 1,
|
| 13 |
+
"transformers_version": "4.26.0"
|
| 14 |
+
}
|
gitattributes.txt
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48c2a7c14073903e786d0299e4bc4d9b54ff68b64ecd6b022d30318c1748a1c9
|
| 3 |
+
size 1625537293
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"errors": "replace",
|
| 7 |
+
"mask_token": "<mask>",
|
| 8 |
+
"model_max_length": 1024,
|
| 9 |
+
"name_or_path": "facebook/bart-large-xsum",
|
| 10 |
+
"pad_token": "<pad>",
|
| 11 |
+
"sep_token": "</s>",
|
| 12 |
+
"special_tokens_map_file": null,
|
| 13 |
+
"tokenizer_class": "BartTokenizer",
|
| 14 |
+
"trim_offsets": true,
|
| 15 |
+
"unk_token": "<unk>"
|
| 16 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba7aa1fbf15dcb9783f587f16c1e1b0e48461eff10e83ac003e008a9b1cba17d
|
| 3 |
+
size 3643
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|