Upload 41 files
Browse files- added_tokens.json +5 -0
- config.json +74 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- onnx/decoder_model.onnx +3 -0
- onnx/decoder_model_bnb4.onnx +3 -0
- onnx/decoder_model_fp16.onnx +3 -0
- onnx/decoder_model_int8.onnx +3 -0
- onnx/decoder_model_merged.onnx +3 -0
- onnx/decoder_model_merged_bnb4.onnx +3 -0
- onnx/decoder_model_merged_fp16.onnx +3 -0
- onnx/decoder_model_merged_int8.onnx +3 -0
- onnx/decoder_model_merged_q4.onnx +3 -0
- onnx/decoder_model_merged_q4f16.onnx +3 -0
- onnx/decoder_model_merged_quantized.onnx +3 -0
- onnx/decoder_model_merged_uint8.onnx +3 -0
- onnx/decoder_model_q4.onnx +3 -0
- onnx/decoder_model_q4f16.onnx +3 -0
- onnx/decoder_model_quantized.onnx +3 -0
- onnx/decoder_model_uint8.onnx +3 -0
- onnx/decoder_with_past_model.onnx +3 -0
- onnx/decoder_with_past_model_bnb4.onnx +3 -0
- onnx/decoder_with_past_model_fp16.onnx +3 -0
- onnx/decoder_with_past_model_int8.onnx +3 -0
- onnx/decoder_with_past_model_q4.onnx +3 -0
- onnx/decoder_with_past_model_q4f16.onnx +3 -0
- onnx/decoder_with_past_model_quantized.onnx +3 -0
- onnx/decoder_with_past_model_uint8.onnx +3 -0
- onnx/encoder_model.onnx +3 -0
- onnx/encoder_model_bnb4.onnx +3 -0
- onnx/encoder_model_fp16.onnx +3 -0
- onnx/encoder_model_int8.onnx +3 -0
- onnx/encoder_model_q4.onnx +3 -0
- onnx/encoder_model_q4f16.onnx +3 -0
- onnx/encoder_model_quantized.onnx +3 -0
- onnx/encoder_model_uint8.onnx +3 -0
- quantize_config.json +18 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +86 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<LEVEL_ADVANCED>": 50265,
|
| 3 |
+
"<LEVEL_ELEMENTARY>": 50267,
|
| 4 |
+
"<LEVEL_SECONDARY>": 50266
|
| 5 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_attn_implementation_autoset": true,
|
| 3 |
+
"_name_or_path": "pabRomero/BART-Firefox-Simplification",
|
| 4 |
+
"activation_dropout": 0.1,
|
| 5 |
+
"activation_function": "gelu",
|
| 6 |
+
"add_bias_logits": false,
|
| 7 |
+
"add_final_layer_norm": false,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"BartForConditionalGeneration"
|
| 10 |
+
],
|
| 11 |
+
"attention_dropout": 0.1,
|
| 12 |
+
"bos_token_id": 0,
|
| 13 |
+
"classif_dropout": 0.1,
|
| 14 |
+
"classifier_dropout": 0.0,
|
| 15 |
+
"d_model": 768,
|
| 16 |
+
"decoder_attention_heads": 12,
|
| 17 |
+
"decoder_ffn_dim": 3072,
|
| 18 |
+
"decoder_layerdrop": 0.0,
|
| 19 |
+
"decoder_layers": 6,
|
| 20 |
+
"decoder_start_token_id": 2,
|
| 21 |
+
"dropout": 0.1,
|
| 22 |
+
"early_stopping": null,
|
| 23 |
+
"encoder_attention_heads": 12,
|
| 24 |
+
"encoder_ffn_dim": 3072,
|
| 25 |
+
"encoder_layerdrop": 0.0,
|
| 26 |
+
"encoder_layers": 6,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"forced_eos_token_id": 2,
|
| 29 |
+
"gradient_checkpointing": false,
|
| 30 |
+
"id2label": {
|
| 31 |
+
"0": "LABEL_0",
|
| 32 |
+
"1": "LABEL_1",
|
| 33 |
+
"2": "LABEL_2"
|
| 34 |
+
},
|
| 35 |
+
"init_std": 0.02,
|
| 36 |
+
"is_encoder_decoder": true,
|
| 37 |
+
"label2id": {
|
| 38 |
+
"LABEL_0": 0,
|
| 39 |
+
"LABEL_1": 1,
|
| 40 |
+
"LABEL_2": 2
|
| 41 |
+
},
|
| 42 |
+
"max_position_embeddings": 1024,
|
| 43 |
+
"model_type": "bart",
|
| 44 |
+
"no_repeat_ngram_size": null,
|
| 45 |
+
"normalize_before": false,
|
| 46 |
+
"normalize_embedding": true,
|
| 47 |
+
"num_beams": null,
|
| 48 |
+
"num_hidden_layers": 6,
|
| 49 |
+
"pad_token_id": 1,
|
| 50 |
+
"scale_embedding": false,
|
| 51 |
+
"task_specific_params": {
|
| 52 |
+
"summarization": {
|
| 53 |
+
"length_penalty": 1.0,
|
| 54 |
+
"max_length": 128,
|
| 55 |
+
"min_length": 12,
|
| 56 |
+
"num_beams": 4
|
| 57 |
+
},
|
| 58 |
+
"summarization_cnn": {
|
| 59 |
+
"length_penalty": 2.0,
|
| 60 |
+
"max_length": 142,
|
| 61 |
+
"min_length": 56,
|
| 62 |
+
"num_beams": 4
|
| 63 |
+
},
|
| 64 |
+
"summarization_xsum": {
|
| 65 |
+
"length_penalty": 1.0,
|
| 66 |
+
"max_length": 62,
|
| 67 |
+
"min_length": 11,
|
| 68 |
+
"num_beams": 6
|
| 69 |
+
}
|
| 70 |
+
},
|
| 71 |
+
"transformers_version": "4.48.3",
|
| 72 |
+
"use_cache": true,
|
| 73 |
+
"vocab_size": 50268
|
| 74 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_bos_token_id": 0,
|
| 8 |
+
"forced_eos_token_id": 2,
|
| 9 |
+
"no_repeat_ngram_size": 3,
|
| 10 |
+
"num_beams": 4,
|
| 11 |
+
"pad_token_id": 1,
|
| 12 |
+
"transformers_version": "4.48.3"
|
| 13 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
onnx/decoder_model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b0d8456dc45604408d8e68be52ef5ee2963a153c84c3bb8d6cf4da8f66338e4
|
| 3 |
+
size 539121264
|
onnx/decoder_model_bnb4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c668b4574d9e321758058d104df1554d095967ea4ea555b457f7097fb481e46
|
| 3 |
+
size 211781316
|
onnx/decoder_model_fp16.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8dec3e8534a13a319fe79cdceee8430cb5db3df8e4af92f40e87520bd6cc32a
|
| 3 |
+
size 269699620
|
onnx/decoder_model_int8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae58ea5388d12e74e962c39f997516ad5a251b06427183c400cc68d5ae6e93b4
|
| 3 |
+
size 135878754
|
onnx/decoder_model_merged.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3406bd8f43cae40b1de5385c57711874d8aa1729ecfb05f7030cbcd9b3b5ec69
|
| 3 |
+
size 539652680
|
onnx/decoder_model_merged_bnb4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3070b6c0e1e99ed05f53808f73b0586fb3fca57ef1ce4423fffccf66436bd65
|
| 3 |
+
size 212319906
|
onnx/decoder_model_merged_fp16.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:faf70c580eed4519d52be7aded448a005db73fc800dc22338201dcadd9df3f9d
|
| 3 |
+
size 525495782
|
onnx/decoder_model_merged_int8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1633f48b95b8dad849ca91501a0102f08b8376cc857bb0e8d2366680d391e603
|
| 3 |
+
size 136471791
|
onnx/decoder_model_merged_q4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74e3bb6abf4f4cd60d44a448eaecf9abbc17c63aba5f513314a50b6e36ac0f2b
|
| 3 |
+
size 218270833
|
onnx/decoder_model_merged_q4f16.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4176cbffd24a6bdceb0c6207ed04c70392e51853a52f58c026a9e91a7989bccf
|
| 3 |
+
size 261905531
|
onnx/decoder_model_merged_quantized.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1633f48b95b8dad849ca91501a0102f08b8376cc857bb0e8d2366680d391e603
|
| 3 |
+
size 136471791
|
onnx/decoder_model_merged_uint8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:122f425d1f66edebefcbb627f46a24436ca0aadc8995cc4068d0d01f9a4910c4
|
| 3 |
+
size 136471791
|
onnx/decoder_model_q4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2d2b9d4fa06bcd2ada83dfd9e3b1899bde0ce5c92214198d17c9fbfaad5917d
|
| 3 |
+
size 217732684
|
onnx/decoder_model_q4f16.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09a72ea412086c54b25367a04d5c7cc1d7477eb463ed880ed5a4a5df76f9f4eb
|
| 3 |
+
size 132817184
|
onnx/decoder_model_quantized.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae58ea5388d12e74e962c39f997516ad5a251b06427183c400cc68d5ae6e93b4
|
| 3 |
+
size 135878754
|
onnx/decoder_model_uint8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d317757e9fced3fc291a69ffc7fdbf30007c58ef65edbcd198e709fce38f11ce
|
| 3 |
+
size 135878754
|
onnx/decoder_with_past_model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3469a20d65f9dc19670badcab313357192c2f9acfb276fbfce9095e885f97c8d
|
| 3 |
+
size 510705312
|
onnx/decoder_with_past_model_bnb4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9ac84005022e802bec38a634e3c3eee9bd6b9f675b9a7b55a01da3b51a6c110
|
| 3 |
+
size 207693744
|
onnx/decoder_with_past_model_fp16.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e83076aae4c60ee423f2838da46d878f01a382aa4edda3d5b7931d229bb10249
|
| 3 |
+
size 255460703
|
onnx/decoder_with_past_model_int8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c95205185f014fa7cfdc780a4133800b23e2b9139f43a10cf646b5c1996f7ec
|
| 3 |
+
size 128638461
|
onnx/decoder_with_past_model_q4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d19ecb1229b18a5afe557b9611c331a9e881e5bfb9ea4df891ee364bb999229
|
| 3 |
+
size 213202828
|
onnx/decoder_with_past_model_q4f16.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40510e5e1224044c743f7e6763f63bdc29565f4fa2a58879dc2545453eafe024
|
| 3 |
+
size 128750932
|
onnx/decoder_with_past_model_quantized.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c95205185f014fa7cfdc780a4133800b23e2b9139f43a10cf646b5c1996f7ec
|
| 3 |
+
size 128638461
|
onnx/decoder_with_past_model_uint8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4bdb85a42bcb93794b6a7ff39787f04f0c08534b211cc31d7d4e21b3fee44b2e
|
| 3 |
+
size 128638461
|
onnx/encoder_model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b18ba5c33796e5d9d4a8a912fc0defe0c399aa7888cdeadad6db2b5170feb056
|
| 3 |
+
size 327813481
|
onnx/encoder_model_bnb4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab40909866c82171e90a9d7ad709b518c0435b20bf1c29accfe06a3f58865682
|
| 3 |
+
size 181837663
|
onnx/encoder_model_fp16.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65d29627e50163152cd0576cb5f31b989c74220255cbfa4d2d22f6bec908cffa
|
| 3 |
+
size 163968377
|
onnx/encoder_model_int8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7c8ea90d02faa9ad71b80006da91f9ca182397ae2527f630aa70148dcd7ca0e
|
| 3 |
+
size 82474768
|
onnx/encoder_model_q4.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:619a18f3f12a916f46c9844d91c7b93be32519e7e80fd355adc144fddeff4bad
|
| 3 |
+
size 184491607
|
onnx/encoder_model_q4f16.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2bded7f0edf68674e6a08986e742f834a54c1c281ebd7d40eac98ccf9332f404
|
| 3 |
+
size 102927000
|
onnx/encoder_model_quantized.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7c8ea90d02faa9ad71b80006da91f9ca182397ae2527f630aa70148dcd7ca0e
|
| 3 |
+
size 82474768
|
onnx/encoder_model_uint8.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35124ae8f14a76ff97f1a630831eb2414db40c4b874dbe9adfded45f6d50023a
|
| 3 |
+
size 82474768
|
quantize_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"modes": [
|
| 3 |
+
"fp16",
|
| 4 |
+
"q8",
|
| 5 |
+
"int8",
|
| 6 |
+
"uint8",
|
| 7 |
+
"q4",
|
| 8 |
+
"q4f16",
|
| 9 |
+
"bnb4"
|
| 10 |
+
],
|
| 11 |
+
"per_channel": true,
|
| 12 |
+
"reduce_range": true,
|
| 13 |
+
"block_size": null,
|
| 14 |
+
"is_symmetric": true,
|
| 15 |
+
"accuracy_level": null,
|
| 16 |
+
"quant_type": 1,
|
| 17 |
+
"op_block_list": null
|
| 18 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"50265": {
|
| 45 |
+
"content": "<LEVEL_ADVANCED>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": false
|
| 51 |
+
},
|
| 52 |
+
"50266": {
|
| 53 |
+
"content": "<LEVEL_SECONDARY>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": true,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": false
|
| 59 |
+
},
|
| 60 |
+
"50267": {
|
| 61 |
+
"content": "<LEVEL_ELEMENTARY>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": true,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": false
|
| 67 |
+
}
|
| 68 |
+
},
|
| 69 |
+
"bos_token": "<s>",
|
| 70 |
+
"clean_up_tokenization_spaces": true,
|
| 71 |
+
"cls_token": "<s>",
|
| 72 |
+
"eos_token": "</s>",
|
| 73 |
+
"errors": "replace",
|
| 74 |
+
"extra_special_tokens": {},
|
| 75 |
+
"mask_token": "<mask>",
|
| 76 |
+
"max_length": 80,
|
| 77 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 78 |
+
"pad_token": "<pad>",
|
| 79 |
+
"sep_token": "</s>",
|
| 80 |
+
"stride": 0,
|
| 81 |
+
"tokenizer_class": "BartTokenizer",
|
| 82 |
+
"trim_offsets": true,
|
| 83 |
+
"truncation_side": "right",
|
| 84 |
+
"truncation_strategy": "longest_first",
|
| 85 |
+
"unk_token": "<unk>"
|
| 86 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|