Fan Jiang
commited on
Commit
•
36f915b
1
Parent(s):
45f37dd
upload checkpoint
Browse files- config.json +41 -0
- dev_reader_xor_eng_span_predictions.json +0 -0
- dev_xor_retrieve_pids.jsonl +0 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +5 -0
- spiece.model +3 -0
- tokenizer_config.json +12 -0
config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "checkpoints/de-experiments/xor-retrieve-english-span-mt5-mss-distill-unsupervised-parallel-augmentation-ICL-mss-target-anchor-pretrain-nq/checkpoint-best",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RRForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"barlow_twins": false,
|
| 7 |
+
"d_ff": 2816,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 1024,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "gelu_new",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "gated-gelu",
|
| 15 |
+
"id2label": {
|
| 16 |
+
"0": "LABEL_0"
|
| 17 |
+
},
|
| 18 |
+
"initializer_factor": 1.0,
|
| 19 |
+
"is_encoder_decoder": true,
|
| 20 |
+
"is_gated_act": true,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"LABEL_0": 0
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_epsilon": 1e-06,
|
| 25 |
+
"model_type": "mt5",
|
| 26 |
+
"n_passages": 100,
|
| 27 |
+
"num_decoder_layers": 24,
|
| 28 |
+
"num_heads": 16,
|
| 29 |
+
"num_layers": 24,
|
| 30 |
+
"output_past": true,
|
| 31 |
+
"pad_token_id": 0,
|
| 32 |
+
"relative_attention_max_distance": 128,
|
| 33 |
+
"relative_attention_num_buckets": 32,
|
| 34 |
+
"retriever_layer": 12,
|
| 35 |
+
"tie_word_embeddings": false,
|
| 36 |
+
"tokenizer_class": "T5Tokenizer",
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.30.2",
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 250112
|
| 41 |
+
}
|
dev_reader_xor_eng_span_predictions.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
dev_xor_retrieve_pids.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.30.2"
|
| 7 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10b12d33f77caaf389acf2814826402eb14b27a3d2e7874ce80a11ad087c0ae9
|
| 3 |
+
size 4926912921
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": "</s>",
|
| 3 |
+
"pad_token": "<pad>",
|
| 4 |
+
"unk_token": "<unk>"
|
| 5 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
| 3 |
+
size 4309802
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": null,
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"extra_ids": 0,
|
| 6 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
+
"pad_token": "<pad>",
|
| 8 |
+
"sp_model_kwargs": {},
|
| 9 |
+
"tokenizer_class": "T5Tokenizer",
|
| 10 |
+
"tokenizer_file": null,
|
| 11 |
+
"unk_token": "<unk>"
|
| 12 |
+
}
|