Commit
·
e66bd8f
1
Parent(s):
dca24c8
Upload 8 files
Browse files- config.json +30 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
- removed.jsonl +0 -0
- special_tokens_map.json +5 -0
- spiece.model +3 -0
- tokenizer_config.json +9 -0
- vocamaru_log.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"MT5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"d_ff": 1024,
|
| 6 |
+
"d_kv": 48,
|
| 7 |
+
"d_model": 256,
|
| 8 |
+
"decoder_start_token_id": 0,
|
| 9 |
+
"dense_act_fn": "gelu_new",
|
| 10 |
+
"dropout_rate": 0.1,
|
| 11 |
+
"eos_token_id": 1,
|
| 12 |
+
"feed_forward_proj": "gated-gelu",
|
| 13 |
+
"initializer_factor": 1.0,
|
| 14 |
+
"is_encoder_decoder": true,
|
| 15 |
+
"is_gated_act": true,
|
| 16 |
+
"layer_norm_epsilon": 1e-06,
|
| 17 |
+
"model_type": "mt5",
|
| 18 |
+
"num_decoder_layers": 12,
|
| 19 |
+
"num_heads": 8,
|
| 20 |
+
"num_layers": 12,
|
| 21 |
+
"pad_token_id": 0,
|
| 22 |
+
"relative_attention_max_distance": 128,
|
| 23 |
+
"relative_attention_num_buckets": 32,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"tokenizer_class": "T5Tokenizer",
|
| 26 |
+
"torch_dtype": "float32",
|
| 27 |
+
"transformers_version": "4.26.1",
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 32200
|
| 30 |
+
}
|
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": "4.26.1"
|
| 7 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f002cc1d35a61df64b57976ec402fcf1dd3f0275c22d95734cfadaea5ac8d4cc
|
| 3 |
+
size 198225077
|
removed.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
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 sha256:108ea5dbb232558d744aff5011d29b92a76751c210ad8560e6a65738c9630bdf
|
| 3 |
+
size 775057
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [],
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"extra_ids": 0,
|
| 5 |
+
"pad_token": "<pad>",
|
| 6 |
+
"sp_model_kwargs": {},
|
| 7 |
+
"tokenizer_class": "T5Tokenizer",
|
| 8 |
+
"unk_token": "<unk>"
|
| 9 |
+
}
|
vocamaru_log.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|