Delete model
Browse files- model/config.json +0 -31
- model/generation_config.json +0 -7
- model/ojt_chatgptplus_tested.jsonl +0 -0
- model/pytorch_model.bin +0 -3
- model/special_tokens_map.json +0 -5
- model/spiece.model +0 -3
- model/t5marulog.jsonl +0 -1
- model/tokenizer_config.json +0 -11
model/config.json
DELETED
|
@@ -1,31 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "kkuramitsu/mt5-tiny12L",
|
| 3 |
-
"architectures": [
|
| 4 |
-
"MT5ForConditionalGeneration"
|
| 5 |
-
],
|
| 6 |
-
"d_ff": 1024,
|
| 7 |
-
"d_kv": 64,
|
| 8 |
-
"d_model": 512,
|
| 9 |
-
"decoder_start_token_id": 0,
|
| 10 |
-
"dense_act_fn": "gelu_new",
|
| 11 |
-
"dropout_rate": 0.1,
|
| 12 |
-
"eos_token_id": 1,
|
| 13 |
-
"feed_forward_proj": "gated-gelu",
|
| 14 |
-
"initializer_factor": 1.0,
|
| 15 |
-
"is_encoder_decoder": true,
|
| 16 |
-
"is_gated_act": true,
|
| 17 |
-
"layer_norm_epsilon": 1e-06,
|
| 18 |
-
"model_type": "mt5",
|
| 19 |
-
"num_decoder_layers": 8,
|
| 20 |
-
"num_heads": 6,
|
| 21 |
-
"num_layers": 8,
|
| 22 |
-
"pad_token_id": 0,
|
| 23 |
-
"relative_attention_max_distance": 128,
|
| 24 |
-
"relative_attention_num_buckets": 32,
|
| 25 |
-
"tie_word_embeddings": false,
|
| 26 |
-
"tokenizer_class": "T5Tokenizer",
|
| 27 |
-
"torch_dtype": "float32",
|
| 28 |
-
"transformers_version": "4.29.2",
|
| 29 |
-
"use_cache": true,
|
| 30 |
-
"vocab_size": 8200
|
| 31 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
model/generation_config.json
DELETED
|
@@ -1,7 +0,0 @@
|
|
| 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": "4.29.2"
|
| 7 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
model/ojt_chatgptplus_tested.jsonl
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model/pytorch_model.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:712e1edaceb61791e4df5f99474c3841c3c32ae5b504fe71e72e24b356815610
|
| 3 |
-
size 209898245
|
|
|
|
|
|
|
|
|
|
|
|
model/special_tokens_map.json
DELETED
|
@@ -1,5 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"eos_token": "</s>",
|
| 3 |
-
"pad_token": "<pad>",
|
| 4 |
-
"unk_token": "<unk>"
|
| 5 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
model/spiece.model
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:e7307cde47644d4ca6bca723f63a8c95e0349ac56497a2dc5df8d38ed80a3fd5
|
| 3 |
-
size 352368
|
|
|
|
|
|
|
|
|
|
|
|
model/t5marulog.jsonl
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"log": "trained", "date": "2023-05-19T07:14:13", "elapsed": "00:10:23", "model": "kkuramitsu/mt5-tiny12L", "max_length": 128, "target_max_length": 128, "batch_size": 16, "gradient_accumulation_steps": 1, "train_steps": 1604, "accelerator": "gpu", "devices": "auto", "precision": 32, "strategy": "auto", "gradient_clip_val": 1.0, "compile": true, "solver": "adamw", "lr": 0.0003, "warmup_steps": 1, "training_steps": 100000, "adam_epsilon": 1e-08, "weight_decay": 0.0, "epoch": 8, "step": 1600, "saved": "model"}
|
|
|
|
|
|
model/tokenizer_config.json
DELETED
|
@@ -1,11 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"additional_special_tokens": [],
|
| 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 |
-
"unk_token": "<unk>"
|
| 11 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|