Training in progress, epoch 1
Browse files- config.json +5 -5
- pytorch_model.bin +2 -2
- tokenizer_config.json +1 -1
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "rinna/japanese-gpt2-
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
@@ -13,10 +13,10 @@
|
|
13 |
"layer_norm_epsilon": 1e-05,
|
14 |
"model_type": "gpt2",
|
15 |
"n_ctx": 1024,
|
16 |
-
"n_embd":
|
17 |
-
"n_head":
|
18 |
-
"n_inner":
|
19 |
-
"n_layer":
|
20 |
"n_positions": 1024,
|
21 |
"reorder_and_upcast_attn": false,
|
22 |
"resid_pdrop": 0.1,
|
1 |
{
|
2 |
+
"_name_or_path": "rinna/japanese-gpt2-medium",
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
13 |
"layer_norm_epsilon": 1e-05,
|
14 |
"model_type": "gpt2",
|
15 |
"n_ctx": 1024,
|
16 |
+
"n_embd": 1024,
|
17 |
+
"n_head": 16,
|
18 |
+
"n_inner": 4096,
|
19 |
+
"n_layer": 24,
|
20 |
"n_positions": 1024,
|
21 |
"reorder_and_upcast_attn": false,
|
22 |
"resid_pdrop": 0.1,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e86ff398dde37b11c462c74db23d499e784bdf3df13e6d0629ec7970583b6643
|
3 |
+
size 1369804761
|
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "[PAD]", "extra_ids": 0, "additional_special_tokens": [], "sp_model_kwargs": {}, "bos_token": "<s>", "cls_token": "[CLS]", "sep_token": "[SEP]", "mask_token": "[MASK]", "do_lower_case": true, "special_tokens_map_file": "/root/.cache/huggingface/transformers/
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "[PAD]", "extra_ids": 0, "additional_special_tokens": [], "sp_model_kwargs": {}, "bos_token": "<s>", "cls_token": "[CLS]", "sep_token": "[SEP]", "mask_token": "[MASK]", "do_lower_case": true, "special_tokens_map_file": "/root/.cache/huggingface/transformers/42091916a8a40b3949b8a4f56ce63e437a166ae0e88d1d15546860c13bdc5ceb.9049458ebcd1cf666b7b0a046aa394597f12e611077571cfc86e0938f8675d82", "tokenizer_file": null, "name_or_path": "rinna/japanese-gpt2-medium", "tokenizer_class": "T5Tokenizer"}
|