new one
Browse files- added_tokens.json +1 -1
- config.json +17 -7
- pytorch_model.bin +2 -2
- special_tokens_map.json +1 -1
- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
added_tokens.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"<|endoftext|>": 50257}
|
|
|
|
| 1 |
+
{"|PAD|": 50261, "<END>": 50260, "<|endoftext|>": 50257, "<IN>": 50258, "<OUT>": 50259}
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
@@ -8,17 +8,27 @@
|
|
| 8 |
"bos_token_id": 50256,
|
| 9 |
"embd_pdrop": 0.1,
|
| 10 |
"eos_token_id": 50256,
|
| 11 |
-
"
|
|
|
|
|
|
|
| 12 |
"initializer_range": 0.02,
|
|
|
|
|
|
|
|
|
|
| 13 |
"layer_norm_epsilon": 1e-05,
|
| 14 |
"model_type": "gpt2",
|
| 15 |
"n_ctx": 2048,
|
| 16 |
-
"n_embd":
|
| 17 |
-
"n_head":
|
| 18 |
"n_inner": null,
|
| 19 |
-
"n_layer":
|
| 20 |
"n_positions": 2048,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
"resid_pdrop": 0.1,
|
|
|
|
| 22 |
"scale_attn_weights": true,
|
| 23 |
"summary_activation": null,
|
| 24 |
"summary_first_dropout": 0.1,
|
|
@@ -26,7 +36,7 @@
|
|
| 26 |
"summary_type": "cls_index",
|
| 27 |
"summary_use_proj": true,
|
| 28 |
"torch_dtype": "float32",
|
| 29 |
-
"transformers_version": "4.
|
| 30 |
"use_cache": true,
|
| 31 |
-
"vocab_size":
|
| 32 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "Nehc/AGIRussia",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
|
|
| 8 |
"bos_token_id": 50256,
|
| 9 |
"embd_pdrop": 0.1,
|
| 10 |
"eos_token_id": 50256,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0"
|
| 13 |
+
},
|
| 14 |
"initializer_range": 0.02,
|
| 15 |
+
"label2id": {
|
| 16 |
+
"LABEL_0": 0
|
| 17 |
+
},
|
| 18 |
"layer_norm_epsilon": 1e-05,
|
| 19 |
"model_type": "gpt2",
|
| 20 |
"n_ctx": 2048,
|
| 21 |
+
"n_embd": 1024,
|
| 22 |
+
"n_head": 16,
|
| 23 |
"n_inner": null,
|
| 24 |
+
"n_layer": 24,
|
| 25 |
"n_positions": 2048,
|
| 26 |
+
"n_special": 0,
|
| 27 |
+
"output_past": true,
|
| 28 |
+
"predict_special_tokens": true,
|
| 29 |
+
"reorder_and_upcast_attn": false,
|
| 30 |
"resid_pdrop": 0.1,
|
| 31 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 32 |
"scale_attn_weights": true,
|
| 33 |
"summary_activation": null,
|
| 34 |
"summary_first_dropout": 0.1,
|
|
|
|
| 36 |
"summary_type": "cls_index",
|
| 37 |
"summary_use_proj": true,
|
| 38 |
"torch_dtype": "float32",
|
| 39 |
+
"transformers_version": "4.16.2",
|
| 40 |
"use_cache": true,
|
| 41 |
+
"vocab_size": 50262
|
| 42 |
}
|
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 sha256:0b1aa1a4cee7909fc1b6bf3c14ec16c6dc6f6d44033b5504b51023ffd2d223f4
|
| 3 |
+
size 1524293593
|
special_tokens_map.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
|
|
|
|
| 1 |
+
{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "|PAD|", "additional_special_tokens": ["<IN>", "<OUT>", "<END>", "|PAD|"]}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "special_tokens_map_file": null, "name_or_path": "
|
|
|
|
| 1 |
+
{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "special_tokens_map_file": null, "name_or_path": "Nehc/AGIRussia", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}
|