Upload 7 files
Browse files- added_tokens.json +1 -0
- config.json +38 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"[FIRST]": 50257, "[SECOND]": 50258, "<FIRST_SPEAKER>": 50259, "<SECOND_SPEAKER>": 50260}
|
config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_function": "gelu_new",
|
3 |
+
"attn_pdrop": 0.1,
|
4 |
+
"bos_token_id": 50256,
|
5 |
+
"embd_pdrop": 0.1,
|
6 |
+
"eos_token_id": 50256,
|
7 |
+
"id2label": {
|
8 |
+
"0": "LABEL_0"
|
9 |
+
},
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"label2id": {
|
12 |
+
"LABEL_0": 0
|
13 |
+
},
|
14 |
+
"layer_norm_epsilon": 1e-05,
|
15 |
+
"model_type": "gpt2",
|
16 |
+
"n_ctx": 2048,
|
17 |
+
"n_embd": 1024,
|
18 |
+
"n_head": 16,
|
19 |
+
"n_inner": null,
|
20 |
+
"n_layer": 24,
|
21 |
+
"n_positions": 2048,
|
22 |
+
"n_special": 0,
|
23 |
+
"output_past": true,
|
24 |
+
"predict_special_tokens": true,
|
25 |
+
"reorder_and_upcast_attn": false,
|
26 |
+
"resid_pdrop": 0.1,
|
27 |
+
"scale_attn_by_inverse_layer_idx": false,
|
28 |
+
"scale_attn_weights": true,
|
29 |
+
"summary_activation": null,
|
30 |
+
"summary_first_dropout": 0.1,
|
31 |
+
"summary_proj_to_labels": true,
|
32 |
+
"summary_type": "cls_index",
|
33 |
+
"summary_use_proj": true,
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.15.0",
|
36 |
+
"use_cache": true,
|
37 |
+
"vocab_size": 50261
|
38 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63c43b3834b279073e85862dddf924c2c961ba882a1e34fdb1008e2e353dff3b
|
3 |
+
size 1524289497
|
special_tokens_map.json
ADDED
@@ -0,0 +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}, "pad_token": "<pad>"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"errors": "replace", "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, "use_fast": true, "tokenizer_class": "GPT2Tokenizer"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|