lchaloupsky
commited on
Commit
•
7f0c53f
1
Parent(s):
540b669
Upload 7 files
Browse files- config.json +59 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tf_model.h5 +3 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_function": "gelu_new",
|
3 |
+
"architectures": [
|
4 |
+
"GPT2LMHeadModel"
|
5 |
+
],
|
6 |
+
"attn_pdrop": 0.1,
|
7 |
+
"bos_token_id": 50256,
|
8 |
+
"do_sample": false,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"eos_token_ids": 0,
|
12 |
+
"finetuning_task": null,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"is_decoder": false,
|
19 |
+
"label2id": {
|
20 |
+
"LABEL_0": 0,
|
21 |
+
"LABEL_1": 1
|
22 |
+
},
|
23 |
+
"layer_norm_epsilon": 1e-05,
|
24 |
+
"length_penalty": 1.0,
|
25 |
+
"max_length": 20,
|
26 |
+
"model_type": "gpt2",
|
27 |
+
"n_ctx": 1024,
|
28 |
+
"n_embd": 768,
|
29 |
+
"n_head": 12,
|
30 |
+
"n_layer": 12,
|
31 |
+
"n_positions": 1024,
|
32 |
+
"num_beams": 1,
|
33 |
+
"num_labels": 2,
|
34 |
+
"num_return_sequences": 1,
|
35 |
+
"output_attentions": false,
|
36 |
+
"output_hidden_states": false,
|
37 |
+
"output_past": true,
|
38 |
+
"pad_token_id": 0,
|
39 |
+
"pruned_heads": {},
|
40 |
+
"repetition_penalty": 1.0,
|
41 |
+
"resid_pdrop": 0.1,
|
42 |
+
"summary_activation": null,
|
43 |
+
"summary_first_dropout": 0.1,
|
44 |
+
"summary_proj_to_labels": true,
|
45 |
+
"summary_type": "cls_index",
|
46 |
+
"summary_use_proj": true,
|
47 |
+
"task_specific_params": {
|
48 |
+
"text-generation": {
|
49 |
+
"do_sample": true,
|
50 |
+
"max_length": 50
|
51 |
+
}
|
52 |
+
},
|
53 |
+
"temperature": 1.0,
|
54 |
+
"top_k": 50,
|
55 |
+
"top_p": 1.0,
|
56 |
+
"torchscript": false,
|
57 |
+
"use_bfloat16": false,
|
58 |
+
"vocab_size": 50257
|
59 |
+
}
|
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 sha256:87ec9cd0f7cca9683703ff3f8db379ed74a5c22ec26ef6237abe68a19747eefe
|
3 |
+
size 548148737
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "<|endoftext|>"}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7a199fec97d3677f6c43a2178099a85050a025d347b5bf8cfb7843ec051359a
|
3 |
+
size 497933648
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"pad_token": "<|endoftext|>"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|