alibidaran
commited on
Commit
•
2988632
1
Parent(s):
be6ad18
stable version
Browse files- .gitignore +1 -0
- added_tokens.json +5 -0
- config.json +39 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- runs/Jul29_13-11-33_c937c5be3fd0/events.out.tfevents.1690636308.c937c5be3fd0.2463.0 +3 -0
- runs/Jul29_13-19-01_c937c5be3fd0/events.out.tfevents.1690636754.c937c5be3fd0.2463.1 +3 -0
- runs/Jul29_13-19-48_c937c5be3fd0/events.out.tfevents.1690636800.c937c5be3fd0.2463.2 +3 -0
- runs/Jul29_13-21-07_c937c5be3fd0/events.out.tfevents.1690636871.c937c5be3fd0.2463.3 +3 -0
- runs/Jul29_13-42-56_c937c5be3fd0/events.out.tfevents.1690638179.c937c5be3fd0.2463.4 +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<BOS>": 50258,
|
3 |
+
"<EOS>": 50259,
|
4 |
+
"[PAD]": 50257
|
5 |
+
}
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 1024,
|
15 |
+
"n_embd": 768,
|
16 |
+
"n_head": 12,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 12,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"reorder_and_upcast_attn": false,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
23 |
+
"scale_attn_weights": true,
|
24 |
+
"summary_activation": null,
|
25 |
+
"summary_first_dropout": 0.1,
|
26 |
+
"summary_proj_to_labels": true,
|
27 |
+
"summary_type": "cls_index",
|
28 |
+
"summary_use_proj": true,
|
29 |
+
"task_specific_params": {
|
30 |
+
"text-generation": {
|
31 |
+
"do_sample": true,
|
32 |
+
"max_length": 50
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.31.0",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50260
|
39 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.31.0"
|
6 |
+
}
|
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:d3823d4227165ba6adff3247ee43255ae4add9547a00ee0d8a43fa0cc3c138bd
|
3 |
+
size 497816413
|
runs/Jul29_13-11-33_c937c5be3fd0/events.out.tfevents.1690636308.c937c5be3fd0.2463.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7639d47486eb9e75775dbe34a4cf667c89971d80465e147315b172cc8151ef48
|
3 |
+
size 4431
|
runs/Jul29_13-19-01_c937c5be3fd0/events.out.tfevents.1690636754.c937c5be3fd0.2463.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:942c90e7c363bbc7d5151d8713e26cc046f0fe7af410345c27de252d24a132db
|
3 |
+
size 4274
|
runs/Jul29_13-19-48_c937c5be3fd0/events.out.tfevents.1690636800.c937c5be3fd0.2463.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bce642271983a2b3ce2267d8b04e058843a94e8bcf485996e31b48dfab5533c4
|
3 |
+
size 4275
|
runs/Jul29_13-21-07_c937c5be3fd0/events.out.tfevents.1690636871.c937c5be3fd0.2463.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdc44fce61dbcdb5a1ac4f50c4ed4c5e90a52da9df568b061446f013f5724eaa
|
3 |
+
size 4434
|
runs/Jul29_13-42-56_c937c5be3fd0/events.out.tfevents.1690638179.c937c5be3fd0.2463.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:621f2653828c39eb9fb6af9429133e1c243669347b77800c0e47bf110fd4471d
|
3 |
+
size 5487
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<BOS>",
|
3 |
+
"eos_token": "<EOS>",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"eos_token": "<|endoftext|>",
|
6 |
+
"model_max_length": 1024,
|
7 |
+
"tokenizer_class": "GPT2Tokenizer",
|
8 |
+
"unk_token": "<|endoftext|>"
|
9 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1802c8626857bf6097bd51d8ae13febb4af454e37ac506cca90f0495e859760
|
3 |
+
size 3963
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|