niizam
commited on
Commit
•
5fb1b86
1
Parent(s):
5352212
Initial commit
Browse files- gpt2-4chan-mini/config.json +32 -0
- gpt2-4chan-mini/generation_config.json +6 -0
- gpt2-4chan-mini/optimizer.pt +3 -0
- gpt2-4chan-mini/pytorch_model.bin +3 -0
- gpt2-4chan-mini/rng_state.pth +3 -0
- gpt2-4chan-mini/scheduler.pt +3 -0
- gpt2-4chan-mini/trainer_state.json +0 -0
- gpt2-4chan-mini/training_args.bin +3 -0
gpt2-4chan-mini/config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "output/checkpoint-50000",
|
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_embd": 768,
|
15 |
+
"n_head": 12,
|
16 |
+
"n_inner": null,
|
17 |
+
"n_layer": 12,
|
18 |
+
"n_positions": 1024,
|
19 |
+
"reorder_and_upcast_attn": false,
|
20 |
+
"resid_pdrop": 0.1,
|
21 |
+
"scale_attn_by_inverse_layer_idx": false,
|
22 |
+
"scale_attn_weights": true,
|
23 |
+
"summary_activation": null,
|
24 |
+
"summary_first_dropout": 0.1,
|
25 |
+
"summary_proj_to_labels": true,
|
26 |
+
"summary_type": "cls_index",
|
27 |
+
"summary_use_proj": true,
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.28.1",
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 52000
|
32 |
+
}
|
gpt2-4chan-mini/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": "4.28.1"
|
6 |
+
}
|
gpt2-4chan-mini/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b360d9c2b1c6e8cf2afffcfc04a5dd1950b3acb7561b4171910d241e75f53639
|
3 |
+
size 1006314437
|
gpt2-4chan-mini/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c69ec2666594d44282b6530a07efe804f7f547a50e8bd56225a8bf3484d0f41
|
3 |
+
size 515752509
|
gpt2-4chan-mini/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99d3f3a48e3187d23f5c1f6f4dc37260a33a2b714c289a016aba9dc41cf49aa6
|
3 |
+
size 14575
|
gpt2-4chan-mini/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb0389447d60afaeabc4db1beb41d10dfef731fcaeec7922673c08ad55e03700
|
3 |
+
size 627
|
gpt2-4chan-mini/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
gpt2-4chan-mini/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15d18c5fb31a3d62ba792b25bbf7a7fe350f16e07fcd8dffe1340146accd48e6
|
3 |
+
size 3579
|