Commit
•
1c4d5a1
1
Parent(s):
f685d62
Upload 5 files
Browse files- config.json +45 -0
- generation_config.json +6 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- trainer_state.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/kaggle/input/gpt-neo/save/",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPTNeoForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"attention_layers": [
|
| 9 |
+
"global",
|
| 10 |
+
"local",
|
| 11 |
+
"global",
|
| 12 |
+
"local",
|
| 13 |
+
"global",
|
| 14 |
+
"local",
|
| 15 |
+
"global",
|
| 16 |
+
"local"
|
| 17 |
+
],
|
| 18 |
+
"attention_types": [
|
| 19 |
+
[
|
| 20 |
+
[
|
| 21 |
+
"global",
|
| 22 |
+
"local"
|
| 23 |
+
],
|
| 24 |
+
4
|
| 25 |
+
]
|
| 26 |
+
],
|
| 27 |
+
"bos_token_id": 50256,
|
| 28 |
+
"classifier_dropout": 0.1,
|
| 29 |
+
"embed_dropout": 0.0,
|
| 30 |
+
"eos_token_id": 50256,
|
| 31 |
+
"hidden_size": 768,
|
| 32 |
+
"initializer_range": 0.02,
|
| 33 |
+
"intermediate_size": null,
|
| 34 |
+
"layer_norm_epsilon": 1e-05,
|
| 35 |
+
"max_position_embeddings": 2048,
|
| 36 |
+
"model_type": "gpt_neo",
|
| 37 |
+
"num_heads": 16,
|
| 38 |
+
"num_layers": 8,
|
| 39 |
+
"resid_dropout": 0.0,
|
| 40 |
+
"torch_dtype": "float32",
|
| 41 |
+
"transformers_version": "4.29.2",
|
| 42 |
+
"use_cache": true,
|
| 43 |
+
"vocab_size": 50259,
|
| 44 |
+
"window_size": 256
|
| 45 |
+
}
|
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": "4.29.2"
|
| 6 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e47ef1a9a68852343f943e51a1d3eb3a46ebc98fcd4aa79785349f505cad094
|
| 3 |
+
size 421026621
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6869750f95a25c4e970298a33adf90e2d7ab52680bf3317239bff1b10103235
|
| 3 |
+
size 14575
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|