Upload 4 files
Browse files- config.json +114 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"output_attentions": true,
|
| 21 |
+
"pruned_heads": {
|
| 22 |
+
"2": [
|
| 23 |
+
1
|
| 24 |
+
],
|
| 25 |
+
"3": [
|
| 26 |
+
0,
|
| 27 |
+
4
|
| 28 |
+
],
|
| 29 |
+
"4": [
|
| 30 |
+
8,
|
| 31 |
+
2,
|
| 32 |
+
10,
|
| 33 |
+
4
|
| 34 |
+
],
|
| 35 |
+
"5": [
|
| 36 |
+
0,
|
| 37 |
+
1,
|
| 38 |
+
5,
|
| 39 |
+
8,
|
| 40 |
+
9
|
| 41 |
+
],
|
| 42 |
+
"6": [
|
| 43 |
+
2,
|
| 44 |
+
3,
|
| 45 |
+
6,
|
| 46 |
+
9,
|
| 47 |
+
10
|
| 48 |
+
],
|
| 49 |
+
"7": [
|
| 50 |
+
1,
|
| 51 |
+
2,
|
| 52 |
+
6,
|
| 53 |
+
7,
|
| 54 |
+
10,
|
| 55 |
+
11
|
| 56 |
+
],
|
| 57 |
+
"8": [
|
| 58 |
+
0,
|
| 59 |
+
1,
|
| 60 |
+
3,
|
| 61 |
+
6,
|
| 62 |
+
9,
|
| 63 |
+
11
|
| 64 |
+
],
|
| 65 |
+
"9": [
|
| 66 |
+
0,
|
| 67 |
+
1,
|
| 68 |
+
2,
|
| 69 |
+
4,
|
| 70 |
+
5,
|
| 71 |
+
6,
|
| 72 |
+
8,
|
| 73 |
+
9,
|
| 74 |
+
11
|
| 75 |
+
],
|
| 76 |
+
"10": [
|
| 77 |
+
0,
|
| 78 |
+
1,
|
| 79 |
+
2,
|
| 80 |
+
3,
|
| 81 |
+
6,
|
| 82 |
+
7,
|
| 83 |
+
8,
|
| 84 |
+
10
|
| 85 |
+
],
|
| 86 |
+
"11": [
|
| 87 |
+
1,
|
| 88 |
+
2,
|
| 89 |
+
5,
|
| 90 |
+
6,
|
| 91 |
+
7,
|
| 92 |
+
9
|
| 93 |
+
]
|
| 94 |
+
},
|
| 95 |
+
"reorder_and_upcast_attn": false,
|
| 96 |
+
"resid_pdrop": 0.1,
|
| 97 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 98 |
+
"scale_attn_weights": true,
|
| 99 |
+
"summary_activation": null,
|
| 100 |
+
"summary_first_dropout": 0.1,
|
| 101 |
+
"summary_proj_to_labels": true,
|
| 102 |
+
"summary_type": "cls_index",
|
| 103 |
+
"summary_use_proj": true,
|
| 104 |
+
"task_specific_params": {
|
| 105 |
+
"text-generation": {
|
| 106 |
+
"do_sample": true,
|
| 107 |
+
"max_length": 50
|
| 108 |
+
}
|
| 109 |
+
},
|
| 110 |
+
"torch_dtype": "float32",
|
| 111 |
+
"transformers_version": "4.36.2",
|
| 112 |
+
"use_cache": true,
|
| 113 |
+
"vocab_size": 50257
|
| 114 |
+
}
|
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": "4.36.2"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4cf7afbffc0619f608e01493dbd572c1b1fb8cb4103c78ae57eec566e59b7a00
|
| 3 |
+
size 456839800
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d8dd69fb13eaed6fb5b0cd3bdbffd20509469cae8b6fd8682e2756c2306638d
|
| 3 |
+
size 4728
|