szhang1061
commited on
Commit
•
a30db8a
1
Parent(s):
cec6047
first commit
Browse files- config.json +31 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- tokenizer.json +0 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"layer_norm_epsilon": 1e-05,
|
| 12 |
+
"model_type": "gpt2",
|
| 13 |
+
"n_ctx": 1024,
|
| 14 |
+
"n_embd": 1280,
|
| 15 |
+
"n_head": 20,
|
| 16 |
+
"n_layer": 36,
|
| 17 |
+
"n_positions": 1024,
|
| 18 |
+
"resid_pdrop": 0.1,
|
| 19 |
+
"summary_activation": null,
|
| 20 |
+
"summary_first_dropout": 0.1,
|
| 21 |
+
"summary_proj_to_labels": true,
|
| 22 |
+
"summary_type": "cls_index",
|
| 23 |
+
"summary_use_proj": true,
|
| 24 |
+
"task_specific_params": {
|
| 25 |
+
"text-generation": {
|
| 26 |
+
"do_sample": true,
|
| 27 |
+
"max_length": 50
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"vocab_size": 50257
|
| 31 |
+
}
|
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:eed9ef705908fe58e2fe5da70aa18ad07b62e2fab8c8d4fc89b5b5e38b3a5941
|
| 3 |
+
size 3134057737
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|