update model
Browse files- config.json +6 -14
- merges.txt +0 -0
- pytorch_model.bin +2 -2
- vocab.json +0 -0
config.json
CHANGED
|
@@ -1,6 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
| 6 |
],
|
|
@@ -11,29 +10,22 @@
|
|
| 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":
|
| 18 |
"n_layer": 12,
|
| 19 |
"n_positions": 1024,
|
| 20 |
-
"reorder_and_upcast_attn":
|
| 21 |
"resid_pdrop": 0.1,
|
| 22 |
-
"scale_attn_by_inverse_layer_idx":
|
| 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 |
-
"
|
| 30 |
-
|
| 31 |
-
"do_sample": true,
|
| 32 |
-
"max_length": 50
|
| 33 |
-
}
|
| 34 |
-
},
|
| 35 |
-
"torch_dtype": "float32",
|
| 36 |
-
"transformers_version": "4.12.2",
|
| 37 |
"use_cache": true,
|
| 38 |
"vocab_size": 32768
|
| 39 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"activation_function": "gelu_fast",
|
|
|
|
| 3 |
"architectures": [
|
| 4 |
"GPT2LMHeadModel"
|
| 5 |
],
|
|
|
|
| 10 |
"initializer_range": 0.02,
|
| 11 |
"layer_norm_epsilon": 1e-05,
|
| 12 |
"model_type": "gpt2",
|
|
|
|
| 13 |
"n_embd": 768,
|
| 14 |
"n_head": 12,
|
| 15 |
+
"n_inner": 3072,
|
| 16 |
"n_layer": 12,
|
| 17 |
"n_positions": 1024,
|
| 18 |
+
"reorder_and_upcast_attn": false,
|
| 19 |
"resid_pdrop": 0.1,
|
| 20 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 21 |
"scale_attn_weights": true,
|
| 22 |
"summary_activation": null,
|
| 23 |
"summary_first_dropout": 0.1,
|
| 24 |
"summary_proj_to_labels": true,
|
| 25 |
"summary_type": "cls_index",
|
| 26 |
"summary_use_proj": true,
|
| 27 |
+
"tokenizer_class": "GPT2TokenizerFast",
|
| 28 |
+
"transformers_version": "4.19.0",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
"use_cache": true,
|
| 30 |
"vocab_size": 32768
|
| 31 |
}
|
merges.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0207f6b427e3cbf1bcb9726abb6bbba6620e9912e1abf23087ccdef61818ffb2
|
| 3 |
+
size 247234217
|
vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|