at2507/finetuned_gpt2
Browse files- config.json +3 -1
- generation_config.json +2 -0
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,15 +1,17 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
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,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "gpt_output",
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
6 |
],
|
7 |
"attn_pdrop": 0.1,
|
8 |
"bos_token_id": 50256,
|
9 |
+
"do_sample": true,
|
10 |
"embd_pdrop": 0.1,
|
11 |
"eos_token_id": 50256,
|
12 |
"initializer_range": 0.02,
|
13 |
"layer_norm_epsilon": 1e-05,
|
14 |
+
"max_length": 50,
|
15 |
"model_type": "gpt2",
|
16 |
"n_ctx": 1024,
|
17 |
"n_embd": 768,
|
generation_config.json
CHANGED
@@ -1,6 +1,8 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 50256,
|
|
|
4 |
"eos_token_id": 50256,
|
|
|
5 |
"transformers_version": "4.30.2"
|
6 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 50256,
|
4 |
+
"do_sample": true,
|
5 |
"eos_token_id": 50256,
|
6 |
+
"max_length": 50,
|
7 |
"transformers_version": "4.30.2"
|
8 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3899
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e882a8ad79943ebaf2908ab8b05dcbf5238f1f57e1831ba2891425cbdcfc0672
|
3 |
size 3899
|