Upload 9 files
Browse filesCorrected Model
- config.json +5 -8
- generation_config.json +0 -1
- merges.txt +0 -0
- pytorch_model.bin +2 -2
- special_tokens_map.json +21 -3
- tokenizer.json +0 -0
- tokenizer_config.json +1 -8
- vocab.json +0 -0
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
@@ -8,7 +8,6 @@
|
|
8 |
"bos_token_id": 50256,
|
9 |
"embd_pdrop": 0.1,
|
10 |
"eos_token_id": 50256,
|
11 |
-
"eos_token_ids": 0,
|
12 |
"initializer_range": 0.02,
|
13 |
"layer_norm_epsilon": 1e-05,
|
14 |
"model_type": "gpt2",
|
@@ -18,8 +17,7 @@
|
|
18 |
"n_inner": null,
|
19 |
"n_layer": 12,
|
20 |
"n_positions": 1024,
|
21 |
-
"
|
22 |
-
"pad_token_id": 0,
|
23 |
"reorder_and_upcast_attn": false,
|
24 |
"resid_pdrop": 0.1,
|
25 |
"scale_attn_by_inverse_layer_idx": false,
|
@@ -30,13 +28,12 @@
|
|
30 |
"summary_type": "cls_index",
|
31 |
"summary_use_proj": true,
|
32 |
"task_specific_params": {
|
33 |
-
"
|
34 |
-
"
|
35 |
-
"max_length": 50
|
36 |
}
|
37 |
},
|
38 |
"torch_dtype": "float32",
|
39 |
"transformers_version": "4.29.2",
|
40 |
"use_cache": true,
|
41 |
-
"vocab_size":
|
42 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "microsoft/DialoGPT-small",
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
|
|
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",
|
|
|
17 |
"n_inner": null,
|
18 |
"n_layer": 12,
|
19 |
"n_positions": 1024,
|
20 |
+
"pad_token_id": 50256,
|
|
|
21 |
"reorder_and_upcast_attn": false,
|
22 |
"resid_pdrop": 0.1,
|
23 |
"scale_attn_by_inverse_layer_idx": false,
|
|
|
28 |
"summary_type": "cls_index",
|
29 |
"summary_use_proj": true,
|
30 |
"task_specific_params": {
|
31 |
+
"conversational": {
|
32 |
+
"max_length": 1000
|
|
|
33 |
}
|
34 |
},
|
35 |
"torch_dtype": "float32",
|
36 |
"transformers_version": "4.29.2",
|
37 |
"use_cache": true,
|
38 |
+
"vocab_size": 50261
|
39 |
}
|
generation_config.json
CHANGED
@@ -2,6 +2,5 @@
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 50256,
|
4 |
"eos_token_id": 50256,
|
5 |
-
"pad_token_id": 0,
|
6 |
"transformers_version": "4.29.2"
|
7 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 50256,
|
4 |
"eos_token_id": 50256,
|
|
|
5 |
"transformers_version": "4.29.2"
|
6 |
}
|
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 sha256:717109cbb403db4cff7720f0148ee34c1c610c46a66aed6d39d50122a5941408
|
3 |
+
size 510410301
|
special_tokens_map.json
CHANGED
@@ -1,6 +1,24 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
"pad_token": "<|endoftext|>",
|
5 |
-
"unk_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
"pad_token": "<|endoftext|>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<|endoftext|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -20,14 +20,7 @@
|
|
20 |
},
|
21 |
"errors": "replace",
|
22 |
"model_max_length": 1024,
|
23 |
-
"pad_token":
|
24 |
-
"__type": "AddedToken",
|
25 |
-
"content": "<|endoftext|>",
|
26 |
-
"lstrip": false,
|
27 |
-
"normalized": true,
|
28 |
-
"rstrip": false,
|
29 |
-
"single_word": false
|
30 |
-
},
|
31 |
"tokenizer_class": "GPT2Tokenizer",
|
32 |
"unk_token": {
|
33 |
"__type": "AddedToken",
|
|
|
20 |
},
|
21 |
"errors": "replace",
|
22 |
"model_max_length": 1024,
|
23 |
+
"pad_token": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
"tokenizer_class": "GPT2Tokenizer",
|
25 |
"unk_token": {
|
26 |
"__type": "AddedToken",
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|