v2
Browse files- config.json +5 -13
- pytorch_model.bin +2 -2
- tokenizer_config.json +1 -1
- training_args.bin +2 -2
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
@@ -8,6 +8,7 @@
|
|
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",
|
@@ -17,10 +18,7 @@
|
|
17 |
"n_inner": null,
|
18 |
"n_layer": 12,
|
19 |
"n_positions": 1024,
|
20 |
-
"reorder_and_upcast_attn": false,
|
21 |
"resid_pdrop": 0.1,
|
22 |
-
"scale_attn_by_inverse_layer_idx": false,
|
23 |
-
"scale_attn_weights": true,
|
24 |
"summary_activation": null,
|
25 |
"summary_first_dropout": 0.1,
|
26 |
"summary_proj_to_labels": true,
|
@@ -28,16 +26,10 @@
|
|
28 |
"summary_use_proj": true,
|
29 |
"task_specific_params": {
|
30 |
"conversational": {
|
31 |
-
|
32 |
-
"no_repeat_ngram_size":3,
|
33 |
-
"do_sample":true,
|
34 |
-
"top_k":100,
|
35 |
-
"top_p":0.7,
|
36 |
-
"temperature":0.8
|
37 |
}
|
38 |
},
|
39 |
-
"
|
40 |
-
"
|
41 |
-
"use_cache": false,
|
42 |
"vocab_size": 50257
|
43 |
}
|
|
|
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 |
+
"gradient_checkpointing": false,
|
12 |
"initializer_range": 0.02,
|
13 |
"layer_norm_epsilon": 1e-05,
|
14 |
"model_type": "gpt2",
|
|
|
18 |
"n_inner": null,
|
19 |
"n_layer": 12,
|
20 |
"n_positions": 1024,
|
|
|
21 |
"resid_pdrop": 0.1,
|
|
|
|
|
22 |
"summary_activation": null,
|
23 |
"summary_first_dropout": 0.1,
|
24 |
"summary_proj_to_labels": true,
|
|
|
26 |
"summary_use_proj": true,
|
27 |
"task_specific_params": {
|
28 |
"conversational": {
|
29 |
+
"max_length": 1000
|
|
|
|
|
|
|
|
|
|
|
30 |
}
|
31 |
},
|
32 |
+
"transformers_version": "4.5.1",
|
33 |
+
"use_cache": true,
|
|
|
34 |
"vocab_size": 50257
|
35 |
}
|
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:b01e921afa4d202ec51b87870b7a96af20dc7976a2567383c850746f2e7dd80a
|
3 |
+
size 510403817
|
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "microsoft/DialoGPT-small", "errors": "replace"
|
|
|
1 |
+
{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "microsoft/DialoGPT-small", "errors": "replace"}
|
training_args.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:e6fa610da259cae1a376d6b5ae66fa72e4873d9ea870c6e6d1e27af759190391
|
3 |
+
size 1327
|