Upload model
Browse files- config.json +31 -56
- generation_config.json +2 -11
- pytorch_model.bin +2 -2
config.json
CHANGED
@@ -1,64 +1,39 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"
|
4 |
-
"activation_function": "gelu",
|
5 |
-
"add_bias_logits": false,
|
6 |
-
"add_final_layer_norm": true,
|
7 |
"architectures": [
|
8 |
-
"
|
9 |
],
|
10 |
-
"
|
11 |
-
"bos_token_id":
|
12 |
-
"
|
13 |
-
"
|
14 |
-
"
|
15 |
-
"
|
16 |
-
"
|
17 |
-
"
|
18 |
-
"
|
19 |
-
"
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"
|
23 |
-
"
|
24 |
-
"
|
25 |
-
"
|
26 |
-
"
|
27 |
-
"
|
28 |
-
"
|
29 |
-
"
|
30 |
-
"
|
31 |
-
"
|
32 |
-
"
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
},
|
38 |
-
"init_std": 0.02,
|
39 |
-
"is_encoder_decoder": true,
|
40 |
-
"label2id": {
|
41 |
-
"LABEL_0": 0,
|
42 |
-
"LABEL_1": 1,
|
43 |
-
"LABEL_2": 2
|
44 |
-
},
|
45 |
-
"layernorm_variant": "prelayernorm",
|
46 |
-
"length_penalty": 0.65,
|
47 |
-
"max_length": 60,
|
48 |
-
"max_position_embeddings": 128,
|
49 |
-
"min_length": 20,
|
50 |
-
"model_type": "blenderbot",
|
51 |
-
"no_repeat_ngram_size": 3,
|
52 |
-
"normalize_before": true,
|
53 |
-
"normalize_embedding": false,
|
54 |
-
"num_beams": 10,
|
55 |
-
"num_hidden_layers": 2,
|
56 |
-
"pad_token_id": 0,
|
57 |
-
"scale_embedding": true,
|
58 |
-
"static_position_embeddings": false,
|
59 |
"torch_dtype": "float32",
|
60 |
"transformers_version": "4.30.1",
|
61 |
-
"unk_token_id": 3,
|
62 |
"use_cache": true,
|
63 |
-
"vocab_size":
|
64 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "gpt2",
|
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,
|
16 |
+
"n_head": 12,
|
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,
|
27 |
+
"summary_type": "cls_index",
|
28 |
+
"summary_use_proj": true,
|
29 |
+
"task_specific_params": {
|
30 |
+
"text-generation": {
|
31 |
+
"do_sample": true,
|
32 |
+
"max_length": 50
|
33 |
+
}
|
34 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
35 |
"torch_dtype": "float32",
|
36 |
"transformers_version": "4.30.1",
|
|
|
37 |
"use_cache": true,
|
38 |
+
"vocab_size": 50257
|
39 |
}
|
generation_config.json
CHANGED
@@ -1,15 +1,6 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
-
"bos_token_id":
|
4 |
-
"
|
5 |
-
"encoder_no_repeat_ngram_size": 3,
|
6 |
-
"eos_token_id": 2,
|
7 |
-
"forced_eos_token_id": 2,
|
8 |
-
"length_penalty": 0.65,
|
9 |
-
"max_length": 60,
|
10 |
-
"min_length": 20,
|
11 |
-
"no_repeat_ngram_size": 3,
|
12 |
-
"num_beams": 10,
|
13 |
-
"pad_token_id": 0,
|
14 |
"transformers_version": "4.30.1"
|
15 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"transformers_version": "4.30.1"
|
6 |
}
|
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 sha256:99b24777bd9fbe447f3f241523d32a29b9ef49d1a1d0eff81100e242a7ab64f7
|
3 |
+
size 497807197
|