add model
Browse files- config.json +18 -54
- pytorch_model.bin +2 -2
config.json
CHANGED
|
@@ -1,74 +1,38 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
-
"
|
| 6 |
-
],
|
| 7 |
-
"attention_dropout": 0,
|
| 8 |
-
"attention_layers": [
|
| 9 |
-
"global",
|
| 10 |
-
"local",
|
| 11 |
-
"global",
|
| 12 |
-
"local",
|
| 13 |
-
"global",
|
| 14 |
-
"local",
|
| 15 |
-
"global",
|
| 16 |
-
"local",
|
| 17 |
-
"global",
|
| 18 |
-
"local",
|
| 19 |
-
"global",
|
| 20 |
-
"local",
|
| 21 |
-
"global",
|
| 22 |
-
"local",
|
| 23 |
-
"global",
|
| 24 |
-
"local",
|
| 25 |
-
"global",
|
| 26 |
-
"local",
|
| 27 |
-
"global",
|
| 28 |
-
"local",
|
| 29 |
-
"global",
|
| 30 |
-
"local",
|
| 31 |
-
"global",
|
| 32 |
-
"local"
|
| 33 |
-
],
|
| 34 |
-
"attention_types": [
|
| 35 |
-
[
|
| 36 |
-
[
|
| 37 |
-
"global",
|
| 38 |
-
"local"
|
| 39 |
-
],
|
| 40 |
-
12
|
| 41 |
-
]
|
| 42 |
],
|
|
|
|
| 43 |
"bos_token_id": 50256,
|
| 44 |
-
"
|
| 45 |
"eos_token_id": 50256,
|
| 46 |
-
"gradient_checkpointing": false,
|
| 47 |
-
"hidden_size": 2048,
|
| 48 |
"initializer_range": 0.02,
|
| 49 |
-
"intermediate_size": null,
|
| 50 |
"layer_norm_epsilon": 1e-05,
|
| 51 |
-
"
|
| 52 |
-
"
|
| 53 |
-
"
|
| 54 |
-
"
|
| 55 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
"summary_activation": null,
|
| 57 |
"summary_first_dropout": 0.1,
|
| 58 |
"summary_proj_to_labels": true,
|
| 59 |
"summary_type": "cls_index",
|
| 60 |
"summary_use_proj": true,
|
| 61 |
"task_specific_params": {
|
| 62 |
-
"
|
| 63 |
-
"
|
| 64 |
-
"max_length": 50,
|
| 65 |
-
"temperature": 0.9
|
| 66 |
}
|
| 67 |
},
|
| 68 |
-
"tokenizer_class": "GPT2Tokenizer",
|
| 69 |
"torch_dtype": "float32",
|
| 70 |
"transformers_version": "4.15.0",
|
| 71 |
"use_cache": true,
|
| 72 |
-
"vocab_size": 50257
|
| 73 |
-
"window_size": 256
|
| 74 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "microsoft/DialoGPT-large",
|
| 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": 1280,
|
| 16 |
+
"n_head": 20,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 36,
|
| 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 |
+
"conversational": {
|
| 31 |
+
"max_length": 1000
|
|
|
|
|
|
|
| 32 |
}
|
| 33 |
},
|
|
|
|
| 34 |
"torch_dtype": "float32",
|
| 35 |
"transformers_version": "4.15.0",
|
| 36 |
"use_cache": true,
|
| 37 |
+
"vocab_size": 50257
|
|
|
|
| 38 |
}
|
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:b23e9eab2b440e18612a2ab19505a7bf128c346a441804c21bcedd1076fca4ac
|
| 3 |
+
size 3134045897
|