Upload config.json
Browse files- config.json +2 -12
config.json
CHANGED
@@ -4,19 +4,12 @@
|
|
4 |
"GPT2LMHeadModel"
|
5 |
],
|
6 |
"attn_pdrop": 0.1,
|
7 |
-
"auto_map": {
|
8 |
-
"AutoModelForCausalLM": "modeling_gpt2.GPT2LMHeadModel"
|
9 |
-
},
|
10 |
"bos_token_id": 50256,
|
11 |
-
"do_sample": true,
|
12 |
"embd_pdrop": 0.1,
|
13 |
"eos_token_id": 50256,
|
14 |
"gradient_checkpointing": false,
|
15 |
"initializer_range": 0.02,
|
16 |
"layer_norm_epsilon": 1e-05,
|
17 |
-
"length_penalty": 2.3,
|
18 |
-
"max_length": 64,
|
19 |
-
"min_length": 16,
|
20 |
"model_type": "gpt2",
|
21 |
"n_ctx": 2048,
|
22 |
"n_embd": 2048,
|
@@ -24,10 +17,7 @@
|
|
24 |
"n_inner": null,
|
25 |
"n_layer": 24,
|
26 |
"n_positions": 2048,
|
27 |
-
"no_repeat_ngram_size": 4,
|
28 |
-
"reorder_and_upcast_attn": false,
|
29 |
"resid_pdrop": 0.1,
|
30 |
-
"scale_attn_by_inverse_layer_idx": false,
|
31 |
"scale_attn_weights": true,
|
32 |
"summary_activation": null,
|
33 |
"summary_first_dropout": 0.1,
|
@@ -35,7 +25,7 @@
|
|
35 |
"summary_type": "cls_index",
|
36 |
"summary_use_proj": true,
|
37 |
"torch_dtype": "float32",
|
38 |
-
"transformers_version": "4.
|
39 |
-
"use_cache":
|
40 |
"vocab_size": 100000
|
41 |
}
|
|
|
4 |
"GPT2LMHeadModel"
|
5 |
],
|
6 |
"attn_pdrop": 0.1,
|
|
|
|
|
|
|
7 |
"bos_token_id": 50256,
|
|
|
8 |
"embd_pdrop": 0.1,
|
9 |
"eos_token_id": 50256,
|
10 |
"gradient_checkpointing": false,
|
11 |
"initializer_range": 0.02,
|
12 |
"layer_norm_epsilon": 1e-05,
|
|
|
|
|
|
|
13 |
"model_type": "gpt2",
|
14 |
"n_ctx": 2048,
|
15 |
"n_embd": 2048,
|
|
|
17 |
"n_inner": null,
|
18 |
"n_layer": 24,
|
19 |
"n_positions": 2048,
|
|
|
|
|
20 |
"resid_pdrop": 0.1,
|
|
|
21 |
"scale_attn_weights": true,
|
22 |
"summary_activation": null,
|
23 |
"summary_first_dropout": 0.1,
|
|
|
25 |
"summary_type": "cls_index",
|
26 |
"summary_use_proj": true,
|
27 |
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.10.3",
|
29 |
+
"use_cache": true,
|
30 |
"vocab_size": 100000
|
31 |
}
|