JulianS commited on
Commit
9fbf832
·
verified ·
1 Parent(s): dccf1ba

Added .config files

Browse files
Files changed (2) hide show
  1. config.json +34 -0
  2. generation_config.json +8 -0
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./results-2688-3.0-kbps/checkpoint-255000/",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "decoder_start_token_id": 1024,
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 1025,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": 3072,
18
+ "n_layer": 12,
19
+ "n_positions": 2688,
20
+ "pad_token_id": 1024,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.39.3",
32
+ "use_cache": true,
33
+ "vocab_size": 1026
34
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "decoder_start_token_id": 1024,
5
+ "eos_token_id": 1025,
6
+ "pad_token_id": 1024,
7
+ "transformers_version": "4.39.3"
8
+ }