osazuwa commited on
Commit
c7177ca
·
1 Parent(s): 3cd621b

Updated to GPT2-medium for king-model

Browse files
Files changed (2) hide show
  1. config.json +6 -4
  2. pytorch_model.bin +2 -2
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "gpt2",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
@@ -12,11 +12,13 @@
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,
 
1
  {
2
+ "_name_or_path": "gpt2-medium",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
 
12
  "layer_norm_epsilon": 1e-05,
13
  "model_type": "gpt2",
14
  "n_ctx": 1024,
15
+ "n_embd": 1024,
16
+ "n_head": 16,
17
  "n_inner": null,
18
+ "n_layer": 24,
19
  "n_positions": 1024,
20
+ "n_special": 0,
21
+ "predict_special_tokens": true,
22
  "reorder_and_upcast_attn": false,
23
  "resid_pdrop": 0.1,
24
  "scale_attn_by_inverse_layer_idx": false,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85d89e14f1956bc9199c5228979074235ae0d168461acf24f01f624acc177a4f
3
- size 497807197
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9b02edccf9755b03a1083eb5ea67284de035a92baad50e91100aa1008a185c6
3
+ size 1419387869