deepparag commited on
Commit
6301780
1 Parent(s): 87b3669
Files changed (2) hide show
  1. config.json +5 -4
  2. pytorch_model.bin +2 -2
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "microsoft/DialoGPT-medium",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
@@ -8,14 +8,15 @@
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": 1024,
16
- "n_head": 16,
17
  "n_inner": null,
18
- "n_layer": 24,
19
  "n_positions": 1024,
20
  "reorder_and_upcast_attn": false,
21
  "resid_pdrop": 0.1,
 
1
  {
2
+ "_name_or_path": "transfaeries/DialoGPT-small-Discord-1.0",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
 
8
  "bos_token_id": 50256,
9
  "embd_pdrop": 0.1,
10
  "eos_token_id": 50256,
11
+ "gradient_checkpointing": false,
12
  "initializer_range": 0.02,
13
  "layer_norm_epsilon": 1e-05,
14
  "model_type": "gpt2",
15
  "n_ctx": 1024,
16
+ "n_embd": 768,
17
+ "n_head": 12,
18
  "n_inner": null,
19
+ "n_layer": 12,
20
  "n_positions": 1024,
21
  "reorder_and_upcast_attn": false,
22
  "resid_pdrop": 0.1,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f90fb72ba527223daaf0cff29b586d8f8f3cad63fe21caf53ea592545057c4d3
3
- size 1444576537
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5186d4306ebb6342f0243b6fbbf8015ed930b1c7f6c95ee13cf75dcf6520c90e
3
+ size 510401385