gamallo commited on
Commit
71f9158
1 Parent(s): 8e49a7c

Upload 5 files

Browse files
Files changed (5) hide show
  1. config.json +33 -0
  2. generation_config.json +6 -0
  3. merges.txt +0 -0
  4. rng_state.pth +3 -0
  5. scaler.pt +3 -0
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "models/NOS_GPT_1.3_CPT",
3
+ "activation_function": "gelu",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.0,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_embd": 2048,
15
+ "n_head": 16,
16
+ "n_inner": 8192,
17
+ "n_layer": 24,
18
+ "n_positions": 2048,
19
+ "pad_token_id": 50256,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.0,
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
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.28.1",
31
+ "use_cache": true,
32
+ "vocab_size": 50257
33
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.28.1"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c1c56fdd8351b1702a183ee747828594ef88b59ac499059e3a75d10ed82c1e5
3
+ size 21665
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e4030b1924cf92e6cc4f801ee9388e73a45b021f3f1520a8abff48d62a3bab5
3
+ size 557