Ekgren commited on
Commit
ba1cb6a
1 Parent(s): 4080ff5

Upload model

Browse files
Files changed (2) hide show
  1. config.json +36 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/ariel/gpt_sw3/hf_new/126m/",
3
+ "activation_function": "gelu",
4
+ "apply_query_key_layer_scaling": true,
5
+ "architectures": [
6
+ "GPT2LMHeadModel"
7
+ ],
8
+ "attn_pdrop": 0.1,
9
+ "bos_token_id": 2,
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 3,
12
+ "initializer_range": 0.023,
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": 2048,
20
+ "normalize_attention_scores": true,
21
+ "pad_token_id": 0,
22
+ "reorder_and_upcast_attn": false,
23
+ "resid_pdrop": 0.1,
24
+ "scale_attn_by_inverse_layer_idx": false,
25
+ "scale_attn_weights": true,
26
+ "summary_activation": null,
27
+ "summary_first_dropout": 0.1,
28
+ "summary_proj_to_labels": true,
29
+ "summary_type": "cls_index",
30
+ "summary_use_proj": true,
31
+ "tokenizer_class": "GPTSw3Tokenizer",
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.25.0.dev0",
34
+ "use_cache": false,
35
+ "vocab_size": 64000
36
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:251d28a8c1e9d05eb81ea69b1d974aeb6fc2add583976408976a8cb919a297d7
3
+ size 593508541