kurumuz commited on
Commit
658edeb
1 Parent(s): 674a405

upload 6B weights

Browse files
Files changed (2) hide show
  1. config.json +49 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPTJForCausalLM"
5
+ ],
6
+ "attention_dropout": 0,
7
+ "attention_layers": ["global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global", "global"],
8
+ "attention_types": [
9
+ [
10
+ [
11
+ "global"
12
+ ],
13
+ 28
14
+ ]
15
+ ],
16
+ "bos_token_id": 50256,
17
+ "embed_dropout": 0,
18
+ "eos_token_id": 50256,
19
+ "gradient_checkpointing": false,
20
+ "hidden_size": 4096,
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": null,
23
+ "jax": true,
24
+ "layer_norm_epsilon": 1e-05,
25
+ "max_position_embeddings": 2048,
26
+ "model_type": "gptj",
27
+ "num_heads": 16,
28
+ "num_layers": 28,
29
+ "resid_dropout": 0,
30
+ "rotary": true,
31
+ "rotary_dim": 64,
32
+ "summary_activation": null,
33
+ "summary_first_dropout": 0.1,
34
+ "summary_proj_to_labels": true,
35
+ "summary_type": "cls_index",
36
+ "summary_use_proj": true,
37
+ "transformers_version": "4.10.0.dev0",
38
+ "use_cache": true,
39
+ "vocab_size": 50400,
40
+ "window_size": 256,
41
+ "tokenizer_class": "GPT2Tokenizer",
42
+ "task_specific_params": {
43
+ "text-generation": {
44
+ "do_sample": true,
45
+ "temperature": 1.0,
46
+ "max_length": 50
47
+ }
48
+ }
49
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae2983ccc0a206013798f2e50a6b8fae0579d5ce18ee25d4d6c6221db0f3e875
3
+ size 12571637995