Aung2024 commited on
Commit
f3c41f5
1 Parent(s): 7e44677

Upload GPTNeoForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +61 -16
  2. generation_config.json +3 -0
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,22 +1,60 @@
1
  {
2
- "_name_or_path": "karpathy/gpt2_1558M_final2_hf",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
- "GPT2LMHeadModel"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  ],
7
- "attn_pdrop": 0.1,
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": 1600,
16
- "n_head": 25,
17
- "n_inner": null,
18
- "n_layer": 48,
19
- "n_positions": 1024,
20
  "quantization_config": {
21
  "_load_in_4bit": true,
22
  "_load_in_8bit": false,
@@ -32,17 +70,24 @@
32
  "load_in_8bit": false,
33
  "quant_method": "bitsandbytes"
34
  },
35
- "reorder_and_upcast_attn": false,
36
- "resid_pdrop": 0.1,
37
- "scale_attn_by_inverse_layer_idx": false,
38
- "scale_attn_weights": true,
39
  "summary_activation": null,
40
  "summary_first_dropout": 0.1,
41
  "summary_proj_to_labels": true,
42
  "summary_type": "cls_index",
43
  "summary_use_proj": true,
 
 
 
 
 
 
 
 
 
44
  "torch_dtype": "float16",
45
  "transformers_version": "4.41.2",
46
  "use_cache": true,
47
- "vocab_size": 50257
 
48
  }
 
1
  {
2
+ "_name_or_path": "EleutherAI/gpt-neo-1.3B",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
+ "GPTNeoForCausalLM"
6
+ ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local",
13
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local",
21
+ "global",
22
+ "local",
23
+ "global",
24
+ "local",
25
+ "global",
26
+ "local",
27
+ "global",
28
+ "local",
29
+ "global",
30
+ "local",
31
+ "global",
32
+ "local"
33
+ ],
34
+ "attention_types": [
35
+ [
36
+ [
37
+ "global",
38
+ "local"
39
+ ],
40
+ 12
41
+ ]
42
  ],
 
43
  "bos_token_id": 50256,
44
+ "classifier_dropout": 0.1,
45
+ "do_sample": true,
46
+ "embed_dropout": 0,
47
  "eos_token_id": 50256,
48
+ "gradient_checkpointing": false,
49
+ "hidden_size": 2048,
50
  "initializer_range": 0.02,
51
+ "intermediate_size": null,
52
  "layer_norm_epsilon": 1e-05,
53
+ "max_length": 50,
54
+ "max_position_embeddings": 2048,
55
+ "model_type": "gpt_neo",
56
+ "num_heads": 16,
57
+ "num_layers": 24,
 
 
58
  "quantization_config": {
59
  "_load_in_4bit": true,
60
  "_load_in_8bit": false,
 
70
  "load_in_8bit": false,
71
  "quant_method": "bitsandbytes"
72
  },
73
+ "resid_dropout": 0,
 
 
 
74
  "summary_activation": null,
75
  "summary_first_dropout": 0.1,
76
  "summary_proj_to_labels": true,
77
  "summary_type": "cls_index",
78
  "summary_use_proj": true,
79
+ "task_specific_params": {
80
+ "text-generation": {
81
+ "do_sample": true,
82
+ "max_length": 50,
83
+ "temperature": 0.9
84
+ }
85
+ },
86
+ "temperature": 0.9,
87
+ "tokenizer_class": "GPT2Tokenizer",
88
  "torch_dtype": "float16",
89
  "transformers_version": "4.41.2",
90
  "use_cache": true,
91
+ "vocab_size": 50257,
92
+ "window_size": 256
93
  }
generation_config.json CHANGED
@@ -1,7 +1,10 @@
1
  {
2
  "_from_model_config": true,
3
  "bos_token_id": 50256,
 
4
  "eos_token_id": 50256,
 
5
  "pad_token_id": 50256,
 
6
  "transformers_version": "4.41.2"
7
  }
 
1
  {
2
  "_from_model_config": true,
3
  "bos_token_id": 50256,
4
+ "do_sample": true,
5
  "eos_token_id": 50256,
6
+ "max_length": 50,
7
  "pad_token_id": 50256,
8
+ "temperature": 0.9,
9
  "transformers_version": "4.41.2"
10
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df59bb5152f95a86a04df5487e12f3e25d0ae6e55d6e1a5207f0785e13cb4f07
3
- size 995697192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf58ed08adfcff88ca15349bd663629d0c41f6171f2d0b7a5574fbc3648430d9
3
+ size 894818344