Hugging Face's logo

ortofasfat
/
hh-open_assistant

Text Generation
Transformers
PyTorch
English
gpt_neox
text-generation-inference
Model card Files
xet
Community
1
ortofasfat commited on
Commit
01f7f37
·
1 Parent(s): 2597e81

Upload folder using huggingface_hub

Browse files
Files changed (4) hide show
  1. config.json +85 -70
  2. generation_config.json +74 -4
  3. pytorch_model.bin +3 -0
  4. training_args.bin +1 -1
config.json CHANGED
@@ -1,81 +1,96 @@
1
  {
2
- "_name_or_path": "PygmalionAI/pygmalion-2.7b",
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
- "global",
34
- "local",
35
- "global",
36
- "local",
37
- "global",
38
- "local",
39
- "global",
40
- "local"
41
- ],
42
- "attention_types": [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43
  [
44
- [
45
- "global",
46
- "local"
47
- ],
48
- 16
49
  ]
50
  ],
51
- "bos_token_id": 50256,
52
- "embed_dropout": 0,
53
- "eos_token_id": 50256,
54
- "hidden_size": 2560,
55
  "initializer_range": 0.02,
56
- "intermediate_size": null,
57
- "layer_norm_epsilon": 1e-05,
58
  "max_position_embeddings": 2048,
59
- "model_type": "gpt_neo",
60
- "num_heads": 20,
61
- "num_layers": 32,
62
- "resid_dropout": 0,
63
- "summary_activation": null,
64
- "summary_first_dropout": 0.1,
65
- "summary_proj_to_labels": true,
66
- "summary_type": "cls_index",
67
- "summary_use_proj": true,
68
- "task_specific_params": {
69
- "text-generation": {
70
- "do_sample": true,
71
- "max_length": 50,
72
- "temperature": 0.9
73
- }
74
- },
75
- "tokenizer_class": "GPT2Tokenizer",
76
  "torch_dtype": "float32",
77
  "transformers_version": "4.28.1",
78
- "use_cache": false,
79
- "vocab_size": 50279,
80
- "window_size": 256
81
  }
 
1
  {
2
+ "_name_or_path": "PygmalionAI/pygmalion-1.3b",
 
3
  "architectures": [
4
+ "GPTNeoXForCausalLM"
5
  ],
6
+ "bad_words_ids": [
7
+ [
8
+ 434,
9
+ 15694,
10
+ 66,
11
+ 27,
12
+ 209
13
+ ],
14
+ [
15
+ 15362
16
+ ],
17
+ [
18
+ 1713
19
+ ],
20
+ [
21
+ 1713,
22
+ 64
23
+ ],
24
+ [
25
+ 1713,
26
+ 876
27
+ ],
28
+ [
29
+ 2016,
30
+ 251,
31
+ 857,
32
+ 75,
33
+ 9194,
34
+ 35478
35
+ ],
36
+ [
37
+ 2391
38
+ ],
39
+ [
40
+ 20340
41
+ ],
42
+ [
43
+ 33021
44
+ ],
45
+ [
46
+ 2391,
47
+ 1051
48
+ ],
49
+ [
50
+ 5638
51
+ ],
52
+ [
53
+ 2391,
54
+ 20340
55
+ ],
56
+ [
57
+ 5638,
58
+ 537
59
+ ],
60
+ [
61
+ 1559,
62
+ 2345
63
+ ],
64
+ [
65
+ 1559,
66
+ 7849
67
+ ],
68
+ [
69
+ 1559,
70
+ 17379
71
+ ],
72
  [
73
+ 25321,
74
+ 4611
 
 
 
75
  ]
76
  ],
77
+ "bos_token_id": 0,
78
+ "eos_token_id": 0,
79
+ "hidden_act": "gelu",
80
+ "hidden_size": 2048,
81
  "initializer_range": 0.02,
82
+ "intermediate_size": 8192,
83
+ "layer_norm_eps": 1e-05,
84
  "max_position_embeddings": 2048,
85
+ "model_type": "gpt_neox",
86
+ "num_attention_heads": 16,
87
+ "num_hidden_layers": 24,
88
+ "rotary_emb_base": 10000,
89
+ "rotary_pct": 0.25,
90
+ "tie_word_embeddings": false,
 
 
 
 
 
 
 
 
 
 
 
91
  "torch_dtype": "float32",
92
  "transformers_version": "4.28.1",
93
+ "use_cache": true,
94
+ "use_parallel_residual": true,
95
+ "vocab_size": 50279
96
  }
generation_config.json CHANGED
@@ -1,7 +1,77 @@
1
  {
2
  "_from_model_config": true,
3
- "bos_token_id": 50256,
4
- "eos_token_id": 50256,
5
- "transformers_version": "4.28.1",
6
- "use_cache": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bad_words_ids": [
4
+ [
5
+ 434,
6
+ 15694,
7
+ 66,
8
+ 27,
9
+ 209
10
+ ],
11
+ [
12
+ 15362
13
+ ],
14
+ [
15
+ 1713
16
+ ],
17
+ [
18
+ 1713,
19
+ 64
20
+ ],
21
+ [
22
+ 1713,
23
+ 876
24
+ ],
25
+ [
26
+ 2016,
27
+ 251,
28
+ 857,
29
+ 75,
30
+ 9194,
31
+ 35478
32
+ ],
33
+ [
34
+ 2391
35
+ ],
36
+ [
37
+ 20340
38
+ ],
39
+ [
40
+ 33021
41
+ ],
42
+ [
43
+ 2391,
44
+ 1051
45
+ ],
46
+ [
47
+ 5638
48
+ ],
49
+ [
50
+ 2391,
51
+ 20340
52
+ ],
53
+ [
54
+ 5638,
55
+ 537
56
+ ],
57
+ [
58
+ 1559,
59
+ 2345
60
+ ],
61
+ [
62
+ 1559,
63
+ 7849
64
+ ],
65
+ [
66
+ 1559,
67
+ 17379
68
+ ],
69
+ [
70
+ 25321,
71
+ 4611
72
+ ]
73
+ ],
74
+ "bos_token_id": 0,
75
+ "eos_token_id": 0,
76
+ "transformers_version": "4.28.1"
77
  }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bb23bdd15f2cd55b973edd309db0148055a3cde463d8ddb99241fbd54ff369c
3
+ size 5758970401
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:002e67e22937ca12201d62769c954b52cbc661bf8d92131dbd7e6bdab1961687
3
  size 3579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:539bc5db348d5051a7d0d0e0b366781d838004bd111569b30ad50d88310d1c7d
3
  size 3579