Hugging Face's logo

deepparag
/
DumBot

Text Generation
Transformers
PyTorch
gpt2
conversational
text-generation-inference
Model card Files
xet
Community
1
deepparag commited on
Commit
7f767c2
·
1 Parent(s): 56893ec

add model

Browse files
Files changed (2) hide show
  1. config.json +60 -22
  2. pytorch_model.bin +2 -2
config.json CHANGED
@@ -1,44 +1,82 @@
1
  {
2
- "_name_or_path": "output-small",
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
  "gradient_checkpointing": false,
 
12
  "initializer_range": 0.02,
 
13
  "layer_norm_epsilon": 1e-05,
14
- "model_type": "gpt2",
15
- "n_ctx": 1024,
16
- "n_embd": 1024,
17
- "n_head": 16,
18
- "n_inner": null,
19
- "n_layer": 24,
20
- "n_positions": 1024,
21
- "reorder_and_upcast_attn": false,
22
- "resid_pdrop": 0.1,
23
- "scale_attn_by_inverse_layer_idx": false,
24
- "scale_attn_weights": true,
25
  "summary_activation": null,
26
  "summary_first_dropout": 0.1,
27
  "summary_proj_to_labels": true,
28
  "summary_type": "cls_index",
29
  "summary_use_proj": true,
30
  "task_specific_params": {
31
- "conversational": {
32
  "do_sample": true,
33
- "max_length": 1000,
34
- "no_repeat_ngram_size": 4,
35
- "temperature": 0.8,
36
- "top_k": 100,
37
- "top_p": 0.7
38
  }
39
  },
 
40
  "torch_dtype": "float32",
41
  "transformers_version": "4.14.1",
42
  "use_cache": true,
43
- "vocab_size": 50257
 
44
  }
 
1
  {
2
+ "_name_or_path": "EleutherAI/gpt-neo-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
  "gradient_checkpointing": false,
55
+ "hidden_size": 2560,
56
  "initializer_range": 0.02,
57
+ "intermediate_size": null,
58
  "layer_norm_epsilon": 1e-05,
59
+ "max_position_embeddings": 2048,
60
+ "model_type": "gpt_neo",
61
+ "num_heads": 20,
62
+ "num_layers": 32,
63
+ "resid_dropout": 0,
 
 
 
 
 
 
64
  "summary_activation": null,
65
  "summary_first_dropout": 0.1,
66
  "summary_proj_to_labels": true,
67
  "summary_type": "cls_index",
68
  "summary_use_proj": true,
69
  "task_specific_params": {
70
+ "text-generation": {
71
  "do_sample": true,
72
+ "max_length": 50,
73
+ "temperature": 0.9
 
 
 
74
  }
75
  },
76
+ "tokenizer_class": "GPT2Tokenizer",
77
  "torch_dtype": "float32",
78
  "transformers_version": "4.14.1",
79
  "use_cache": true,
80
+ "vocab_size": 50257,
81
+ "window_size": 256
82
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1565cbad0add8dbadec81ce799ff03e2a444afa64dc3d41da081c9b31a969f1
3
- size 1444576537
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:055b66a0b9805bab97fc993b5324d6cea6f690e58415594a7c52e67f84bd2f63
3
+ size 10739628777