Update config.json
Browse files- config.json +133 -3
config.json
CHANGED
@@ -1,9 +1,139 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
{
|
2 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"task_specific_params": {
|
4 |
"text-generation": {
|
5 |
"do_sample": true,
|
6 |
-
"max_length":
|
|
|
7 |
}
|
8 |
-
}
|
|
|
|
|
|
|
|
|
|
|
9 |
}
|
|
|
|
1 |
+
Hugging Face's logo
|
2 |
+
Hugging Face
|
3 |
+
Search models, datasets, users...
|
4 |
+
Models
|
5 |
+
Datasets
|
6 |
+
Spaces
|
7 |
+
Posts
|
8 |
+
Docs
|
9 |
+
Pricing
|
10 |
+
|
11 |
+
|
12 |
+
|
13 |
+
|
14 |
+
EleutherAI
|
15 |
+
/
|
16 |
+
gpt-neo-2.7B
|
17 |
+
|
18 |
+
like
|
19 |
+
400
|
20 |
+
Text Generation
|
21 |
+
Transformers
|
22 |
+
PyTorch
|
23 |
+
JAX
|
24 |
+
Rust
|
25 |
+
Safetensors
|
26 |
+
|
27 |
+
EleutherAI/pile
|
28 |
+
English
|
29 |
+
gpt_neo
|
30 |
+
text generation
|
31 |
+
causal-lm
|
32 |
+
Inference Endpoints
|
33 |
+
|
34 |
+
License:
|
35 |
+
mit
|
36 |
+
Model card
|
37 |
+
Files and versions
|
38 |
+
Community
|
39 |
+
15
|
40 |
+
gpt-neo-2.7B
|
41 |
+
/
|
42 |
+
config.json
|
43 |
+
|
44 |
+
valhalla's picture
|
45 |
+
valhalla
|
46 |
+
add flax model
|
47 |
+
0b8087b
|
48 |
+
about 3 years ago
|
49 |
+
raw
|
50 |
+
|
51 |
+
Copy download link
|
52 |
+
history
|
53 |
+
blame
|
54 |
+
contribute
|
55 |
+
delete
|
56 |
+
No virus
|
57 |
+
|
58 |
+
1.46 kB
|
59 |
{
|
60 |
+
"activation_function": "gelu_new",
|
61 |
+
"architectures": [
|
62 |
+
"GPTNeoForCausalLM"
|
63 |
+
],
|
64 |
+
"attention_dropout": 0,
|
65 |
+
"attention_layers": [
|
66 |
+
"global",
|
67 |
+
"local",
|
68 |
+
"global",
|
69 |
+
"local",
|
70 |
+
"global",
|
71 |
+
"local",
|
72 |
+
"global",
|
73 |
+
"local",
|
74 |
+
"global",
|
75 |
+
"local",
|
76 |
+
"global",
|
77 |
+
"local",
|
78 |
+
"global",
|
79 |
+
"local",
|
80 |
+
"global",
|
81 |
+
"local",
|
82 |
+
"global",
|
83 |
+
"local",
|
84 |
+
"global",
|
85 |
+
"local",
|
86 |
+
"global",
|
87 |
+
"local",
|
88 |
+
"global",
|
89 |
+
"local",
|
90 |
+
"global",
|
91 |
+
"local",
|
92 |
+
"global",
|
93 |
+
"local",
|
94 |
+
"global",
|
95 |
+
"local",
|
96 |
+
"global",
|
97 |
+
"local"
|
98 |
+
],
|
99 |
+
"attention_types": [
|
100 |
+
[
|
101 |
+
[
|
102 |
+
"global",
|
103 |
+
"local"
|
104 |
+
],
|
105 |
+
16
|
106 |
+
]
|
107 |
+
],
|
108 |
+
"bos_token_id": 50256,
|
109 |
+
"embed_dropout": 0,
|
110 |
+
"eos_token_id": 50256,
|
111 |
+
"gradient_checkpointing": false,
|
112 |
+
"hidden_size": 2560,
|
113 |
+
"initializer_range": 0.02,
|
114 |
+
"intermediate_size": null,
|
115 |
+
"layer_norm_epsilon": 1e-05,
|
116 |
+
"max_position_embeddings": 2048,
|
117 |
+
"model_type": "gpt_neo",
|
118 |
+
"num_heads": 20,
|
119 |
+
"num_layers": 32,
|
120 |
+
"resid_dropout": 0,
|
121 |
+
"summary_activation": null,
|
122 |
+
"summary_first_dropout": 0.1,
|
123 |
+
"summary_proj_to_labels": true,
|
124 |
+
"summary_type": "cls_index",
|
125 |
+
"summary_use_proj": true,
|
126 |
"task_specific_params": {
|
127 |
"text-generation": {
|
128 |
"do_sample": true,
|
129 |
+
"max_length": 50,
|
130 |
+
"temperature": 0.9
|
131 |
}
|
132 |
+
},
|
133 |
+
"tokenizer_class": "GPT2Tokenizer",
|
134 |
+
"transformers_version": "4.9.0.dev0",
|
135 |
+
"use_cache": true,
|
136 |
+
"vocab_size": 50257,
|
137 |
+
"window_size": 256
|
138 |
}
|
139 |
+
|