luodian commited on
Commit
74490d8
1 Parent(s): 4917f64
config.json ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "/data/bli/checkpoints/OTTER-MPT1B-RPJama",
4
+ "architectures": [
5
+ "OtterForConditionalGeneration"
6
+ ],
7
+ "cross_attn_every_n_layers": 1,
8
+ "model_type": "otter",
9
+ "text_config": {
10
+ "_name_or_path": "",
11
+ "add_cross_attention": false,
12
+ "alibi": true,
13
+ "alibi_bias_max": 8,
14
+ "architectures": [
15
+ "MosaicGPT"
16
+ ],
17
+ "attn_clip_qkv": null,
18
+ "attn_impl": "torch",
19
+ "attn_pdrop": 0,
20
+ "attn_qk_ln": true,
21
+ "attn_uses_sequence_id": false,
22
+ "bad_words_ids": null,
23
+ "begin_suppress_tokens": null,
24
+ "bos_token_id": null,
25
+ "chunk_size_feed_forward": 0,
26
+ "cross_attention_hidden_size": null,
27
+ "d_model": 2048,
28
+ "decoder_start_token_id": null,
29
+ "diversity_penalty": 0.0,
30
+ "do_sample": false,
31
+ "early_stopping": false,
32
+ "emb_init_std": null,
33
+ "emb_init_uniform_lim": null,
34
+ "emb_pdrop": 0,
35
+ "embedding_fraction": 1.0,
36
+ "encoder_no_repeat_ngram_size": 0,
37
+ "eos_token_id": null,
38
+ "exponential_decay_length_penalty": null,
39
+ "fan_mode": "fan_in",
40
+ "finetuning_task": null,
41
+ "forced_bos_token_id": null,
42
+ "forced_eos_token_id": null,
43
+ "hidden_size": 2048,
44
+ "id2label": {
45
+ "0": "LABEL_0",
46
+ "1": "LABEL_1"
47
+ },
48
+ "init_device": "cpu",
49
+ "init_div_is_residual": true,
50
+ "init_gain": 0,
51
+ "init_nonlinearity": "relu",
52
+ "init_std": 0.02,
53
+ "is_decoder": false,
54
+ "is_encoder_decoder": false,
55
+ "label2id": {
56
+ "LABEL_0": 0,
57
+ "LABEL_1": 1
58
+ },
59
+ "length_penalty": 1.0,
60
+ "logit_scale": null,
61
+ "low_precision_layernorm": true,
62
+ "max_length": 20,
63
+ "max_seq_len": 2048,
64
+ "min_length": 0,
65
+ "mlp_ratio": 4,
66
+ "model_type": "mosaic_gpt",
67
+ "n_heads": 16,
68
+ "n_layers": 24,
69
+ "no_bias": true,
70
+ "no_repeat_ngram_size": 0,
71
+ "num_beam_groups": 1,
72
+ "num_beams": 1,
73
+ "num_return_sequences": 1,
74
+ "output_attentions": false,
75
+ "output_hidden_states": false,
76
+ "output_scores": false,
77
+ "pad_token_id": null,
78
+ "param_init_fn": "kaiming_normal_",
79
+ "prefix": null,
80
+ "prefix_lm": false,
81
+ "problem_type": null,
82
+ "pruned_heads": {},
83
+ "remove_invalid_values": false,
84
+ "repetition_penalty": 1.0,
85
+ "resid_pdrop": 0,
86
+ "return_dict": true,
87
+ "return_dict_in_generate": false,
88
+ "sep_token_id": null,
89
+ "softmax_scale": null,
90
+ "suppress_tokens": null,
91
+ "task_specific_params": null,
92
+ "temperature": 1.0,
93
+ "tf_legacy_loss": false,
94
+ "tie_encoder_decoder": false,
95
+ "tie_word_embeddings": true,
96
+ "tokenizer_class": null,
97
+ "tokenizer_name": "EleutherAI/gpt-neox-20b",
98
+ "top_k": 50,
99
+ "top_p": 1.0,
100
+ "torch_dtype": "float32",
101
+ "torchscript": false,
102
+ "transformers_version": "4.29.0",
103
+ "typical_p": 1.0,
104
+ "use_bfloat16": false,
105
+ "use_cache": false,
106
+ "verbose": 0,
107
+ "vocab_size": 50432
108
+ },
109
+ "torch_dtype": "float32",
110
+ "transformers_version": null,
111
+ "use_media_placement_augmentation": true,
112
+ "vision_config": {
113
+ "_name_or_path": "openai/clip-vit-large-patch14",
114
+ "add_cross_attention": false,
115
+ "architectures": null,
116
+ "attention_dropout": 0.0,
117
+ "bad_words_ids": null,
118
+ "begin_suppress_tokens": null,
119
+ "bos_token_id": null,
120
+ "chunk_size_feed_forward": 0,
121
+ "cross_attention_hidden_size": null,
122
+ "decoder_start_token_id": null,
123
+ "diversity_penalty": 0.0,
124
+ "do_sample": false,
125
+ "early_stopping": false,
126
+ "encoder_no_repeat_ngram_size": 0,
127
+ "eos_token_id": null,
128
+ "exponential_decay_length_penalty": null,
129
+ "finetuning_task": null,
130
+ "forced_bos_token_id": null,
131
+ "forced_eos_token_id": null,
132
+ "hidden_act": "quick_gelu",
133
+ "hidden_size": 1024,
134
+ "id2label": {
135
+ "0": "LABEL_0",
136
+ "1": "LABEL_1"
137
+ },
138
+ "image_size": 224,
139
+ "initializer_factor": 1.0,
140
+ "initializer_range": 0.02,
141
+ "intermediate_size": 4096,
142
+ "is_decoder": false,
143
+ "is_encoder_decoder": false,
144
+ "label2id": {
145
+ "LABEL_0": 0,
146
+ "LABEL_1": 1
147
+ },
148
+ "layer_norm_eps": 1e-05,
149
+ "length_penalty": 1.0,
150
+ "max_length": 20,
151
+ "min_length": 0,
152
+ "model_type": "clip_vision_model",
153
+ "no_repeat_ngram_size": 0,
154
+ "num_attention_heads": 16,
155
+ "num_beam_groups": 1,
156
+ "num_beams": 1,
157
+ "num_channels": 3,
158
+ "num_hidden_layers": 24,
159
+ "num_return_sequences": 1,
160
+ "output_attentions": false,
161
+ "output_hidden_states": false,
162
+ "output_scores": false,
163
+ "pad_token_id": null,
164
+ "patch_size": 14,
165
+ "prefix": null,
166
+ "problem_type": null,
167
+ "projection_dim": 512,
168
+ "pruned_heads": {},
169
+ "remove_invalid_values": false,
170
+ "repetition_penalty": 1.0,
171
+ "return_dict": true,
172
+ "return_dict_in_generate": false,
173
+ "sep_token_id": null,
174
+ "suppress_tokens": null,
175
+ "task_specific_params": null,
176
+ "temperature": 1.0,
177
+ "tf_legacy_loss": false,
178
+ "tie_encoder_decoder": false,
179
+ "tie_word_embeddings": true,
180
+ "tokenizer_class": null,
181
+ "top_k": 50,
182
+ "top_p": 1.0,
183
+ "torch_dtype": null,
184
+ "torchscript": false,
185
+ "transformers_version": "4.29.0",
186
+ "typical_p": 1.0,
187
+ "use_bfloat16": false
188
+ }
189
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00fe497fcf6e5879b5cae2674c8499facf75dec4e09f3696923a58dc923a093a
3
+ size 9991503463
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d325540380c71972d189b305093236dc165537cbc49ccc7bb51d9a0650a751da
3
+ size 243420981
pytorch_model.bin.index.json ADDED
The diff for this file is too large to render. See raw diff