LeroyDyer commited on
Commit
85d5f3c
·
verified ·
1 Parent(s): 59e7333

Delete config2.json

Browse files
Files changed (1) hide show
  1. config2.json +0 -195
config2.json DELETED
@@ -1,195 +0,0 @@
1
- {
2
- "_name_or_path": "LeroyDyer/Mixtral_AI_Cyber_Q_Vision",
3
- "architectures": [
4
- "MistralForCausalLM"
5
- ],
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 1,
8
- "eos_token_id": 2,
9
- "hidden_act": "silu",
10
- "hidden_size": 4096,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 14336,
13
- "max_position_embeddings": 32768,
14
- "model_type": "mistral",
15
- "num_attention_heads": 32,
16
- "num_hidden_layers": 32,
17
- "num_key_value_heads": 8,
18
- "pad_token_id": 2,
19
- "rms_norm_eps": 1e-05,
20
- "rope_theta": 10000.0,
21
- "sliding_window": 4096,
22
- "tie_word_embeddings": false,
23
- "torch_dtype": "float16",
24
- "transformers_version": "4.38.2",
25
- "unsloth_version": "2024.3",
26
- "use_cache": true,
27
- "vocab_size": 32004,
28
- "architectures": [
29
- "VisionEncoderDecoderModel"
30
- ],
31
- "decoder": {
32
- "_name_or_path": "Locutusque/TinyMistral-248M-v2",
33
- "add_cross_attention": true,
34
- "architectures": [
35
- "MistralForCausalLM"
36
- ],
37
- "attention_dropout": 0.0,
38
- "bad_words_ids": null,
39
- "begin_suppress_tokens": null,
40
- "bos_token_id": 1,
41
- "chunk_size_feed_forward": 0,
42
- "cross_attention_hidden_size": null,
43
- "decoder_start_token_id": null,
44
- "diversity_penalty": 0.0,
45
- "do_sample": false,
46
- "early_stopping": false,
47
- "encoder_no_repeat_ngram_size": 0,
48
- "eos_token_id": 2,
49
- "exponential_decay_length_penalty": null,
50
- "finetuning_task": null,
51
- "forced_bos_token_id": null,
52
- "forced_eos_token_id": null,
53
- "hidden_act": "silu",
54
- "hidden_size": 1024,
55
- "id2label": {
56
- "0": "LABEL_0",
57
- "1": "LABEL_1"
58
- },
59
- "initializer_range": 0.02,
60
- "intermediate_size": 4096,
61
- "is_decoder": true,
62
- "is_encoder_decoder": false,
63
- "label2id": {
64
- "LABEL_0": 0,
65
- "LABEL_1": 1
66
- },
67
- "length_penalty": 1.0,
68
- "max_length": 20,
69
- "max_position_embeddings": 32768,
70
- "min_length": 0,
71
- "model_type": "mistral",
72
- "no_repeat_ngram_size": 0,
73
- "num_attention_heads": 32,
74
- "num_beam_groups": 1,
75
- "num_beams": 1,
76
- "num_hidden_layers": 12,
77
- "num_key_value_heads": 8,
78
- "num_return_sequences": 1,
79
- "output_attentions": false,
80
- "output_hidden_states": false,
81
- "output_scores": false,
82
- "pad_token_id": null,
83
- "prefix": null,
84
- "problem_type": null,
85
- "pruned_heads": {},
86
- "remove_invalid_values": false,
87
- "repetition_penalty": 1.0,
88
- "return_dict": true,
89
- "return_dict_in_generate": false,
90
- "rms_norm_eps": 1e-06,
91
- "rope_theta": 10000.0,
92
- "sep_token_id": null,
93
- "sliding_window": 32,
94
- "suppress_tokens": null,
95
- "task_specific_params": null,
96
- "temperature": 1.0,
97
- "tf_legacy_loss": false,
98
- "tie_encoder_decoder": false,
99
- "tie_word_embeddings": false,
100
- "tokenizer_class": null,
101
- "top_k": 50,
102
- "top_p": 1.0,
103
- "torch_dtype": "float32",
104
- "torchscript": false,
105
- "typical_p": 1.0,
106
- "use_bfloat16": false,
107
- "use_cache": true,
108
- "vocab_size": 32005
109
- },
110
- "encoder": {
111
- "_name_or_path": "Lin-Chen/ShareGPT4V-7B_Pretrained_vit-large336-l12",
112
- "add_cross_attention": false,
113
- "architectures": [
114
- "CLIPVisionModel"
115
- ],
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
- "dropout": 0.0,
126
- "early_stopping": false,
127
- "encoder_no_repeat_ngram_size": 0,
128
- "eos_token_id": null,
129
- "exponential_decay_length_penalty": null,
130
- "finetuning_task": null,
131
- "forced_bos_token_id": null,
132
- "forced_eos_token_id": null,
133
- "hidden_act": "quick_gelu",
134
- "hidden_size": 1024,
135
- "id2label": {
136
- "0": "LABEL_0",
137
- "1": "LABEL_1"
138
- },
139
- "image_size": 336,
140
- "initializer_factor": 1.0,
141
- "initializer_range": 0.02,
142
- "intermediate_size": 4096,
143
- "is_decoder": false,
144
- "is_encoder_decoder": false,
145
- "label2id": {
146
- "LABEL_0": 0,
147
- "LABEL_1": 1
148
- },
149
- "layer_norm_eps": 1e-05,
150
- "length_penalty": 1.0,
151
- "max_length": 20,
152
- "min_length": 0,
153
- "model_type": "clip_vision_model",
154
- "no_repeat_ngram_size": 0,
155
- "num_attention_heads": 16,
156
- "num_beam_groups": 1,
157
- "num_beams": 1,
158
- "num_channels": 3,
159
- "num_hidden_layers": 24,
160
- "num_return_sequences": 1,
161
- "output_attentions": false,
162
- "output_hidden_states": false,
163
- "output_scores": false,
164
- "pad_token_id": null,
165
- "patch_size": 14,
166
- "prefix": null,
167
- "problem_type": null,
168
- "projection_dim": 768,
169
- "pruned_heads": {},
170
- "remove_invalid_values": false,
171
- "repetition_penalty": 1.0,
172
- "return_dict": true,
173
- "return_dict_in_generate": false,
174
- "sep_token_id": null,
175
- "suppress_tokens": null,
176
- "task_specific_params": null,
177
- "temperature": 1.0,
178
- "tf_legacy_loss": false,
179
- "tie_encoder_decoder": false,
180
- "tie_word_embeddings": true,
181
- "tokenizer_class": null,
182
- "top_k": 50,
183
- "top_p": 1.0,
184
- "torch_dtype": "float32",
185
- "torchscript": false,
186
- "typical_p": 1.0,
187
- "use_bfloat16": false
188
- },
189
- "is_encoder_decoder": true,
190
- "model_type": "vision-encoder-decoder",
191
- "tie_word_embeddings": false,
192
- "torch_dtype": "float32",
193
- "transformers_version": "4.38.2"
194
- }
195
-