LeroyDyer commited on
Commit
acca561
·
verified ·
1 Parent(s): b98301c

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +170 -2
config.json CHANGED
@@ -1,3 +1,171 @@
1
  {
2
- "model_type": "mistral"
3
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
2
+ "architectures": [
3
+ "LlavaMistralForCausalLM"
4
+ ],
5
+ "image_seq_length": 576,
6
+ "image_token_index": 32000,
7
+ "model_type": "llava",
8
+ "multimodal_projector_bias": true,
9
+ "projector_hidden_act": "gelu",
10
+ "text_config": {
11
+ "_attn_implementation_autoset": false,
12
+ "_name_or_path": "LeroyDyer/_Spydaz_Web_AI_Student_History_",
13
+ "add_cross_attention": false,
14
+ "architectures": [
15
+ "MistralForCausalLM"
16
+ ],
17
+ "attention_dropout": 0.0,
18
+ "bad_words_ids": null,
19
+ "begin_suppress_tokens": null,
20
+ "bos_token_id": 1,
21
+ "chunk_size_feed_forward": 0,
22
+ "cross_attention_hidden_size": null,
23
+ "decoder_start_token_id": null,
24
+ "diversity_penalty": 0.0,
25
+ "do_sample": false,
26
+ "early_stopping": false,
27
+ "encoder_no_repeat_ngram_size": 0,
28
+ "eos_token_id": 2,
29
+ "exponential_decay_length_penalty": null,
30
+ "finetuning_task": null,
31
+ "forced_bos_token_id": null,
32
+ "forced_eos_token_id": null,
33
+ "head_dim": 128,
34
+ "hidden_act": "silu",
35
+ "hidden_size": 4096,
36
+ "id2label": {
37
+ "0": "LABEL_0",
38
+ "1": "LABEL_1"
39
+ },
40
+ "initializer_range": 0.02,
41
+ "intermediate_size": 14336,
42
+ "is_decoder": false,
43
+ "is_encoder_decoder": false,
44
+ "label2id": {
45
+ "LABEL_0": 0,
46
+ "LABEL_1": 1
47
+ },
48
+ "length_penalty": 1.0,
49
+ "max_length": 20,
50
+ "max_position_embeddings": 131072,
51
+ "min_length": 0,
52
+ "model_type": "mistral",
53
+ "no_repeat_ngram_size": 0,
54
+ "num_attention_heads": 32,
55
+ "num_beam_groups": 1,
56
+ "num_beams": 1,
57
+ "num_hidden_layers": 32,
58
+ "num_key_value_heads": 8,
59
+ "num_return_sequences": 1,
60
+ "output_attentions": false,
61
+ "output_hidden_states": false,
62
+ "output_scores": false,
63
+ "pad_token_id": 0,
64
+ "prefix": null,
65
+ "problem_type": null,
66
+ "pruned_heads": {},
67
+ "remove_invalid_values": false,
68
+ "repetition_penalty": 1.0,
69
+ "return_dict": true,
70
+ "return_dict_in_generate": false,
71
+ "rms_norm_eps": 1e-06,
72
+ "rope_scaling": null,
73
+ "rope_theta": 10000.0,
74
+ "sep_token_id": null,
75
+ "sliding_window": 6096,
76
+ "suppress_tokens": null,
77
+ "task_specific_params": null,
78
+ "temperature": 1.0,
79
+ "tf_legacy_loss": false,
80
+ "tie_encoder_decoder": false,
81
+ "tie_word_embeddings": false,
82
+ "tokenizer_class": null,
83
+ "top_k": 50,
84
+ "top_p": 1.0,
85
+ "torch_dtype": "bfloat16",
86
+ "torchscript": false,
87
+ "typical_p": 1.0,
88
+ "unsloth_version": "2025.3.17",
89
+ "use_bfloat16": false,
90
+ "use_cache": true,
91
+ "vocab_size": 32002
92
+ },
93
+ "torch_dtype": "float16",
94
+ "transformers_version": "4.49.0",
95
+ "vision_config": {
96
+ "_attn_implementation_autoset": false,
97
+ "_name_or_path": "",
98
+ "add_cross_attention": false,
99
+ "architectures": null,
100
+ "attention_dropout": 0.0,
101
+ "bad_words_ids": null,
102
+ "begin_suppress_tokens": null,
103
+ "bos_token_id": null,
104
+ "chunk_size_feed_forward": 0,
105
+ "cross_attention_hidden_size": null,
106
+ "decoder_start_token_id": null,
107
+ "diversity_penalty": 0.0,
108
+ "do_sample": false,
109
+ "early_stopping": false,
110
+ "encoder_no_repeat_ngram_size": 0,
111
+ "eos_token_id": null,
112
+ "exponential_decay_length_penalty": null,
113
+ "finetuning_task": null,
114
+ "forced_bos_token_id": null,
115
+ "forced_eos_token_id": null,
116
+ "hidden_act": "gelu_pytorch_tanh",
117
+ "hidden_size": 1152,
118
+ "id2label": {
119
+ "0": "LABEL_0",
120
+ "1": "LABEL_1"
121
+ },
122
+ "image_size": 384,
123
+ "intermediate_size": 4304,
124
+ "is_decoder": false,
125
+ "is_encoder_decoder": false,
126
+ "label2id": {
127
+ "LABEL_0": 0,
128
+ "LABEL_1": 1
129
+ },
130
+ "layer_norm_eps": 1e-06,
131
+ "length_penalty": 1.0,
132
+ "max_length": 20,
133
+ "min_length": 0,
134
+ "model_type": "siglip_vision_model",
135
+ "no_repeat_ngram_size": 0,
136
+ "num_attention_heads": 16,
137
+ "num_beam_groups": 1,
138
+ "num_beams": 1,
139
+ "num_channels": 3,
140
+ "num_hidden_layers": 27,
141
+ "num_return_sequences": 1,
142
+ "output_attentions": false,
143
+ "output_hidden_states": false,
144
+ "output_scores": false,
145
+ "pad_token_id": null,
146
+ "patch_size": 14,
147
+ "prefix": null,
148
+ "problem_type": null,
149
+ "pruned_heads": {},
150
+ "remove_invalid_values": false,
151
+ "repetition_penalty": 1.0,
152
+ "return_dict": true,
153
+ "return_dict_in_generate": false,
154
+ "sep_token_id": null,
155
+ "suppress_tokens": null,
156
+ "task_specific_params": null,
157
+ "temperature": 1.0,
158
+ "tf_legacy_loss": false,
159
+ "tie_encoder_decoder": false,
160
+ "tie_word_embeddings": true,
161
+ "tokenizer_class": null,
162
+ "top_k": 50,
163
+ "top_p": 1.0,
164
+ "torch_dtype": null,
165
+ "torchscript": false,
166
+ "typical_p": 1.0,
167
+ "use_bfloat16": false
168
+ },
169
+ "vision_feature_layer": -2,
170
+ "vision_feature_select_strategy": "default"
171
+ }