File size: 5,625 Bytes
bdd4e1e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
{
    "architectures": [
        "LlavaForConditionalGeneration"
    ],
    "ignore_index": -100,
    "image_seq_length": 576,
    "image_token_index": 32000,
    "model_type": "llava",
    "pad_token_id": 32001,
    "projector_hidden_act": "gelu",
    "quantization": {
        "group_size": 64,
        "bits": 4
    },
    "text_config": {
        "_attn_implementation_autoset": false,
        "_name_or_path": "lmsys/vicuna-7b-v1.5",
        "add_cross_attention": false,
        "architectures": [
            "LlamaForCausalLM"
        ],
        "attention_bias": false,
        "attention_dropout": 0.0,
        "bad_words_ids": null,
        "begin_suppress_tokens": null,
        "bos_token_id": 1,
        "chunk_size_feed_forward": 0,
        "cross_attention_hidden_size": null,
        "decoder_start_token_id": null,
        "diversity_penalty": 0.0,
        "do_sample": false,
        "early_stopping": false,
        "encoder_no_repeat_ngram_size": 0,
        "eos_token_id": 2,
        "exponential_decay_length_penalty": null,
        "finetuning_task": null,
        "forced_bos_token_id": null,
        "forced_eos_token_id": null,
        "head_dim": 128,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "id2label": {
            "0": "LABEL_0",
            "1": "LABEL_1"
        },
        "initializer_range": 0.02,
        "intermediate_size": 11008,
        "is_decoder": false,
        "is_encoder_decoder": false,
        "label2id": {
            "LABEL_0": 0,
            "LABEL_1": 1
        },
        "length_penalty": 1.0,
        "max_length": 20,
        "max_position_embeddings": 4096,
        "min_length": 0,
        "mlp_bias": false,
        "model_type": "llama",
        "no_repeat_ngram_size": 0,
        "num_attention_heads": 32,
        "num_beam_groups": 1,
        "num_beams": 1,
        "num_hidden_layers": 32,
        "num_key_value_heads": 32,
        "num_return_sequences": 1,
        "output_attentions": false,
        "output_hidden_states": false,
        "output_scores": false,
        "pad_token_id": 32001,
        "prefix": null,
        "pretraining_tp": 1,
        "problem_type": null,
        "pruned_heads": {},
        "remove_invalid_values": false,
        "repetition_penalty": 1.0,
        "return_dict": true,
        "return_dict_in_generate": false,
        "rms_norm_eps": 1e-05,
        "rope_scaling": null,
        "rope_theta": 10000.0,
        "sep_token_id": null,
        "suppress_tokens": null,
        "task_specific_params": null,
        "temperature": 1.0,
        "tf_legacy_loss": false,
        "tie_encoder_decoder": false,
        "tie_word_embeddings": false,
        "tokenizer_class": null,
        "top_k": 50,
        "top_p": 1.0,
        "torch_dtype": "float16",
        "torchscript": false,
        "typical_p": 1.0,
        "use_bfloat16": false,
        "use_cache": true,
        "vocab_size": 32064
    },
    "tie_word_embeddings": false,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.46.3",
    "unsloth_fixed": true,
    "vision_config": {
        "_attn_implementation_autoset": false,
        "_name_or_path": "",
        "add_cross_attention": false,
        "architectures": null,
        "attention_dropout": 0.0,
        "bad_words_ids": null,
        "begin_suppress_tokens": null,
        "bos_token_id": null,
        "chunk_size_feed_forward": 0,
        "cross_attention_hidden_size": null,
        "decoder_start_token_id": null,
        "diversity_penalty": 0.0,
        "do_sample": false,
        "early_stopping": false,
        "encoder_no_repeat_ngram_size": 0,
        "eos_token_id": null,
        "exponential_decay_length_penalty": null,
        "finetuning_task": null,
        "forced_bos_token_id": null,
        "forced_eos_token_id": null,
        "hidden_act": "quick_gelu",
        "hidden_size": 1024,
        "id2label": {
            "0": "LABEL_0",
            "1": "LABEL_1"
        },
        "image_size": 336,
        "initializer_factor": 1.0,
        "initializer_range": 0.02,
        "intermediate_size": 4096,
        "is_decoder": false,
        "is_encoder_decoder": false,
        "label2id": {
            "LABEL_0": 0,
            "LABEL_1": 1
        },
        "layer_norm_eps": 1e-05,
        "length_penalty": 1.0,
        "max_length": 20,
        "min_length": 0,
        "model_type": "clip_vision_model",
        "no_repeat_ngram_size": 0,
        "num_attention_heads": 16,
        "num_beam_groups": 1,
        "num_beams": 1,
        "num_channels": 3,
        "num_hidden_layers": 24,
        "num_return_sequences": 1,
        "output_attentions": false,
        "output_hidden_states": false,
        "output_scores": false,
        "pad_token_id": 32001,
        "patch_size": 14,
        "prefix": null,
        "problem_type": null,
        "projection_dim": 768,
        "pruned_heads": {},
        "remove_invalid_values": false,
        "repetition_penalty": 1.0,
        "return_dict": true,
        "return_dict_in_generate": false,
        "sep_token_id": null,
        "suppress_tokens": null,
        "task_specific_params": null,
        "temperature": 1.0,
        "tf_legacy_loss": false,
        "tie_encoder_decoder": false,
        "tie_word_embeddings": true,
        "tokenizer_class": null,
        "top_k": 50,
        "top_p": 1.0,
        "torch_dtype": null,
        "torchscript": false,
        "typical_p": 1.0,
        "use_bfloat16": false,
        "vocab_size": 32000
    },
    "vision_feature_layer": -2,
    "vision_feature_select_strategy": "default",
    "vocab_size": 32064
}