File size: 8,726 Bytes
3bcc962
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
{
    "_attn_implementation_autoset": false,
    "_attn_implementation_internal": null,
    "_commit_hash": null,
    "add_cross_attention": false,
    "architectures": [
        "InternVLChatModel"
    ],
    "auto_map": {
        "AutoConfig": "configuration_internvl_chat.InternVLChatConfig",
        "AutoModel": "modeling_internvl_chat.InternVLChatModel",
        "AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel"
    },
    "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,
    "downsample_ratio": 0.5,
    "dynamic_image_size": true,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": null,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "force_image_size": 448,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "hidden_size": 1536,
    "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
    },
    "image_fold": null,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
    },
    "length_penalty": 1.0,
    "max_dynamic_patch": 12,
    "max_length": 20,
    "min_dynamic_patch": 1,
    "min_length": 0,
    "model_type": "internvl_chat",
    "no_repeat_ngram_size": 0,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad2square": false,
    "pad_token_id": null,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "ps_version": "v2",
    "quantization": {
        "group_size": 64,
        "bits": 4
    },
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "select_layer": -1,
    "sep_token_id": null,
    "suppress_tokens": null,
    "system_message": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "template": "internvl2_5",
    "text_config": {
        "vocab_size": 151674,
        "max_position_embeddings": 32768,
        "hidden_size": 1536,
        "intermediate_size": 8960,
        "num_hidden_layers": 28,
        "num_attention_heads": 12,
        "use_sliding_window": false,
        "sliding_window": null,
        "max_window_layers": 70,
        "num_key_value_heads": 2,
        "hidden_act": "silu",
        "initializer_range": 0.02,
        "rms_norm_eps": 1e-06,
        "use_cache": false,
        "rope_theta": 1000000.0,
        "rope_scaling": {
            "factor": 2.0,
            "rope_type": "dynamic",
            "type": "dynamic"
        },
        "attention_dropout": 0.0,
        "return_dict": true,
        "output_hidden_states": false,
        "output_attentions": false,
        "torchscript": false,
        "torch_dtype": "bfloat16",
        "use_bfloat16": true,
        "tf_legacy_loss": false,
        "pruned_heads": {},
        "tie_word_embeddings": false,
        "chunk_size_feed_forward": 0,
        "is_encoder_decoder": false,
        "is_decoder": false,
        "cross_attention_hidden_size": null,
        "add_cross_attention": false,
        "tie_encoder_decoder": false,
        "max_length": 20,
        "min_length": 0,
        "do_sample": false,
        "early_stopping": false,
        "num_beams": 1,
        "num_beam_groups": 1,
        "diversity_penalty": 0.0,
        "temperature": 1.0,
        "top_k": 50,
        "top_p": 1.0,
        "typical_p": 1.0,
        "repetition_penalty": 1.0,
        "length_penalty": 1.0,
        "no_repeat_ngram_size": 0,
        "encoder_no_repeat_ngram_size": 0,
        "bad_words_ids": null,
        "num_return_sequences": 1,
        "output_scores": false,
        "return_dict_in_generate": false,
        "forced_bos_token_id": null,
        "forced_eos_token_id": null,
        "remove_invalid_values": false,
        "exponential_decay_length_penalty": null,
        "suppress_tokens": null,
        "begin_suppress_tokens": null,
        "architectures": [
            "Qwen2ForCausalLM"
        ],
        "finetuning_task": null,
        "id2label": {
            "0": "LABEL_0",
            "1": "LABEL_1"
        },
        "label2id": {
            "LABEL_0": 0,
            "LABEL_1": 1
        },
        "tokenizer_class": null,
        "prefix": null,
        "bos_token_id": 151643,
        "pad_token_id": null,
        "eos_token_id": 151643,
        "sep_token_id": null,
        "decoder_start_token_id": null,
        "task_specific_params": null,
        "problem_type": null,
        "_name_or_path": "./pretrained/Qwen2.5-32B-Instruct",
        "_attn_implementation_autoset": true,
        "transformers_version": "4.51.2",
        "model_type": "qwen2",
        "moe_config": null
    },
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": false,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torchscript": false,
    "transformers_version": null,
    "typical_p": 1.0,
    "use_backbone_lora": 0,
    "use_bfloat16": false,
    "use_llm_lora": 0,
    "use_thumbnail": true,
    "vision_config": {
        "return_dict": true,
        "output_hidden_states": false,
        "output_attentions": false,
        "torchscript": false,
        "torch_dtype": "bfloat16",
        "use_bfloat16": true,
        "tf_legacy_loss": false,
        "pruned_heads": {},
        "tie_word_embeddings": true,
        "chunk_size_feed_forward": 0,
        "is_encoder_decoder": false,
        "is_decoder": false,
        "cross_attention_hidden_size": null,
        "add_cross_attention": false,
        "tie_encoder_decoder": false,
        "max_length": 20,
        "min_length": 0,
        "do_sample": false,
        "early_stopping": false,
        "num_beams": 1,
        "num_beam_groups": 1,
        "diversity_penalty": 0.0,
        "temperature": 1.0,
        "top_k": 50,
        "top_p": 1.0,
        "typical_p": 1.0,
        "repetition_penalty": 1.0,
        "length_penalty": 1.0,
        "no_repeat_ngram_size": 0,
        "encoder_no_repeat_ngram_size": 0,
        "bad_words_ids": null,
        "num_return_sequences": 1,
        "output_scores": false,
        "return_dict_in_generate": false,
        "forced_bos_token_id": null,
        "forced_eos_token_id": null,
        "remove_invalid_values": false,
        "exponential_decay_length_penalty": null,
        "suppress_tokens": null,
        "begin_suppress_tokens": null,
        "architectures": [
            "InternVisionModel"
        ],
        "finetuning_task": null,
        "id2label": {
            "0": "LABEL_0",
            "1": "LABEL_1"
        },
        "label2id": {
            "LABEL_0": 0,
            "LABEL_1": 1
        },
        "tokenizer_class": null,
        "prefix": null,
        "bos_token_id": null,
        "pad_token_id": null,
        "eos_token_id": null,
        "sep_token_id": null,
        "decoder_start_token_id": null,
        "task_specific_params": null,
        "problem_type": null,
        "_name_or_path": "OpenGVLab/InternViT-6B-448px-V1-5",
        "_attn_implementation_autoset": true,
        "transformers_version": "4.51.2",
        "auto_map": {
            "AutoConfig": "configuration_intern_vit.InternVisionConfig",
            "AutoModel": "modeling_intern_vit.InternVisionModel"
        },
        "capacity_factor": 1.2,
        "eval_capacity_factor": 1.4,
        "laux_allreduce": "all_nodes",
        "model_type": "intern_vit_6b",
        "moe_coeff_ratio": 0.5,
        "moe_intermediate_size": 768,
        "moe_output_scale": 4.0,
        "noisy_gate_policy": "RSample_before",
        "num_experts": 8,
        "num_routed_experts": 4,
        "num_shared_experts": 4,
        "shared_expert_intermediate_size": 3072,
        "use_moe": false,
        "use_residual": true,
        "use_rts": false,
        "use_weighted_residual": false,
        "hidden_size": 1024,
        "intermediate_size": 4096,
        "dropout": 0.0,
        "drop_path_rate": 0.1,
        "num_hidden_layers": 24,
        "num_attention_heads": 16,
        "num_channels": 3,
        "patch_size": 14,
        "image_size": 448,
        "initializer_range": 1e-10,
        "initializer_factor": 0.1,
        "attention_dropout": 0.0,
        "layer_norm_eps": 1e-06,
        "hidden_act": "gelu",
        "norm_type": "layer_norm",
        "qkv_bias": true,
        "qk_normalization": false,
        "use_flash_attn": true,
        "skip_vision": true
    }
}