Tingquan commited on
Commit
486c0c8
·
verified ·
1 Parent(s): 51b49df

Upload config.json

Browse files
Files changed (1) hide show
  1. config.json +149 -5
config.json CHANGED
@@ -1,6 +1,150 @@
1
  {
2
- "mode": "paddle",
3
- "Global": {
4
- "model_name": "PP-DocBee-7B"
5
- }
6
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
2
+ "architectures": [
3
+ "Qwen2VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "image_token_id": 151655,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 18944,
14
+ "max_position_embeddings": 32768,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen2_vl",
17
+ "num_attention_heads": 28,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 4,
20
+ "paddlenlp_version": "3.0.0b2",
21
+ "rms_norm_eps": 1e-06,
22
+ "rope_scaling": {
23
+ "mrope_section": [
24
+ 16,
25
+ 24,
26
+ 24
27
+ ],
28
+ "type": "mrope"
29
+ },
30
+ "rope_theta": 1000000.0,
31
+ "sliding_window": 32768,
32
+ "tie_word_embeddings": false,
33
+ "use_sliding_window": false,
34
+ "video_token_id": 151656,
35
+ "vision_config": {
36
+ "_name_or_path": "",
37
+ "add_cross_attention": false,
38
+ "architectures": null,
39
+ "attn_implementation": "eager",
40
+ "bad_words_ids": null,
41
+ "begin_suppress_tokens": null,
42
+ "bos_token_id": null,
43
+ "chunk_size_feed_forward": 0,
44
+ "classifier_dropout": null,
45
+ "context_parallel_degree": 1,
46
+ "cross_attention_hidden_size": null,
47
+ "decoder_start_token_id": null,
48
+ "depth": 32,
49
+ "diversity_penalty": 0.0,
50
+ "do_sample": false,
51
+ "dtype": "float32",
52
+ "early_stopping": false,
53
+ "embed_dim": 1280,
54
+ "encoder_no_repeat_ngram_size": 0,
55
+ "eos_token_id": null,
56
+ "exponential_decay_length_penalty": null,
57
+ "finetuning_task": null,
58
+ "forced_bos_token_id": null,
59
+ "forced_eos_token_id": null,
60
+ "fuse_attention_ffn": false,
61
+ "fuse_attention_qkv": false,
62
+ "fuse_sequence_parallel_allreduce": false,
63
+ "hidden_act": "quick_gelu",
64
+ "hidden_size": 3584,
65
+ "id2label": {
66
+ "0": "LABEL_0",
67
+ "1": "LABEL_1"
68
+ },
69
+ "in_channels": 3,
70
+ "in_chans": 3,
71
+ "is_decoder": false,
72
+ "is_encoder_decoder": false,
73
+ "label2id": {
74
+ "LABEL_0": 0,
75
+ "LABEL_1": 1
76
+ },
77
+ "length_penalty": 1.0,
78
+ "max_length": 20,
79
+ "min_length": 0,
80
+ "mlp_ratio": 4,
81
+ "model_type": "qwen2_vl",
82
+ "no_recompute_layers": null,
83
+ "no_repeat_ngram_size": 0,
84
+ "num_beam_groups": 1,
85
+ "num_beams": 1,
86
+ "num_choices": null,
87
+ "num_heads": 16,
88
+ "num_return_sequences": 1,
89
+ "output_attentions": false,
90
+ "output_hidden_states": false,
91
+ "output_scores": false,
92
+ "pad_token_id": null,
93
+ "patch_size": 14,
94
+ "pipeline_parallel_degree": 1,
95
+ "pp_recompute_interval": 1,
96
+ "prefix": null,
97
+ "problem_type": null,
98
+ "pruned_heads": {},
99
+ "quantization_config": {
100
+ "act_quant_method": "abs_max",
101
+ "llm_int8_threshold": 6.0,
102
+ "quant_round_type": 0,
103
+ "quant_type": null,
104
+ "shift": false,
105
+ "shift_smooth_all_linears": false,
106
+ "smooth": false,
107
+ "weight_blocksize": 64,
108
+ "weight_double_quant": false,
109
+ "weight_double_quant_block_size": 256,
110
+ "weight_quant_method": "abs_max_channel_wise",
111
+ "weight_quantize_algo": null
112
+ },
113
+ "recompute": false,
114
+ "recompute_granularity": "full",
115
+ "recompute_use_reentrant": false,
116
+ "remove_invalid_values": false,
117
+ "repetition_penalty": 1.0,
118
+ "return_dict": false,
119
+ "return_dict_in_generate": false,
120
+ "sep_parallel_degree": 1,
121
+ "sep_token_id": null,
122
+ "sequence_parallel": false,
123
+ "spatial_merge_size": 2,
124
+ "spatial_patch_size": 14,
125
+ "suppress_tokens": null,
126
+ "task_specific_params": null,
127
+ "temperature": 1.0,
128
+ "temporal_patch_size": 2,
129
+ "tensor_parallel_degree": 1,
130
+ "tensor_parallel_output": true,
131
+ "tensor_parallel_rank": 0,
132
+ "tie_encoder_decoder": false,
133
+ "tie_word_embeddings": true,
134
+ "tokenizer_class": null,
135
+ "top_k": 50,
136
+ "top_p": 1.0,
137
+ "typical_p": 1.0,
138
+ "use_cache": false,
139
+ "use_flash_attention": false,
140
+ "use_fused_dropout_add": false,
141
+ "use_fused_linear": false,
142
+ "use_fused_rms_norm": false,
143
+ "use_fused_rope": false,
144
+ "virtual_pp_degree": 1
145
+ },
146
+ "vision_end_token_id": 151653,
147
+ "vision_start_token_id": 151652,
148
+ "vision_token_id": 151654,
149
+ "vocab_size": 152064
150
+ }