bobmilk commited on
Commit
1750ac4
·
1 Parent(s): a50363c

add ChemDFM-X model files

Browse files
README.md CHANGED
@@ -1,3 +1,4 @@
1
  ---
2
  license: agpl-3.0
3
  ---
 
 
1
  ---
2
  license: agpl-3.0
3
  ---
4
+ Processing...
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<|mm_end|>": 39410,
3
+ "<|mm_start|>": 39409,
4
+ "<|mm_tokens|>": 39411,
5
+ "[PAD]": 39408
6
+ }
config.json ADDED
@@ -0,0 +1,134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/public/home/coop_1/Chen_Dir/DeepSpeed-Chat/training/step1_supervised_finetuning/output/encoder-mm-merge/reorder_init",
3
+ "architectures": [
4
+ "ChemDFMMMForPreTraining"
5
+ ],
6
+ "attention_bias": false,
7
+ "bos_token_id": 1,
8
+ "end_token_id": 2,
9
+ "eos_token_id": 2,
10
+ "figure_config": {
11
+ "_name_or_path": "",
12
+ "add_cross_attention": false,
13
+ "architectures": null,
14
+ "attention_dropout": 0.0,
15
+ "bad_words_ids": null,
16
+ "begin_suppress_tokens": null,
17
+ "bos_token_id": null,
18
+ "chunk_size_feed_forward": 0,
19
+ "cross_attention_hidden_size": null,
20
+ "decoder_start_token_id": null,
21
+ "diversity_penalty": 0.0,
22
+ "do_sample": false,
23
+ "dropout": 0.0,
24
+ "early_stopping": false,
25
+ "encoder_no_repeat_ngram_size": 0,
26
+ "eos_token_id": null,
27
+ "exponential_decay_length_penalty": null,
28
+ "finetuning_task": null,
29
+ "forced_bos_token_id": null,
30
+ "forced_eos_token_id": null,
31
+ "hidden_act": "quick_gelu",
32
+ "hidden_size": 1024,
33
+ "id2label": {
34
+ "0": "LABEL_0",
35
+ "1": "LABEL_1"
36
+ },
37
+ "image_size": 336,
38
+ "initializer_factor": 1.0,
39
+ "initializer_range": 0.02,
40
+ "intermediate_size": 4096,
41
+ "is_decoder": false,
42
+ "is_encoder_decoder": false,
43
+ "label2id": {
44
+ "LABEL_0": 0,
45
+ "LABEL_1": 1
46
+ },
47
+ "layer_norm_eps": 1e-05,
48
+ "length_penalty": 1.0,
49
+ "max_length": 20,
50
+ "min_length": 0,
51
+ "model_type": "clip_vision_model",
52
+ "no_repeat_ngram_size": 0,
53
+ "num_attention_heads": 16,
54
+ "num_beam_groups": 1,
55
+ "num_beams": 1,
56
+ "num_channels": 3,
57
+ "num_hidden_layers": 24,
58
+ "num_return_sequences": 1,
59
+ "output_attentions": false,
60
+ "output_hidden_states": false,
61
+ "output_scores": false,
62
+ "pad_token_id": null,
63
+ "patch_size": 14,
64
+ "prefix": null,
65
+ "problem_type": null,
66
+ "projection_dim": 768,
67
+ "pruned_heads": {},
68
+ "remove_invalid_values": false,
69
+ "repetition_penalty": 1.0,
70
+ "return_dict": true,
71
+ "return_dict_in_generate": false,
72
+ "sep_token_id": null,
73
+ "suppress_tokens": null,
74
+ "task_specific_params": null,
75
+ "temperature": 1.0,
76
+ "tf_legacy_loss": false,
77
+ "tie_encoder_decoder": false,
78
+ "tie_word_embeddings": true,
79
+ "tokenizer_class": null,
80
+ "top_k": 50,
81
+ "top_p": 1.0,
82
+ "torch_dtype": null,
83
+ "torchscript": false,
84
+ "typical_p": 1.0,
85
+ "use_bfloat16": false
86
+ },
87
+ "hidden_act": "silu",
88
+ "hidden_size": 5120,
89
+ "initializer_range": 0.02,
90
+ "intermediate_size": 13824,
91
+ "max_position_embeddings": 2048,
92
+ "modality": {
93
+ "mol_geometry_3d": {
94
+ "hidden_size": 5120,
95
+ "mm_hidden_size": 512,
96
+ "mm_projector_type": "mlp2x_gelu"
97
+ },
98
+ "mol_graph_2d": {
99
+ "hidden_size": 5120,
100
+ "mm_hidden_size": 300,
101
+ "mm_projector_type": "mlp2x_gelu"
102
+ },
103
+ "mol_figure_2d": {
104
+ "conv_shape": "1x8",
105
+ "hidden_size": 5120,
106
+ "mm_hidden_size": 1024,
107
+ "mm_projector_type": "mlp2x_gelu"
108
+ },
109
+ "mol_ms": {
110
+ "hidden_size": 5120,
111
+ "mm_hidden_size": 512,
112
+ "mm_projector_type": "mlp2x_gelu"
113
+ },
114
+ "mol_ir": {
115
+ "hidden_size": 5120,
116
+ "mm_hidden_size": 768,
117
+ "mm_projector_type": "mlp2x_gelu"
118
+ }
119
+ },
120
+ "model_type": "llama",
121
+ "num_attention_heads": 40,
122
+ "num_hidden_layers": 40,
123
+ "num_key_value_heads": 40,
124
+ "pad_token_id": 2,
125
+ "pretraining_tp": 1,
126
+ "rms_norm_eps": 1e-06,
127
+ "rope_scaling": null,
128
+ "rope_theta": 10000,
129
+ "tie_word_embeddings": false,
130
+ "torch_dtype": "float16",
131
+ "transformers_version": "4.35.0",
132
+ "use_cache": true,
133
+ "vocab_size": 39416
134
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 2,
6
+ "transformers_version": "4.35.0"
7
+ }
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61a67cc1d118fda4fb09c149972917728cc4a7ca75554863e40a9a145d1c91ed
3
+ size 4949347744
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:217661e5ba20cb717f9e54b42f402b35edabfa460da49d8df44b0705bff75b0f
3
+ size 4970422160
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99ec56f0c422a852215e28aa40bf67fe5a3f56d7729c929367a5263f6973fa42
3
+ size 4933701432
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32a54918e7126427758913905d8ad21bb5b5d65adb5d922c2de3de27e0d96a09
3
+ size 4933722144
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4f48fadc349845a2cc0c84652c2b780d2e35528350f334e0aff060c5d3594ab
3
+ size 4933722136
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e2691060ce5c12caa2e8ecd6135a8cf50f469ac098a56f0a5077bdb2b5cf194
3
+ size 2858669294
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|mm_start|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|mm_end|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<|mm_tokens|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ ],
25
+ "bos_token": {
26
+ "content": "<s>",
27
+ "lstrip": false,
28
+ "normalized": true,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "eos_token": {
33
+ "content": "</s>",
34
+ "lstrip": false,
35
+ "normalized": true,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ },
39
+ "pad_token": {
40
+ "content": "[PAD]",
41
+ "lstrip": false,
42
+ "normalized": false,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "unk_token": {
47
+ "content": "<unk>",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ }
53
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e605041f0df5267b062935be72043a8c8c30d6482aeaf8fe6e067cf4806267f
3
+ size 603435
tokenizer_config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "39408": {
30
+ "content": "[PAD]",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "39409": {
38
+ "content": "<|mm_start|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "39410": {
46
+ "content": "<|mm_end|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "39411": {
54
+ "content": "<|mm_tokens|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ }
61
+ },
62
+ "additional_special_tokens": [
63
+ "<|mm_start|>",
64
+ "<|mm_end|>",
65
+ "<|mm_tokens|>"
66
+ ],
67
+ "bos_token": "<s>",
68
+ "clean_up_tokenization_spaces": false,
69
+ "eos_token": "</s>",
70
+ "legacy": true,
71
+ "model_max_length": 1000000000000000019884624838656,
72
+ "pad_token": "[PAD]",
73
+ "sp_model_kwargs": {},
74
+ "spaces_between_special_tokens": false,
75
+ "tokenizer_class": "LlamaTokenizer",
76
+ "unk_token": "<unk>",
77
+ "use_default_system_prompt": false,
78
+ "use_fast": true
79
+ }