alexhafnerd
commited on
Commit
•
79149bb
0
Parent(s):
Initial commit
Browse files- .gitattributes +6 -0
- added_tokens.json +10 -0
- clip_vision_embedding.bin +3 -0
- config.json +88 -0
- dream_embedding.bin +3 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +39 -0
- stable_diffusion_head.bin +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +116 -0
.gitattributes
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
clip_vision_embedding.bin filter=lfs diff=lfs merge=lfs -text
|
2 |
+
dream_embedding.bin filter=lfs diff=lfs merge=lfs -text
|
3 |
+
pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
stable_diffusion_head.bin filter=lfs diff=lfs merge=lfs -text
|
5 |
+
tokenizer.model filter=lfs diff=lfs merge=lfs -text
|
6 |
+
pytorch_model_back.bin filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<dream>": 32007,
|
3 |
+
"<dream_end>": 32002,
|
4 |
+
"<dream_start>": 32003,
|
5 |
+
"<im_end>": 32005,
|
6 |
+
"<im_patch>": 32004,
|
7 |
+
"<im_start>": 32001,
|
8 |
+
"<image>": 32006,
|
9 |
+
"[PAD]": 32000
|
10 |
+
}
|
clip_vision_embedding.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9278c079148131df640e45f35d3dc9c26d09443c2eb5b45b4becedb0042974bf
|
3 |
+
size 614896585
|
config.json
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"DreamLLMForCausalMLM"
|
4 |
+
],
|
5 |
+
"attention_bias": false,
|
6 |
+
"bos_token_id": 0,
|
7 |
+
"eos_token_id": 1,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 4096,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 11008,
|
12 |
+
"log_attentions": false,
|
13 |
+
"log_hidden_states": false,
|
14 |
+
"loss_scale_schedule": "none",
|
15 |
+
"loss_weight_lm": 1.0,
|
16 |
+
"loss_weight_vm": 10.0,
|
17 |
+
"max_position_embeddings": 2048,
|
18 |
+
"max_sequence_length": 2048,
|
19 |
+
"model_type": "dreamllm",
|
20 |
+
"num_attention_heads": 32,
|
21 |
+
"num_hidden_layers": 32,
|
22 |
+
"num_key_value_heads": 32,
|
23 |
+
"pad_token_id": -1,
|
24 |
+
"plugins_init_kwargs": {
|
25 |
+
"clip_vision_embedding": {
|
26 |
+
"_target_": "omni.models.dreamllm.modeling_plugins.CLIPVisionEmbedding",
|
27 |
+
"clip_vision_model_name_or_path": "openai/clip-vit-large-patch14",
|
28 |
+
"embed_hidden_size": 4096,
|
29 |
+
"freeze_clip_vision_model": true,
|
30 |
+
"freeze_embedding_layers": true,
|
31 |
+
"freeze_projector": false,
|
32 |
+
"local_files_only": true,
|
33 |
+
"pretrained_model_name_or_path": "none",
|
34 |
+
"projector_depth": 1,
|
35 |
+
"projector_type": "linear",
|
36 |
+
"select_layer": -2,
|
37 |
+
"use_additional_post_layernorm": false
|
38 |
+
},
|
39 |
+
"dream_embedding": {
|
40 |
+
"_target_": "omni.models.dreamllm.modeling_plugins.DreamEmbedding",
|
41 |
+
"embed_hidden_size": 4096,
|
42 |
+
"freeze_dream_queries": false,
|
43 |
+
"num_dream_queries": 64,
|
44 |
+
"pretrained_model_name_or_path": "none"
|
45 |
+
},
|
46 |
+
"stable_diffusion_head": {
|
47 |
+
"_target_": "omni.models.dreamllm.modeling_plugins.StableDiffusionHead",
|
48 |
+
"diffusion_name_or_path": "stabilityai/stable-diffusion-2-1-base",
|
49 |
+
"embed_hidden_size": 4096,
|
50 |
+
"freeze_projector": false,
|
51 |
+
"freeze_unet": true,
|
52 |
+
"freeze_vae": true,
|
53 |
+
"local_files_only": true,
|
54 |
+
"pretrained_model_name_or_path": "none",
|
55 |
+
"projector_depth": 1,
|
56 |
+
"projector_type": "linear"
|
57 |
+
}
|
58 |
+
},
|
59 |
+
"plugins_type": {
|
60 |
+
"clip_vision_embedding": "embedding",
|
61 |
+
"dream_embedding": "embedding",
|
62 |
+
"stable_diffusion_head": "head"
|
63 |
+
},
|
64 |
+
"pretraining_tp": 1,
|
65 |
+
"rms_norm_eps": 1e-06,
|
66 |
+
"rope_scaling": null,
|
67 |
+
"rope_theta": 10000.0,
|
68 |
+
"special_tokens2ids_dict": {
|
69 |
+
"</s>": 2,
|
70 |
+
"<s>": 1,
|
71 |
+
"<unk>": 0,
|
72 |
+
"[PAD]": 32000,
|
73 |
+
"additional_special_tokens": {
|
74 |
+
"<dream>": 32007,
|
75 |
+
"<dream_end>": 32002,
|
76 |
+
"<dream_start>": 32003,
|
77 |
+
"<im_end>": 32005,
|
78 |
+
"<im_patch>": 32004,
|
79 |
+
"<im_start>": 32001,
|
80 |
+
"<image>": 32006
|
81 |
+
}
|
82 |
+
},
|
83 |
+
"tie_word_embeddings": false,
|
84 |
+
"torch_dtype": "bfloat16",
|
85 |
+
"transformers_version": "4.35.2",
|
86 |
+
"use_cache": true,
|
87 |
+
"vocab_size": 32008
|
88 |
+
}
|
dream_embedding.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33f3d3a9253888ac871ad48114c0605c72916db997fec6cb3a5df0f2b29d2fe7
|
3 |
+
size 525123
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.35.2"
|
7 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d03418a0b76c463790c1406381c1ab309a8d0392a20b58bc5d33435b789fc9b6
|
3 |
+
size 13477250085
|
special_tokens_map.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<im_start>",
|
4 |
+
"<dream_end>",
|
5 |
+
"<dream_start>",
|
6 |
+
"<im_patch>",
|
7 |
+
"<im_end>",
|
8 |
+
"<image>",
|
9 |
+
"<dream>"
|
10 |
+
],
|
11 |
+
"bos_token": {
|
12 |
+
"content": "<s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false
|
17 |
+
},
|
18 |
+
"eos_token": {
|
19 |
+
"content": "</s>",
|
20 |
+
"lstrip": false,
|
21 |
+
"normalized": false,
|
22 |
+
"rstrip": false,
|
23 |
+
"single_word": false
|
24 |
+
},
|
25 |
+
"pad_token": {
|
26 |
+
"content": "[PAD]",
|
27 |
+
"lstrip": false,
|
28 |
+
"normalized": false,
|
29 |
+
"rstrip": false,
|
30 |
+
"single_word": false
|
31 |
+
},
|
32 |
+
"unk_token": {
|
33 |
+
"content": "<unk>",
|
34 |
+
"lstrip": false,
|
35 |
+
"normalized": false,
|
36 |
+
"rstrip": false,
|
37 |
+
"single_word": false
|
38 |
+
}
|
39 |
+
}
|
stable_diffusion_head.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e35ffb5440055ab8ed76e4dcf2afe3b29e78d9d7d1a2e79f1a855ce776eba822
|
3 |
+
size 1907838193
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,116 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "[PAD]",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"32001": {
|
38 |
+
"content": "<im_start>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"32002": {
|
46 |
+
"content": "<dream_end>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"32003": {
|
54 |
+
"content": "<dream_start>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"32004": {
|
62 |
+
"content": "<im_patch>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"32005": {
|
70 |
+
"content": "<im_end>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"32006": {
|
78 |
+
"content": "<image>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"32007": {
|
86 |
+
"content": "<dream>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
}
|
93 |
+
},
|
94 |
+
"additional_special_tokens": [
|
95 |
+
"<im_start>",
|
96 |
+
"<dream_end>",
|
97 |
+
"<dream_start>",
|
98 |
+
"<im_patch>",
|
99 |
+
"<im_end>",
|
100 |
+
"<image>",
|
101 |
+
"<dream>"
|
102 |
+
],
|
103 |
+
"bos_token": "<s>",
|
104 |
+
"clean_up_tokenization_spaces": false,
|
105 |
+
"eos_token": "</s>",
|
106 |
+
"legacy": true,
|
107 |
+
"model_max_length": 2048,
|
108 |
+
"pad_token": "[PAD]",
|
109 |
+
"padding_side": "right",
|
110 |
+
"sp_model_kwargs": {},
|
111 |
+
"spaces_between_special_tokens": false,
|
112 |
+
"tokenizer_class": "LlamaTokenizer",
|
113 |
+
"unk_token": "<unk>",
|
114 |
+
"use_default_system_prompt": false,
|
115 |
+
"use_fast": true
|
116 |
+
}
|