Hugging Face's logo

U4R
/
GeoX

Safetensors
Model card Files Community
renqiux0302 commited on
Commit
c38c2e5
·
verified ·
1 Parent(s): 03e0285

Delete geox_unigeo

Browse files
Files changed (10) hide show
  1. geox_unigeo/.DS_Store +0 -0
  2. geox_unigeo/config.json +0 -45
  3. geox_unigeo/generation_config.json +0 -7
  4. geox_unigeo/model-00001-of-00003.safetensors +0 -3
  5. geox_unigeo/model-00002-of-00003.safetensors +0 -3
  6. geox_unigeo/model-00003-of-00003.safetensors +0 -3
  7. geox_unigeo/model.safetensors.index.json +0 -740
  8. geox_unigeo/special_tokens_map.json +0 -24
  9. geox_unigeo/tokenizer.model +0 -3
  10. geox_unigeo/tokenizer_config.json +0 -43
geox_unigeo/.DS_Store DELETED
Binary file (6.15 kB)
 
geox_unigeo/config.json DELETED
@@ -1,45 +0,0 @@
1
- {
2
- "_name_or_path": "GeoX-UniGeo",
3
- "architectures": [
4
- "GeoXLlamaForCausalLM"
5
- ],
6
- "attention_bias": false,
7
- "attention_dropout": 0.0,
8
- "bos_token_id": 1,
9
- "eos_token_id": 2,
10
- "freeze_mm_mlp_adapter": false,
11
- "hidden_act": "silu",
12
- "hidden_size": 4096,
13
- "image_aspect_ratio": "square",
14
- "initializer_range": 0.02,
15
- "intermediate_size": 11008,
16
- "max_position_embeddings": 4096,
17
- "mm_hidden_size": 768,
18
- "mm_patch_merge_type": "flat",
19
- "mm_projector_lr": null,
20
- "mm_projector_type": "linear",
21
- "mm_use_im_patch_token": false,
22
- "mm_use_im_start_end": false,
23
- "mm_use_sep_token": false,
24
- "mm_vision_select_feature": "patch",
25
- "mm_vision_select_layer": -1,
26
- "mm_vision_tower": "Geo-ViT.pth",
27
- "model_type": "geox",
28
- "num_attention_heads": 32,
29
- "num_hidden_layers": 32,
30
- "num_key_value_heads": 32,
31
- "pad_token_id": 0,
32
- "pretraining_tp": 1,
33
- "rms_norm_eps": 1e-05,
34
- "rope_scaling": null,
35
- "rope_theta": 10000.0,
36
- "tie_word_embeddings": false,
37
- "tokenizer_model_max_length": 2048,
38
- "tokenizer_padding_side": "right",
39
- "torch_dtype": "bfloat16",
40
- "transformers_version": "4.37.2",
41
- "tune_mm_mlp_adapter": false,
42
- "use_cache": true,
43
- "use_mm_proj": true,
44
- "vocab_size": 32016
45
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
geox_unigeo/generation_config.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "eos_token_id": 2,
5
- "pad_token_id": 0,
6
- "transformers_version": "4.37.2"
7
- }
 
 
 
 
 
 
 
 
geox_unigeo/model-00001-of-00003.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:693ed444083f51f7d2d135b8dc67693a54c2dd35712fcccd85a5bc70db2e32a1
3
- size 4939116424
 
 
 
 
geox_unigeo/model-00002-of-00003.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:79fbe5fca6a56ecc5aa17e2254a7ae243ae3f4dd5dc84b99b65dab333db2dba5
3
- size 4947390880
 
 
 
 
geox_unigeo/model-00003-of-00003.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c67aa47007d7ec1ecd23808289bb5eeacfdf48f8be2b3dccba8b111370a1322
3
- size 3990319158
 
 
 
 
geox_unigeo/model.safetensors.index.json DELETED
@@ -1,740 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 13876733454
4
- },
5
- "weight_map": {
6
- "lm_head.weight": "model-00003-of-00003.safetensors",
7
- "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
- "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
- "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
- "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
27
- "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
28
- "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
- "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
- "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
31
- "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
- "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
- "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
- "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
- "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
- "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
- "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
38
- "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
- "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
- "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
41
- "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
42
- "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
43
- "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
44
- "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
- "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
- "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
- "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
- "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
- "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
- "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
- "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
- "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
- "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
- "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
- "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
- "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
- "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
- "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
- "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
- "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
- "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
- "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
- "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
- "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
- "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
- "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
- "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
- "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
- "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
- "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
- "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
- "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
- "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
- "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
- "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
- "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
- "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
- "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
- "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
- "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
- "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
- "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
- "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
- "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
- "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
- "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
- "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
- "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
- "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
- "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
- "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
- "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
- "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
- "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
- "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
- "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
- "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
- "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
- "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
- "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
- "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
- "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
- "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
- "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
- "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
- "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
- "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
- "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
- "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
- "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
- "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
- "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
- "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
- "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
- "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
- "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
- "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
- "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
- "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
- "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
- "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
- "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
- "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
- "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
- "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
- "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
- "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
- "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
- "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
- "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
- "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
- "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
- "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
- "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
- "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
144
- "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
145
- "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
146
- "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
147
- "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
148
- "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
- "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
- "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
- "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
- "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
- "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
- "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
155
- "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
156
- "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
- "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
158
- "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
159
- "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
160
- "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
161
- "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
- "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
- "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
- "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
- "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
- "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
- "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
- "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
- "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
- "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
171
- "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
172
- "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
173
- "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
174
- "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
175
- "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
176
- "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
177
- "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
178
- "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
179
- "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
- "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
- "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
- "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
- "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
- "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
- "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
- "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
- "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
- "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
- "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
- "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
- "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
- "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
- "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
- "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
- "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
- "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
- "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
198
- "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
199
- "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
200
- "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
201
- "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
202
- "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
- "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
- "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
205
- "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
206
- "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
- "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
- "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
- "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
- "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
- "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
212
- "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
213
- "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
214
- "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
215
- "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
- "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
- "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
- "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
- "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
- "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
- "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
- "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
- "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
- "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
- "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
- "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
- "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
- "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
- "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
- "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
- "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
- "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
- "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
- "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
- "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
- "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
- "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
- "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
- "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
- "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
- "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
- "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
- "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
- "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
- "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
- "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
- "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
- "model.mm_projector.bias": "model-00003-of-00003.safetensors",
297
- "model.mm_projector.weight": "model-00003-of-00003.safetensors",
298
- "model.norm.weight": "model-00003-of-00003.safetensors",
299
- "model.gs_former.learnable_query": "model-00003-of-00003.safetensors",
300
- "model.gs_former.mmtransformer.embeddings.LayerNorm.bias": "model-00003-of-00003.safetensors",
301
- "model.gs_former.mmtransformer.embeddings.LayerNorm.weight": "model-00003-of-00003.safetensors",
302
- "model.gs_former.mmtransformer.embeddings.position_ids": "model-00003-of-00003.safetensors",
303
- "model.gs_former.mmtransformer.layer.0.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
304
- "model.gs_former.mmtransformer.layer.0.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
305
- "model.gs_former.mmtransformer.layer.0.attention.output.dense.bias": "model-00003-of-00003.safetensors",
306
- "model.gs_former.mmtransformer.layer.0.attention.output.dense.weight": "model-00003-of-00003.safetensors",
307
- "model.gs_former.mmtransformer.layer.0.attention.self.key.bias": "model-00003-of-00003.safetensors",
308
- "model.gs_former.mmtransformer.layer.0.attention.self.key.weight": "model-00003-of-00003.safetensors",
309
- "model.gs_former.mmtransformer.layer.0.attention.self.query.bias": "model-00003-of-00003.safetensors",
310
- "model.gs_former.mmtransformer.layer.0.attention.self.query.weight": "model-00003-of-00003.safetensors",
311
- "model.gs_former.mmtransformer.layer.0.attention.self.value.bias": "model-00003-of-00003.safetensors",
312
- "model.gs_former.mmtransformer.layer.0.attention.self.value.weight": "model-00003-of-00003.safetensors",
313
- "model.gs_former.mmtransformer.layer.0.crossattention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
314
- "model.gs_former.mmtransformer.layer.0.crossattention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
315
- "model.gs_former.mmtransformer.layer.0.crossattention.output.dense.bias": "model-00003-of-00003.safetensors",
316
- "model.gs_former.mmtransformer.layer.0.crossattention.output.dense.weight": "model-00003-of-00003.safetensors",
317
- "model.gs_former.mmtransformer.layer.0.crossattention.self.key.bias": "model-00003-of-00003.safetensors",
318
- "model.gs_former.mmtransformer.layer.0.crossattention.self.key.weight": "model-00003-of-00003.safetensors",
319
- "model.gs_former.mmtransformer.layer.0.crossattention.self.query.bias": "model-00003-of-00003.safetensors",
320
- "model.gs_former.mmtransformer.layer.0.crossattention.self.query.weight": "model-00003-of-00003.safetensors",
321
- "model.gs_former.mmtransformer.layer.0.crossattention.self.value.bias": "model-00003-of-00003.safetensors",
322
- "model.gs_former.mmtransformer.layer.0.crossattention.self.value.weight": "model-00003-of-00003.safetensors",
323
- "model.gs_former.mmtransformer.layer.0.intermediate_query.dense.bias": "model-00003-of-00003.safetensors",
324
- "model.gs_former.mmtransformer.layer.0.intermediate_query.dense.weight": "model-00003-of-00003.safetensors",
325
- "model.gs_former.mmtransformer.layer.0.output_query.LayerNorm.bias": "model-00003-of-00003.safetensors",
326
- "model.gs_former.mmtransformer.layer.0.output_query.LayerNorm.weight": "model-00003-of-00003.safetensors",
327
- "model.gs_former.mmtransformer.layer.0.output_query.dense.bias": "model-00003-of-00003.safetensors",
328
- "model.gs_former.mmtransformer.layer.0.output_query.dense.weight": "model-00003-of-00003.safetensors",
329
- "model.gs_former.mmtransformer.layer.1.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
330
- "model.gs_former.mmtransformer.layer.1.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
331
- "model.gs_former.mmtransformer.layer.1.attention.output.dense.bias": "model-00003-of-00003.safetensors",
332
- "model.gs_former.mmtransformer.layer.1.attention.output.dense.weight": "model-00003-of-00003.safetensors",
333
- "model.gs_former.mmtransformer.layer.1.attention.self.key.bias": "model-00003-of-00003.safetensors",
334
- "model.gs_former.mmtransformer.layer.1.attention.self.key.weight": "model-00003-of-00003.safetensors",
335
- "model.gs_former.mmtransformer.layer.1.attention.self.query.bias": "model-00003-of-00003.safetensors",
336
- "model.gs_former.mmtransformer.layer.1.attention.self.query.weight": "model-00003-of-00003.safetensors",
337
- "model.gs_former.mmtransformer.layer.1.attention.self.value.bias": "model-00003-of-00003.safetensors",
338
- "model.gs_former.mmtransformer.layer.1.attention.self.value.weight": "model-00003-of-00003.safetensors",
339
- "model.gs_former.mmtransformer.layer.1.intermediate_query.dense.bias": "model-00003-of-00003.safetensors",
340
- "model.gs_former.mmtransformer.layer.1.intermediate_query.dense.weight": "model-00003-of-00003.safetensors",
341
- "model.gs_former.mmtransformer.layer.1.output_query.LayerNorm.bias": "model-00003-of-00003.safetensors",
342
- "model.gs_former.mmtransformer.layer.1.output_query.LayerNorm.weight": "model-00003-of-00003.safetensors",
343
- "model.gs_former.mmtransformer.layer.1.output_query.dense.bias": "model-00003-of-00003.safetensors",
344
- "model.gs_former.mmtransformer.layer.1.output_query.dense.weight": "model-00003-of-00003.safetensors",
345
- "model.gs_former.mmtransformer.layer.10.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
346
- "model.gs_former.mmtransformer.layer.10.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
347
- "model.gs_former.mmtransformer.layer.10.attention.output.dense.bias": "model-00003-of-00003.safetensors",
348
- "model.gs_former.mmtransformer.layer.10.attention.output.dense.weight": "model-00003-of-00003.safetensors",
349
- "model.gs_former.mmtransformer.layer.10.attention.self.key.bias": "model-00003-of-00003.safetensors",
350
- "model.gs_former.mmtransformer.layer.10.attention.self.key.weight": "model-00003-of-00003.safetensors",
351
- "model.gs_former.mmtransformer.layer.10.attention.self.query.bias": "model-00003-of-00003.safetensors",
352
- "model.gs_former.mmtransformer.layer.10.attention.self.query.weight": "model-00003-of-00003.safetensors",
353
- "model.gs_former.mmtransformer.layer.10.attention.self.value.bias": "model-00003-of-00003.safetensors",
354
- "model.gs_former.mmtransformer.layer.10.attention.self.value.weight": "model-00003-of-00003.safetensors",
355
- "model.gs_former.mmtransformer.layer.10.crossattention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
356
- "model.gs_former.mmtransformer.layer.10.crossattention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
357
- "model.gs_former.mmtransformer.layer.10.crossattention.output.dense.bias": "model-00003-of-00003.safetensors",
358
- "model.gs_former.mmtransformer.layer.10.crossattention.output.dense.weight": "model-00003-of-00003.safetensors",
359
- "model.gs_former.mmtransformer.layer.10.crossattention.self.key.bias": "model-00003-of-00003.safetensors",
360
- "model.gs_former.mmtransformer.layer.10.crossattention.self.key.weight": "model-00003-of-00003.safetensors",
361
- "model.gs_former.mmtransformer.layer.10.crossattention.self.query.bias": "model-00003-of-00003.safetensors",
362
- "model.gs_former.mmtransformer.layer.10.crossattention.self.query.weight": "model-00003-of-00003.safetensors",
363
- "model.gs_former.mmtransformer.layer.10.crossattention.self.value.bias": "model-00003-of-00003.safetensors",
364
- "model.gs_former.mmtransformer.layer.10.crossattention.self.value.weight": "model-00003-of-00003.safetensors",
365
- "model.gs_former.mmtransformer.layer.10.intermediate_query.dense.bias": "model-00003-of-00003.safetensors",
366
- "model.gs_former.mmtransformer.layer.10.intermediate_query.dense.weight": "model-00003-of-00003.safetensors",
367
- "model.gs_former.mmtransformer.layer.10.output_query.LayerNorm.bias": "model-00003-of-00003.safetensors",
368
- "model.gs_former.mmtransformer.layer.10.output_query.LayerNorm.weight": "model-00003-of-00003.safetensors",
369
- "model.gs_former.mmtransformer.layer.10.output_query.dense.bias": "model-00003-of-00003.safetensors",
370
- "model.gs_former.mmtransformer.layer.10.output_query.dense.weight": "model-00003-of-00003.safetensors",
371
- "model.gs_former.mmtransformer.layer.11.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
372
- "model.gs_former.mmtransformer.layer.11.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
373
- "model.gs_former.mmtransformer.layer.11.attention.output.dense.bias": "model-00003-of-00003.safetensors",
374
- "model.gs_former.mmtransformer.layer.11.attention.output.dense.weight": "model-00003-of-00003.safetensors",
375
- "model.gs_former.mmtransformer.layer.11.attention.self.key.bias": "model-00003-of-00003.safetensors",
376
- "model.gs_former.mmtransformer.layer.11.attention.self.key.weight": "model-00003-of-00003.safetensors",
377
- "model.gs_former.mmtransformer.layer.11.attention.self.query.bias": "model-00003-of-00003.safetensors",
378
- "model.gs_former.mmtransformer.layer.11.attention.self.query.weight": "model-00003-of-00003.safetensors",
379
- "model.gs_former.mmtransformer.layer.11.attention.self.value.bias": "model-00003-of-00003.safetensors",
380
- "model.gs_former.mmtransformer.layer.11.attention.self.value.weight": "model-00003-of-00003.safetensors",
381
- "model.gs_former.mmtransformer.layer.11.intermediate_query.dense.bias": "model-00003-of-00003.safetensors",
382
- "model.gs_former.mmtransformer.layer.11.intermediate_query.dense.weight": "model-00003-of-00003.safetensors",
383
- "model.gs_former.mmtransformer.layer.11.output_query.LayerNorm.bias": "model-00003-of-00003.safetensors",
384
- "model.gs_former.mmtransformer.layer.11.output_query.LayerNorm.weight": "model-00003-of-00003.safetensors",
385
- "model.gs_former.mmtransformer.layer.11.output_query.dense.bias": "model-00003-of-00003.safetensors",
386
- "model.gs_former.mmtransformer.layer.11.output_query.dense.weight": "model-00003-of-00003.safetensors",
387
- "model.gs_former.mmtransformer.layer.2.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
388
- "model.gs_former.mmtransformer.layer.2.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
389
- "model.gs_former.mmtransformer.layer.2.attention.output.dense.bias": "model-00003-of-00003.safetensors",
390
- "model.gs_former.mmtransformer.layer.2.attention.output.dense.weight": "model-00003-of-00003.safetensors",
391
- "model.gs_former.mmtransformer.layer.2.attention.self.key.bias": "model-00003-of-00003.safetensors",
392
- "model.gs_former.mmtransformer.layer.2.attention.self.key.weight": "model-00003-of-00003.safetensors",
393
- "model.gs_former.mmtransformer.layer.2.attention.self.query.bias": "model-00003-of-00003.safetensors",
394
- "model.gs_former.mmtransformer.layer.2.attention.self.query.weight": "model-00003-of-00003.safetensors",
395
- "model.gs_former.mmtransformer.layer.2.attention.self.value.bias": "model-00003-of-00003.safetensors",
396
- "model.gs_former.mmtransformer.layer.2.attention.self.value.weight": "model-00003-of-00003.safetensors",
397
- "model.gs_former.mmtransformer.layer.2.crossattention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
398
- "model.gs_former.mmtransformer.layer.2.crossattention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
399
- "model.gs_former.mmtransformer.layer.2.crossattention.output.dense.bias": "model-00003-of-00003.safetensors",
400
- "model.gs_former.mmtransformer.layer.2.crossattention.output.dense.weight": "model-00003-of-00003.safetensors",
401
- "model.gs_former.mmtransformer.layer.2.crossattention.self.key.bias": "model-00003-of-00003.safetensors",
402
- "model.gs_former.mmtransformer.layer.2.crossattention.self.key.weight": "model-00003-of-00003.safetensors",
403
- "model.gs_former.mmtransformer.layer.2.crossattention.self.query.bias": "model-00003-of-00003.safetensors",
404
- "model.gs_former.mmtransformer.layer.2.crossattention.self.query.weight": "model-00003-of-00003.safetensors",
405
- "model.gs_former.mmtransformer.layer.2.crossattention.self.value.bias": "model-00003-of-00003.safetensors",
406
- "model.gs_former.mmtransformer.layer.2.crossattention.self.value.weight": "model-00003-of-00003.safetensors",
407
- "model.gs_former.mmtransformer.layer.2.intermediate_query.dense.bias": "model-00003-of-00003.safetensors",
408
- "model.gs_former.mmtransformer.layer.2.intermediate_query.dense.weight": "model-00003-of-00003.safetensors",
409
- "model.gs_former.mmtransformer.layer.2.output_query.LayerNorm.bias": "model-00003-of-00003.safetensors",
410
- "model.gs_former.mmtransformer.layer.2.output_query.LayerNorm.weight": "model-00003-of-00003.safetensors",
411
- "model.gs_former.mmtransformer.layer.2.output_query.dense.bias": "model-00003-of-00003.safetensors",
412
- "model.gs_former.mmtransformer.layer.2.output_query.dense.weight": "model-00003-of-00003.safetensors",
413
- "model.gs_former.mmtransformer.layer.3.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
414
- "model.gs_former.mmtransformer.layer.3.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
415
- "model.gs_former.mmtransformer.layer.3.attention.output.dense.bias": "model-00003-of-00003.safetensors",
416
- "model.gs_former.mmtransformer.layer.3.attention.output.dense.weight": "model-00003-of-00003.safetensors",
417
- "model.gs_former.mmtransformer.layer.3.attention.self.key.bias": "model-00003-of-00003.safetensors",
418
- "model.gs_former.mmtransformer.layer.3.attention.self.key.weight": "model-00003-of-00003.safetensors",
419
- "model.gs_former.mmtransformer.layer.3.attention.self.query.bias": "model-00003-of-00003.safetensors",
420
- "model.gs_former.mmtransformer.layer.3.attention.self.query.weight": "model-00003-of-00003.safetensors",
421
- "model.gs_former.mmtransformer.layer.3.attention.self.value.bias": "model-00003-of-00003.safetensors",
422
- "model.gs_former.mmtransformer.layer.3.attention.self.value.weight": "model-00003-of-00003.safetensors",
423
- "model.gs_former.mmtransformer.layer.3.intermediate_query.dense.bias": "model-00003-of-00003.safetensors",
424
- "model.gs_former.mmtransformer.layer.3.intermediate_query.dense.weight": "model-00003-of-00003.safetensors",
425
- "model.gs_former.mmtransformer.layer.3.output_query.LayerNorm.bias": "model-00003-of-00003.safetensors",
426
- "model.gs_former.mmtransformer.layer.3.output_query.LayerNorm.weight": "model-00003-of-00003.safetensors",
427
- "model.gs_former.mmtransformer.layer.3.output_query.dense.bias": "model-00003-of-00003.safetensors",
428
- "model.gs_former.mmtransformer.layer.3.output_query.dense.weight": "model-00003-of-00003.safetensors",
429
- "model.gs_former.mmtransformer.layer.4.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
430
- "model.gs_former.mmtransformer.layer.4.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
431
- "model.gs_former.mmtransformer.layer.4.attention.output.dense.bias": "model-00003-of-00003.safetensors",
432
- "model.gs_former.mmtransformer.layer.4.attention.output.dense.weight": "model-00003-of-00003.safetensors",
433
- "model.gs_former.mmtransformer.layer.4.attention.self.key.bias": "model-00003-of-00003.safetensors",
434
- "model.gs_former.mmtransformer.layer.4.attention.self.key.weight": "model-00003-of-00003.safetensors",
435
- "model.gs_former.mmtransformer.layer.4.attention.self.query.bias": "model-00003-of-00003.safetensors",
436
- "model.gs_former.mmtransformer.layer.4.attention.self.query.weight": "model-00003-of-00003.safetensors",
437
- "model.gs_former.mmtransformer.layer.4.attention.self.value.bias": "model-00003-of-00003.safetensors",
438
- "model.gs_former.mmtransformer.layer.4.attention.self.value.weight": "model-00003-of-00003.safetensors",
439
- "model.gs_former.mmtransformer.layer.4.crossattention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
440
- "model.gs_former.mmtransformer.layer.4.crossattention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
441
- "model.gs_former.mmtransformer.layer.4.crossattention.output.dense.bias": "model-00003-of-00003.safetensors",
442
- "model.gs_former.mmtransformer.layer.4.crossattention.output.dense.weight": "model-00003-of-00003.safetensors",
443
- "model.gs_former.mmtransformer.layer.4.crossattention.self.key.bias": "model-00003-of-00003.safetensors",
444
- "model.gs_former.mmtransformer.layer.4.crossattention.self.key.weight": "model-00003-of-00003.safetensors",
445
- "model.gs_former.mmtransformer.layer.4.crossattention.self.query.bias": "model-00003-of-00003.safetensors",
446
- "model.gs_former.mmtransformer.layer.4.crossattention.self.query.weight": "model-00003-of-00003.safetensors",
447
- "model.gs_former.mmtransformer.layer.4.crossattention.self.value.bias": "model-00003-of-00003.safetensors",
448
- "model.gs_former.mmtransformer.layer.4.crossattention.self.value.weight": "model-00003-of-00003.safetensors",
449
- "model.gs_former.mmtransformer.layer.4.intermediate_query.dense.bias": "model-00003-of-00003.safetensors",
450
- "model.gs_former.mmtransformer.layer.4.intermediate_query.dense.weight": "model-00003-of-00003.safetensors",
451
- "model.gs_former.mmtransformer.layer.4.output_query.LayerNorm.bias": "model-00003-of-00003.safetensors",
452
- "model.gs_former.mmtransformer.layer.4.output_query.LayerNorm.weight": "model-00003-of-00003.safetensors",
453
- "model.gs_former.mmtransformer.layer.4.output_query.dense.bias": "model-00003-of-00003.safetensors",
454
- "model.gs_former.mmtransformer.layer.4.output_query.dense.weight": "model-00003-of-00003.safetensors",
455
- "model.gs_former.mmtransformer.layer.5.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
456
- "model.gs_former.mmtransformer.layer.5.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
457
- "model.gs_former.mmtransformer.layer.5.attention.output.dense.bias": "model-00003-of-00003.safetensors",
458
- "model.gs_former.mmtransformer.layer.5.attention.output.dense.weight": "model-00003-of-00003.safetensors",
459
- "model.gs_former.mmtransformer.layer.5.attention.self.key.bias": "model-00003-of-00003.safetensors",
460
- "model.gs_former.mmtransformer.layer.5.attention.self.key.weight": "model-00003-of-00003.safetensors",
461
- "model.gs_former.mmtransformer.layer.5.attention.self.query.bias": "model-00003-of-00003.safetensors",
462
- "model.gs_former.mmtransformer.layer.5.attention.self.query.weight": "model-00003-of-00003.safetensors",
463
- "model.gs_former.mmtransformer.layer.5.attention.self.value.bias": "model-00003-of-00003.safetensors",
464
- "model.gs_former.mmtransformer.layer.5.attention.self.value.weight": "model-00003-of-00003.safetensors",
465
- "model.gs_former.mmtransformer.layer.5.intermediate_query.dense.bias": "model-00003-of-00003.safetensors",
466
- "model.gs_former.mmtransformer.layer.5.intermediate_query.dense.weight": "model-00003-of-00003.safetensors",
467
- "model.gs_former.mmtransformer.layer.5.output_query.LayerNorm.bias": "model-00003-of-00003.safetensors",
468
- "model.gs_former.mmtransformer.layer.5.output_query.LayerNorm.weight": "model-00003-of-00003.safetensors",
469
- "model.gs_former.mmtransformer.layer.5.output_query.dense.bias": "model-00003-of-00003.safetensors",
470
- "model.gs_former.mmtransformer.layer.5.output_query.dense.weight": "model-00003-of-00003.safetensors",
471
- "model.gs_former.mmtransformer.layer.6.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
472
- "model.gs_former.mmtransformer.layer.6.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
473
- "model.gs_former.mmtransformer.layer.6.attention.output.dense.bias": "model-00003-of-00003.safetensors",
474
- "model.gs_former.mmtransformer.layer.6.attention.output.dense.weight": "model-00003-of-00003.safetensors",
475
- "model.gs_former.mmtransformer.layer.6.attention.self.key.bias": "model-00003-of-00003.safetensors",
476
- "model.gs_former.mmtransformer.layer.6.attention.self.key.weight": "model-00003-of-00003.safetensors",
477
- "model.gs_former.mmtransformer.layer.6.attention.self.query.bias": "model-00003-of-00003.safetensors",
478
- "model.gs_former.mmtransformer.layer.6.attention.self.query.weight": "model-00003-of-00003.safetensors",
479
- "model.gs_former.mmtransformer.layer.6.attention.self.value.bias": "model-00003-of-00003.safetensors",
480
- "model.gs_former.mmtransformer.layer.6.attention.self.value.weight": "model-00003-of-00003.safetensors",
481
- "model.gs_former.mmtransformer.layer.6.crossattention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
482
- "model.gs_former.mmtransformer.layer.6.crossattention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
483
- "model.gs_former.mmtransformer.layer.6.crossattention.output.dense.bias": "model-00003-of-00003.safetensors",
484
- "model.gs_former.mmtransformer.layer.6.crossattention.output.dense.weight": "model-00003-of-00003.safetensors",
485
- "model.gs_former.mmtransformer.layer.6.crossattention.self.key.bias": "model-00003-of-00003.safetensors",
486
- "model.gs_former.mmtransformer.layer.6.crossattention.self.key.weight": "model-00003-of-00003.safetensors",
487
- "model.gs_former.mmtransformer.layer.6.crossattention.self.query.bias": "model-00003-of-00003.safetensors",
488
- "model.gs_former.mmtransformer.layer.6.crossattention.self.query.weight": "model-00003-of-00003.safetensors",
489
- "model.gs_former.mmtransformer.layer.6.crossattention.self.value.bias": "model-00003-of-00003.safetensors",
490
- "model.gs_former.mmtransformer.layer.6.crossattention.self.value.weight": "model-00003-of-00003.safetensors",
491
- "model.gs_former.mmtransformer.layer.6.intermediate_query.dense.bias": "model-00003-of-00003.safetensors",
492
- "model.gs_former.mmtransformer.layer.6.intermediate_query.dense.weight": "model-00003-of-00003.safetensors",
493
- "model.gs_former.mmtransformer.layer.6.output_query.LayerNorm.bias": "model-00003-of-00003.safetensors",
494
- "model.gs_former.mmtransformer.layer.6.output_query.LayerNorm.weight": "model-00003-of-00003.safetensors",
495
- "model.gs_former.mmtransformer.layer.6.output_query.dense.bias": "model-00003-of-00003.safetensors",
496
- "model.gs_former.mmtransformer.layer.6.output_query.dense.weight": "model-00003-of-00003.safetensors",
497
- "model.gs_former.mmtransformer.layer.7.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
498
- "model.gs_former.mmtransformer.layer.7.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
499
- "model.gs_former.mmtransformer.layer.7.attention.output.dense.bias": "model-00003-of-00003.safetensors",
500
- "model.gs_former.mmtransformer.layer.7.attention.output.dense.weight": "model-00003-of-00003.safetensors",
501
- "model.gs_former.mmtransformer.layer.7.attention.self.key.bias": "model-00003-of-00003.safetensors",
502
- "model.gs_former.mmtransformer.layer.7.attention.self.key.weight": "model-00003-of-00003.safetensors",
503
- "model.gs_former.mmtransformer.layer.7.attention.self.query.bias": "model-00003-of-00003.safetensors",
504
- "model.gs_former.mmtransformer.layer.7.attention.self.query.weight": "model-00003-of-00003.safetensors",
505
- "model.gs_former.mmtransformer.layer.7.attention.self.value.bias": "model-00003-of-00003.safetensors",
506
- "model.gs_former.mmtransformer.layer.7.attention.self.value.weight": "model-00003-of-00003.safetensors",
507
- "model.gs_former.mmtransformer.layer.7.intermediate_query.dense.bias": "model-00003-of-00003.safetensors",
508
- "model.gs_former.mmtransformer.layer.7.intermediate_query.dense.weight": "model-00003-of-00003.safetensors",
509
- "model.gs_former.mmtransformer.layer.7.output_query.LayerNorm.bias": "model-00003-of-00003.safetensors",
510
- "model.gs_former.mmtransformer.layer.7.output_query.LayerNorm.weight": "model-00003-of-00003.safetensors",
511
- "model.gs_former.mmtransformer.layer.7.output_query.dense.bias": "model-00003-of-00003.safetensors",
512
- "model.gs_former.mmtransformer.layer.7.output_query.dense.weight": "model-00003-of-00003.safetensors",
513
- "model.gs_former.mmtransformer.layer.8.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
514
- "model.gs_former.mmtransformer.layer.8.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
515
- "model.gs_former.mmtransformer.layer.8.attention.output.dense.bias": "model-00003-of-00003.safetensors",
516
- "model.gs_former.mmtransformer.layer.8.attention.output.dense.weight": "model-00003-of-00003.safetensors",
517
- "model.gs_former.mmtransformer.layer.8.attention.self.key.bias": "model-00003-of-00003.safetensors",
518
- "model.gs_former.mmtransformer.layer.8.attention.self.key.weight": "model-00003-of-00003.safetensors",
519
- "model.gs_former.mmtransformer.layer.8.attention.self.query.bias": "model-00003-of-00003.safetensors",
520
- "model.gs_former.mmtransformer.layer.8.attention.self.query.weight": "model-00003-of-00003.safetensors",
521
- "model.gs_former.mmtransformer.layer.8.attention.self.value.bias": "model-00003-of-00003.safetensors",
522
- "model.gs_former.mmtransformer.layer.8.attention.self.value.weight": "model-00003-of-00003.safetensors",
523
- "model.gs_former.mmtransformer.layer.8.crossattention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
524
- "model.gs_former.mmtransformer.layer.8.crossattention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
525
- "model.gs_former.mmtransformer.layer.8.crossattention.output.dense.bias": "model-00003-of-00003.safetensors",
526
- "model.gs_former.mmtransformer.layer.8.crossattention.output.dense.weight": "model-00003-of-00003.safetensors",
527
- "model.gs_former.mmtransformer.layer.8.crossattention.self.key.bias": "model-00003-of-00003.safetensors",
528
- "model.gs_former.mmtransformer.layer.8.crossattention.self.key.weight": "model-00003-of-00003.safetensors",
529
- "model.gs_former.mmtransformer.layer.8.crossattention.self.query.bias": "model-00003-of-00003.safetensors",
530
- "model.gs_former.mmtransformer.layer.8.crossattention.self.query.weight": "model-00003-of-00003.safetensors",
531
- "model.gs_former.mmtransformer.layer.8.crossattention.self.value.bias": "model-00003-of-00003.safetensors",
532
- "model.gs_former.mmtransformer.layer.8.crossattention.self.value.weight": "model-00003-of-00003.safetensors",
533
- "model.gs_former.mmtransformer.layer.8.intermediate_query.dense.bias": "model-00003-of-00003.safetensors",
534
- "model.gs_former.mmtransformer.layer.8.intermediate_query.dense.weight": "model-00003-of-00003.safetensors",
535
- "model.gs_former.mmtransformer.layer.8.output_query.LayerNorm.bias": "model-00003-of-00003.safetensors",
536
- "model.gs_former.mmtransformer.layer.8.output_query.LayerNorm.weight": "model-00003-of-00003.safetensors",
537
- "model.gs_former.mmtransformer.layer.8.output_query.dense.bias": "model-00003-of-00003.safetensors",
538
- "model.gs_former.mmtransformer.layer.8.output_query.dense.weight": "model-00003-of-00003.safetensors",
539
- "model.gs_former.mmtransformer.layer.9.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
540
- "model.gs_former.mmtransformer.layer.9.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
541
- "model.gs_former.mmtransformer.layer.9.attention.output.dense.bias": "model-00003-of-00003.safetensors",
542
- "model.gs_former.mmtransformer.layer.9.attention.output.dense.weight": "model-00003-of-00003.safetensors",
543
- "model.gs_former.mmtransformer.layer.9.attention.self.key.bias": "model-00003-of-00003.safetensors",
544
- "model.gs_former.mmtransformer.layer.9.attention.self.key.weight": "model-00003-of-00003.safetensors",
545
- "model.gs_former.mmtransformer.layer.9.attention.self.query.bias": "model-00003-of-00003.safetensors",
546
- "model.gs_former.mmtransformer.layer.9.attention.self.query.weight": "model-00003-of-00003.safetensors",
547
- "model.gs_former.mmtransformer.layer.9.attention.self.value.bias": "model-00003-of-00003.safetensors",
548
- "model.gs_former.mmtransformer.layer.9.attention.self.value.weight": "model-00003-of-00003.safetensors",
549
- "model.gs_former.mmtransformer.layer.9.intermediate_query.dense.bias": "model-00003-of-00003.safetensors",
550
- "model.gs_former.mmtransformer.layer.9.intermediate_query.dense.weight": "model-00003-of-00003.safetensors",
551
- "model.gs_former.mmtransformer.layer.9.output_query.LayerNorm.bias": "model-00003-of-00003.safetensors",
552
- "model.gs_former.mmtransformer.layer.9.output_query.LayerNorm.weight": "model-00003-of-00003.safetensors",
553
- "model.gs_former.mmtransformer.layer.9.output_query.dense.bias": "model-00003-of-00003.safetensors",
554
- "model.gs_former.mmtransformer.layer.9.output_query.dense.weight": "model-00003-of-00003.safetensors",
555
- "model.gs_former.mmtransformer.sampler.3.linear_layer.bias": "model-00003-of-00003.safetensors",
556
- "model.gs_former.mmtransformer.sampler.3.linear_layer.weight": "model-00003-of-00003.safetensors",
557
- "model.gs_former.mmtransformer.sampler.6.linear_layer.bias": "model-00003-of-00003.safetensors",
558
- "model.gs_former.mmtransformer.sampler.6.linear_layer.weight": "model-00003-of-00003.safetensors",
559
- "model.gs_former.mmtransformer.sampler.9.linear_layer.bias": "model-00003-of-00003.safetensors",
560
- "model.gs_former.mmtransformer.sampler.9.linear_layer.weight": "model-00003-of-00003.safetensors",
561
- "model.gs_former.generator.attention.bias": "model-00003-of-00003.safetensors",
562
- "model.gs_former.generator.attention.weight": "model-00003-of-00003.safetensors",
563
- "model.gs_former.generator.fc.bias": "model-00003-of-00003.safetensors",
564
- "model.gs_former.generator.fc.weight": "model-00003-of-00003.safetensors",
565
- "model.gs_former.generator.layers.0.linear1.bias": "model-00003-of-00003.safetensors",
566
- "model.gs_former.generator.layers.0.linear1.weight": "model-00003-of-00003.safetensors",
567
- "model.gs_former.generator.layers.0.linear2.bias": "model-00003-of-00003.safetensors",
568
- "model.gs_former.generator.layers.0.linear2.weight": "model-00003-of-00003.safetensors",
569
- "model.gs_former.generator.layers.0.norm1.bias": "model-00003-of-00003.safetensors",
570
- "model.gs_former.generator.layers.0.norm1.weight": "model-00003-of-00003.safetensors",
571
- "model.gs_former.generator.layers.0.norm2.bias": "model-00003-of-00003.safetensors",
572
- "model.gs_former.generator.layers.0.norm2.weight": "model-00003-of-00003.safetensors",
573
- "model.gs_former.generator.layers.0.self_attn.in_proj_bias": "model-00003-of-00003.safetensors",
574
- "model.gs_former.generator.layers.0.self_attn.in_proj_weight": "model-00003-of-00003.safetensors",
575
- "model.gs_former.generator.layers.0.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
576
- "model.gs_former.generator.layers.0.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
577
- "model.gs_former.generator.layers.1.linear1.bias": "model-00003-of-00003.safetensors",
578
- "model.gs_former.generator.layers.1.linear1.weight": "model-00003-of-00003.safetensors",
579
- "model.gs_former.generator.layers.1.linear2.bias": "model-00003-of-00003.safetensors",
580
- "model.gs_former.generator.layers.1.linear2.weight": "model-00003-of-00003.safetensors",
581
- "model.gs_former.generator.layers.1.norm1.bias": "model-00003-of-00003.safetensors",
582
- "model.gs_former.generator.layers.1.norm1.weight": "model-00003-of-00003.safetensors",
583
- "model.gs_former.generator.layers.1.norm2.bias": "model-00003-of-00003.safetensors",
584
- "model.gs_former.generator.layers.1.norm2.weight": "model-00003-of-00003.safetensors",
585
- "model.gs_former.generator.layers.1.self_attn.in_proj_bias": "model-00003-of-00003.safetensors",
586
- "model.gs_former.generator.layers.1.self_attn.in_proj_weight": "model-00003-of-00003.safetensors",
587
- "model.gs_former.generator.layers.1.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
588
- "model.gs_former.generator.layers.1.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
589
- "model.vision_tower.vision_tower.blocks.0.attn.proj.bias": "model-00003-of-00003.safetensors",
590
- "model.vision_tower.vision_tower.blocks.0.attn.proj.weight": "model-00003-of-00003.safetensors",
591
- "model.vision_tower.vision_tower.blocks.0.attn.qkv.bias": "model-00003-of-00003.safetensors",
592
- "model.vision_tower.vision_tower.blocks.0.attn.qkv.weight": "model-00003-of-00003.safetensors",
593
- "model.vision_tower.vision_tower.blocks.0.mlp.fc1.bias": "model-00003-of-00003.safetensors",
594
- "model.vision_tower.vision_tower.blocks.0.mlp.fc1.weight": "model-00003-of-00003.safetensors",
595
- "model.vision_tower.vision_tower.blocks.0.mlp.fc2.bias": "model-00003-of-00003.safetensors",
596
- "model.vision_tower.vision_tower.blocks.0.mlp.fc2.weight": "model-00003-of-00003.safetensors",
597
- "model.vision_tower.vision_tower.blocks.0.norm1.bias": "model-00003-of-00003.safetensors",
598
- "model.vision_tower.vision_tower.blocks.0.norm1.weight": "model-00003-of-00003.safetensors",
599
- "model.vision_tower.vision_tower.blocks.0.norm2.bias": "model-00003-of-00003.safetensors",
600
- "model.vision_tower.vision_tower.blocks.0.norm2.weight": "model-00003-of-00003.safetensors",
601
- "model.vision_tower.vision_tower.blocks.1.attn.proj.bias": "model-00003-of-00003.safetensors",
602
- "model.vision_tower.vision_tower.blocks.1.attn.proj.weight": "model-00003-of-00003.safetensors",
603
- "model.vision_tower.vision_tower.blocks.1.attn.qkv.bias": "model-00003-of-00003.safetensors",
604
- "model.vision_tower.vision_tower.blocks.1.attn.qkv.weight": "model-00003-of-00003.safetensors",
605
- "model.vision_tower.vision_tower.blocks.1.mlp.fc1.bias": "model-00003-of-00003.safetensors",
606
- "model.vision_tower.vision_tower.blocks.1.mlp.fc1.weight": "model-00003-of-00003.safetensors",
607
- "model.vision_tower.vision_tower.blocks.1.mlp.fc2.bias": "model-00003-of-00003.safetensors",
608
- "model.vision_tower.vision_tower.blocks.1.mlp.fc2.weight": "model-00003-of-00003.safetensors",
609
- "model.vision_tower.vision_tower.blocks.1.norm1.bias": "model-00003-of-00003.safetensors",
610
- "model.vision_tower.vision_tower.blocks.1.norm1.weight": "model-00003-of-00003.safetensors",
611
- "model.vision_tower.vision_tower.blocks.1.norm2.bias": "model-00003-of-00003.safetensors",
612
- "model.vision_tower.vision_tower.blocks.1.norm2.weight": "model-00003-of-00003.safetensors",
613
- "model.vision_tower.vision_tower.blocks.10.attn.proj.bias": "model-00003-of-00003.safetensors",
614
- "model.vision_tower.vision_tower.blocks.10.attn.proj.weight": "model-00003-of-00003.safetensors",
615
- "model.vision_tower.vision_tower.blocks.10.attn.qkv.bias": "model-00003-of-00003.safetensors",
616
- "model.vision_tower.vision_tower.blocks.10.attn.qkv.weight": "model-00003-of-00003.safetensors",
617
- "model.vision_tower.vision_tower.blocks.10.mlp.fc1.bias": "model-00003-of-00003.safetensors",
618
- "model.vision_tower.vision_tower.blocks.10.mlp.fc1.weight": "model-00003-of-00003.safetensors",
619
- "model.vision_tower.vision_tower.blocks.10.mlp.fc2.bias": "model-00003-of-00003.safetensors",
620
- "model.vision_tower.vision_tower.blocks.10.mlp.fc2.weight": "model-00003-of-00003.safetensors",
621
- "model.vision_tower.vision_tower.blocks.10.norm1.bias": "model-00003-of-00003.safetensors",
622
- "model.vision_tower.vision_tower.blocks.10.norm1.weight": "model-00003-of-00003.safetensors",
623
- "model.vision_tower.vision_tower.blocks.10.norm2.bias": "model-00003-of-00003.safetensors",
624
- "model.vision_tower.vision_tower.blocks.10.norm2.weight": "model-00003-of-00003.safetensors",
625
- "model.vision_tower.vision_tower.blocks.11.attn.proj.bias": "model-00003-of-00003.safetensors",
626
- "model.vision_tower.vision_tower.blocks.11.attn.proj.weight": "model-00003-of-00003.safetensors",
627
- "model.vision_tower.vision_tower.blocks.11.attn.qkv.bias": "model-00003-of-00003.safetensors",
628
- "model.vision_tower.vision_tower.blocks.11.attn.qkv.weight": "model-00003-of-00003.safetensors",
629
- "model.vision_tower.vision_tower.blocks.11.mlp.fc1.bias": "model-00003-of-00003.safetensors",
630
- "model.vision_tower.vision_tower.blocks.11.mlp.fc1.weight": "model-00003-of-00003.safetensors",
631
- "model.vision_tower.vision_tower.blocks.11.mlp.fc2.bias": "model-00003-of-00003.safetensors",
632
- "model.vision_tower.vision_tower.blocks.11.mlp.fc2.weight": "model-00003-of-00003.safetensors",
633
- "model.vision_tower.vision_tower.blocks.11.norm1.bias": "model-00003-of-00003.safetensors",
634
- "model.vision_tower.vision_tower.blocks.11.norm1.weight": "model-00003-of-00003.safetensors",
635
- "model.vision_tower.vision_tower.blocks.11.norm2.bias": "model-00003-of-00003.safetensors",
636
- "model.vision_tower.vision_tower.blocks.11.norm2.weight": "model-00003-of-00003.safetensors",
637
- "model.vision_tower.vision_tower.blocks.2.attn.proj.bias": "model-00003-of-00003.safetensors",
638
- "model.vision_tower.vision_tower.blocks.2.attn.proj.weight": "model-00003-of-00003.safetensors",
639
- "model.vision_tower.vision_tower.blocks.2.attn.qkv.bias": "model-00003-of-00003.safetensors",
640
- "model.vision_tower.vision_tower.blocks.2.attn.qkv.weight": "model-00003-of-00003.safetensors",
641
- "model.vision_tower.vision_tower.blocks.2.mlp.fc1.bias": "model-00003-of-00003.safetensors",
642
- "model.vision_tower.vision_tower.blocks.2.mlp.fc1.weight": "model-00003-of-00003.safetensors",
643
- "model.vision_tower.vision_tower.blocks.2.mlp.fc2.bias": "model-00003-of-00003.safetensors",
644
- "model.vision_tower.vision_tower.blocks.2.mlp.fc2.weight": "model-00003-of-00003.safetensors",
645
- "model.vision_tower.vision_tower.blocks.2.norm1.bias": "model-00003-of-00003.safetensors",
646
- "model.vision_tower.vision_tower.blocks.2.norm1.weight": "model-00003-of-00003.safetensors",
647
- "model.vision_tower.vision_tower.blocks.2.norm2.bias": "model-00003-of-00003.safetensors",
648
- "model.vision_tower.vision_tower.blocks.2.norm2.weight": "model-00003-of-00003.safetensors",
649
- "model.vision_tower.vision_tower.blocks.3.attn.proj.bias": "model-00003-of-00003.safetensors",
650
- "model.vision_tower.vision_tower.blocks.3.attn.proj.weight": "model-00003-of-00003.safetensors",
651
- "model.vision_tower.vision_tower.blocks.3.attn.qkv.bias": "model-00003-of-00003.safetensors",
652
- "model.vision_tower.vision_tower.blocks.3.attn.qkv.weight": "model-00003-of-00003.safetensors",
653
- "model.vision_tower.vision_tower.blocks.3.mlp.fc1.bias": "model-00003-of-00003.safetensors",
654
- "model.vision_tower.vision_tower.blocks.3.mlp.fc1.weight": "model-00003-of-00003.safetensors",
655
- "model.vision_tower.vision_tower.blocks.3.mlp.fc2.bias": "model-00003-of-00003.safetensors",
656
- "model.vision_tower.vision_tower.blocks.3.mlp.fc2.weight": "model-00003-of-00003.safetensors",
657
- "model.vision_tower.vision_tower.blocks.3.norm1.bias": "model-00003-of-00003.safetensors",
658
- "model.vision_tower.vision_tower.blocks.3.norm1.weight": "model-00003-of-00003.safetensors",
659
- "model.vision_tower.vision_tower.blocks.3.norm2.bias": "model-00003-of-00003.safetensors",
660
- "model.vision_tower.vision_tower.blocks.3.norm2.weight": "model-00003-of-00003.safetensors",
661
- "model.vision_tower.vision_tower.blocks.4.attn.proj.bias": "model-00003-of-00003.safetensors",
662
- "model.vision_tower.vision_tower.blocks.4.attn.proj.weight": "model-00003-of-00003.safetensors",
663
- "model.vision_tower.vision_tower.blocks.4.attn.qkv.bias": "model-00003-of-00003.safetensors",
664
- "model.vision_tower.vision_tower.blocks.4.attn.qkv.weight": "model-00003-of-00003.safetensors",
665
- "model.vision_tower.vision_tower.blocks.4.mlp.fc1.bias": "model-00003-of-00003.safetensors",
666
- "model.vision_tower.vision_tower.blocks.4.mlp.fc1.weight": "model-00003-of-00003.safetensors",
667
- "model.vision_tower.vision_tower.blocks.4.mlp.fc2.bias": "model-00003-of-00003.safetensors",
668
- "model.vision_tower.vision_tower.blocks.4.mlp.fc2.weight": "model-00003-of-00003.safetensors",
669
- "model.vision_tower.vision_tower.blocks.4.norm1.bias": "model-00003-of-00003.safetensors",
670
- "model.vision_tower.vision_tower.blocks.4.norm1.weight": "model-00003-of-00003.safetensors",
671
- "model.vision_tower.vision_tower.blocks.4.norm2.bias": "model-00003-of-00003.safetensors",
672
- "model.vision_tower.vision_tower.blocks.4.norm2.weight": "model-00003-of-00003.safetensors",
673
- "model.vision_tower.vision_tower.blocks.5.attn.proj.bias": "model-00003-of-00003.safetensors",
674
- "model.vision_tower.vision_tower.blocks.5.attn.proj.weight": "model-00003-of-00003.safetensors",
675
- "model.vision_tower.vision_tower.blocks.5.attn.qkv.bias": "model-00003-of-00003.safetensors",
676
- "model.vision_tower.vision_tower.blocks.5.attn.qkv.weight": "model-00003-of-00003.safetensors",
677
- "model.vision_tower.vision_tower.blocks.5.mlp.fc1.bias": "model-00003-of-00003.safetensors",
678
- "model.vision_tower.vision_tower.blocks.5.mlp.fc1.weight": "model-00003-of-00003.safetensors",
679
- "model.vision_tower.vision_tower.blocks.5.mlp.fc2.bias": "model-00003-of-00003.safetensors",
680
- "model.vision_tower.vision_tower.blocks.5.mlp.fc2.weight": "model-00003-of-00003.safetensors",
681
- "model.vision_tower.vision_tower.blocks.5.norm1.bias": "model-00003-of-00003.safetensors",
682
- "model.vision_tower.vision_tower.blocks.5.norm1.weight": "model-00003-of-00003.safetensors",
683
- "model.vision_tower.vision_tower.blocks.5.norm2.bias": "model-00003-of-00003.safetensors",
684
- "model.vision_tower.vision_tower.blocks.5.norm2.weight": "model-00003-of-00003.safetensors",
685
- "model.vision_tower.vision_tower.blocks.6.attn.proj.bias": "model-00003-of-00003.safetensors",
686
- "model.vision_tower.vision_tower.blocks.6.attn.proj.weight": "model-00003-of-00003.safetensors",
687
- "model.vision_tower.vision_tower.blocks.6.attn.qkv.bias": "model-00003-of-00003.safetensors",
688
- "model.vision_tower.vision_tower.blocks.6.attn.qkv.weight": "model-00003-of-00003.safetensors",
689
- "model.vision_tower.vision_tower.blocks.6.mlp.fc1.bias": "model-00003-of-00003.safetensors",
690
- "model.vision_tower.vision_tower.blocks.6.mlp.fc1.weight": "model-00003-of-00003.safetensors",
691
- "model.vision_tower.vision_tower.blocks.6.mlp.fc2.bias": "model-00003-of-00003.safetensors",
692
- "model.vision_tower.vision_tower.blocks.6.mlp.fc2.weight": "model-00003-of-00003.safetensors",
693
- "model.vision_tower.vision_tower.blocks.6.norm1.bias": "model-00003-of-00003.safetensors",
694
- "model.vision_tower.vision_tower.blocks.6.norm1.weight": "model-00003-of-00003.safetensors",
695
- "model.vision_tower.vision_tower.blocks.6.norm2.bias": "model-00003-of-00003.safetensors",
696
- "model.vision_tower.vision_tower.blocks.6.norm2.weight": "model-00003-of-00003.safetensors",
697
- "model.vision_tower.vision_tower.blocks.7.attn.proj.bias": "model-00003-of-00003.safetensors",
698
- "model.vision_tower.vision_tower.blocks.7.attn.proj.weight": "model-00003-of-00003.safetensors",
699
- "model.vision_tower.vision_tower.blocks.7.attn.qkv.bias": "model-00003-of-00003.safetensors",
700
- "model.vision_tower.vision_tower.blocks.7.attn.qkv.weight": "model-00003-of-00003.safetensors",
701
- "model.vision_tower.vision_tower.blocks.7.mlp.fc1.bias": "model-00003-of-00003.safetensors",
702
- "model.vision_tower.vision_tower.blocks.7.mlp.fc1.weight": "model-00003-of-00003.safetensors",
703
- "model.vision_tower.vision_tower.blocks.7.mlp.fc2.bias": "model-00003-of-00003.safetensors",
704
- "model.vision_tower.vision_tower.blocks.7.mlp.fc2.weight": "model-00003-of-00003.safetensors",
705
- "model.vision_tower.vision_tower.blocks.7.norm1.bias": "model-00003-of-00003.safetensors",
706
- "model.vision_tower.vision_tower.blocks.7.norm1.weight": "model-00003-of-00003.safetensors",
707
- "model.vision_tower.vision_tower.blocks.7.norm2.bias": "model-00003-of-00003.safetensors",
708
- "model.vision_tower.vision_tower.blocks.7.norm2.weight": "model-00003-of-00003.safetensors",
709
- "model.vision_tower.vision_tower.blocks.8.attn.proj.bias": "model-00003-of-00003.safetensors",
710
- "model.vision_tower.vision_tower.blocks.8.attn.proj.weight": "model-00003-of-00003.safetensors",
711
- "model.vision_tower.vision_tower.blocks.8.attn.qkv.bias": "model-00003-of-00003.safetensors",
712
- "model.vision_tower.vision_tower.blocks.8.attn.qkv.weight": "model-00003-of-00003.safetensors",
713
- "model.vision_tower.vision_tower.blocks.8.mlp.fc1.bias": "model-00003-of-00003.safetensors",
714
- "model.vision_tower.vision_tower.blocks.8.mlp.fc1.weight": "model-00003-of-00003.safetensors",
715
- "model.vision_tower.vision_tower.blocks.8.mlp.fc2.bias": "model-00003-of-00003.safetensors",
716
- "model.vision_tower.vision_tower.blocks.8.mlp.fc2.weight": "model-00003-of-00003.safetensors",
717
- "model.vision_tower.vision_tower.blocks.8.norm1.bias": "model-00003-of-00003.safetensors",
718
- "model.vision_tower.vision_tower.blocks.8.norm1.weight": "model-00003-of-00003.safetensors",
719
- "model.vision_tower.vision_tower.blocks.8.norm2.bias": "model-00003-of-00003.safetensors",
720
- "model.vision_tower.vision_tower.blocks.8.norm2.weight": "model-00003-of-00003.safetensors",
721
- "model.vision_tower.vision_tower.blocks.9.attn.proj.bias": "model-00003-of-00003.safetensors",
722
- "model.vision_tower.vision_tower.blocks.9.attn.proj.weight": "model-00003-of-00003.safetensors",
723
- "model.vision_tower.vision_tower.blocks.9.attn.qkv.bias": "model-00003-of-00003.safetensors",
724
- "model.vision_tower.vision_tower.blocks.9.attn.qkv.weight": "model-00003-of-00003.safetensors",
725
- "model.vision_tower.vision_tower.blocks.9.mlp.fc1.bias": "model-00003-of-00003.safetensors",
726
- "model.vision_tower.vision_tower.blocks.9.mlp.fc1.weight": "model-00003-of-00003.safetensors",
727
- "model.vision_tower.vision_tower.blocks.9.mlp.fc2.bias": "model-00003-of-00003.safetensors",
728
- "model.vision_tower.vision_tower.blocks.9.mlp.fc2.weight": "model-00003-of-00003.safetensors",
729
- "model.vision_tower.vision_tower.blocks.9.norm1.bias": "model-00003-of-00003.safetensors",
730
- "model.vision_tower.vision_tower.blocks.9.norm1.weight": "model-00003-of-00003.safetensors",
731
- "model.vision_tower.vision_tower.blocks.9.norm2.bias": "model-00003-of-00003.safetensors",
732
- "model.vision_tower.vision_tower.blocks.9.norm2.weight": "model-00003-of-00003.safetensors",
733
- "model.vision_tower.vision_tower.cls_token": "model-00003-of-00003.safetensors",
734
- "model.vision_tower.vision_tower.norm.bias": "model-00003-of-00003.safetensors",
735
- "model.vision_tower.vision_tower.norm.weight": "model-00003-of-00003.safetensors",
736
- "model.vision_tower.vision_tower.patch_embed.proj.bias": "model-00003-of-00003.safetensors",
737
- "model.vision_tower.vision_tower.patch_embed.proj.weight": "model-00003-of-00003.safetensors",
738
- "model.vision_tower.vision_tower.pos_embed": "model-00003-of-00003.safetensors"
739
- }
740
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
geox_unigeo/special_tokens_map.json DELETED
@@ -1,24 +0,0 @@
1
- {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "</s>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": "<unk>",
17
- "unk_token": {
18
- "content": "<unk>",
19
- "lstrip": false,
20
- "normalized": false,
21
- "rstrip": false,
22
- "single_word": false
23
- }
24
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
geox_unigeo/tokenizer.model DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
3
- size 500058
 
 
 
 
geox_unigeo/tokenizer_config.json DELETED
@@ -1,43 +0,0 @@
1
- {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
- "add_prefix_space": true,
5
- "added_tokens_decoder": {
6
- "0": {
7
- "content": "<unk>",
8
- "lstrip": false,
9
- "normalized": false,
10
- "rstrip": false,
11
- "single_word": false,
12
- "special": true
13
- },
14
- "1": {
15
- "content": "<s>",
16
- "lstrip": false,
17
- "normalized": false,
18
- "rstrip": false,
19
- "single_word": false,
20
- "special": true
21
- },
22
- "2": {
23
- "content": "</s>",
24
- "lstrip": false,
25
- "normalized": false,
26
- "rstrip": false,
27
- "single_word": false,
28
- "special": true
29
- }
30
- },
31
- "bos_token": "<s>",
32
- "clean_up_tokenization_spaces": false,
33
- "eos_token": "</s>",
34
- "legacy": true,
35
- "model_max_length": 2048,
36
- "pad_token": "<unk>",
37
- "padding_side": "right",
38
- "sp_model_kwargs": {},
39
- "spaces_between_special_tokens": false,
40
- "tokenizer_class": "LlamaTokenizer",
41
- "unk_token": "<unk>",
42
- "use_default_system_prompt": false
43
- }