Hugging Face's logo

Spaces:
JuanMa360
/
DD360-Bot
Running

App Files Community
JuanMa360 commited on
Commit
a6c3a83
•
1 Parent(s): affcd43

refactor: app

Browse files
Files changed (12) hide show
  1. .DS_Store +0 -0
  2. app.py +18 -31
  3. dd360-v1-3b/config.json +0 -64
  4. dd360-v1-3b/generation_config.json +0 -6
  5. dd360-v1-3b/model.safetensors.index.json +0 -757
  6. requirements.txt +2 -7
  7. tokenizer-dd360/added_tokens.json +0 -42
  8. tokenizer-dd360/merges.txt +0 -0
  9. tokenizer-dd360/special_tokens_map.json +0 -23
  10. tokenizer-dd360/tokenizer.json +0 -0
  11. tokenizer-dd360/tokenizer_config.json +0 -342
  12. tokenizer-dd360/vocab.json +0 -0
.DS_Store CHANGED
Binary files a/.DS_Store and b/.DS_Store differ
 
app.py CHANGED
@@ -1,38 +1,25 @@
1
- import torch
2
- from transformers import AutoModelForCausalLM, AutoTokenizer
3
- from PIL import Image
4
  import gradio as gr
 
 
 
5
 
6
- model = AutoModelForCausalLM.from_pretrained(
7
- "dd360-v1-3b",
8
- torch_dtype=torch.float32,
9
- device_map="auto",
10
- trust_remote_code=True)
11
- tokenizer = AutoTokenizer.from_pretrained("tokenizer-dd360",torch_dtype=torch.float32)
12
-
13
-
14
- def generate_answer(text, image):
15
 
16
- input_ids = tokenizer(text, return_tensors='pt').input_ids
17
- image_tensor = model.image_preprocess(image)
18
 
19
- output_ids = model.generate(
20
- input_ids,
21
- max_new_tokens=100,
22
- images=image_tensor,
23
- use_cache=True)[0]
24
-
25
- return tokenizer.decode(output_ids[input_ids.shape[1]:], skip_special_tokens=True).strip()
26
 
27
- text_input = gr.Textbox(lines=5, label="Enter text")
28
- image_input = gr.Image(type="pil", label="Upload Image")
29
 
30
- iface = gr.Interface(
31
- fn=generate_answer,
32
- inputs=[text_input, image_input],
33
- outputs="text",
34
- title="DD360-Bot-Multimodal",
35
- description="Enter text and upload an image to receive a response from the chatbot."
36
- )
37
 
38
- iface.launch()
 
 
 
 
1
  import gradio as gr
2
+ import spaces
3
+ import torch
4
+ from transformers import AutoProcessor, LlavaForConditionalGeneration
5
 
6
+ model_id = "llava-hf/llava-1.5-7b-hf"
 
 
 
 
 
 
 
 
7
 
8
+ prompt_format = "USER: <image>\n{}\nASSISTANT:"
 
9
 
10
+ model = LlavaForConditionalGeneration.from_pretrained(
11
+ model_id,
12
+ torch_dtype=torch.float16,
13
+ low_cpu_mem_usage=True,
14
+ ).cuda()
 
 
15
 
16
+ processor = AutoProcessor.from_pretrained(model_id)
 
17
 
18
+ @spaces.GPU
19
+ def inference(text, image):
20
+ prompt = prompt_format.format(text)
21
+ inputs = processor(prompt, image, return_tensors='pt').to(0, torch.float16)
22
+ output = model.generate(**inputs, max_new_tokens=1024)
23
+ return processor.decode(output[0], skip_special_tokens=True).split("ASSISTANT:")[-1]
 
24
 
25
+ gr.Interface(fn=inference, inputs=[gr.Text(), gr.Image()], outputs=gr.Text()).launch()
dd360-v1-3b/config.json DELETED
@@ -1,64 +0,0 @@
1
- {
2
- "_name_or_path": "MILVLG/imp-v1-3b",
3
- "activation_function": "gelu_new",
4
- "architectures": [
5
- "ImpForCausalLM"
6
- ],
7
- "attn_pdrop": 0.0,
8
- "auto_map": {
9
- "AutoConfig": "MILVLG/imp-v1-3b--configuration_imp.ImpConfig",
10
- "AutoModelForCausalLM": "MILVLG/imp-v1-3b--modeling_imp.ImpForCausalLM"
11
- },
12
- "embd_pdrop": 0.0,
13
- "eos_token_id": 50295,
14
- "flash_attn": false,
15
- "flash_rotary": false,
16
- "freeze_mm_mlp_adapter": false,
17
- "fused_dense": false,
18
- "image_aspect_ratio": "square",
19
- "image_token": "<image>",
20
- "image_token_index": 50296,
21
- "img_processor": null,
22
- "initializer_range": 0.02,
23
- "layer_norm_epsilon": 1e-05,
24
- "mm_hidden_size": 1152,
25
- "mm_projector_lr": 2e-05,
26
- "mm_projector_type": "mlp2x_gelu",
27
- "mm_use_im_patch_token": false,
28
- "mm_use_im_start_end": false,
29
- "mm_vision_select_feature": "patch",
30
- "mm_vision_select_layer": -2,
31
- "mm_vision_tower": "google/siglip-so400m-patch14-384",
32
- "model_type": "imp",
33
- "n_embd": 2560,
34
- "n_head": 32,
35
- "n_head_kv": null,
36
- "n_inner": null,
37
- "n_layer": 32,
38
- "n_positions": 3072,
39
- "pad_token_id": 50256,
40
- "resid_pdrop": 0.1,
41
- "rotary_dim": 32,
42
- "tie_word_embeddings": false,
43
- "tokenizer_model_max_length": 3072,
44
- "tokenizer_padding_side": "right",
45
- "torch_dtype": "float16",
46
- "transformers_version": "4.38.2",
47
- "use_cache": true,
48
- "use_mm_proj": true,
49
- "vision_tower_config": {
50
- "attention_dropout": 0.0,
51
- "attn_implementation": null,
52
- "hidden_act": "gelu_pytorch_tanh",
53
- "hidden_size": 1152,
54
- "image_size": 384,
55
- "intermediate_size": 4304,
56
- "layer_norm_eps": 1e-06,
57
- "model_type": "siglip_vision_model",
58
- "num_attention_heads": 16,
59
- "num_channels": 3,
60
- "num_hidden_layers": 27,
61
- "patch_size": 14
62
- },
63
- "vocab_size": 51200
64
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
dd360-v1-3b/generation_config.json DELETED
@@ -1,6 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "eos_token_id": 50295,
4
- "pad_token_id": 50256,
5
- "transformers_version": "4.38.2"
6
- }
 
 
 
 
 
 
 
dd360-v1-3b/model.safetensors.index.json DELETED
@@ -1,757 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 6373878848
4
- },
5
- "weight_map": {
6
- "lm_head.linear.bias": "model-00002-of-00002.safetensors",
7
- "lm_head.linear.weight": "model-00002-of-00002.safetensors",
8
- "lm_head.ln.bias": "model-00002-of-00002.safetensors",
9
- "lm_head.ln.weight": "model-00002-of-00002.safetensors",
10
- "transformer.embd.wte.weight": "model-00001-of-00002.safetensors",
11
- "transformer.h.0.ln.bias": "model-00001-of-00002.safetensors",
12
- "transformer.h.0.ln.weight": "model-00001-of-00002.safetensors",
13
- "transformer.h.0.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
14
- "transformer.h.0.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
15
- "transformer.h.0.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
16
- "transformer.h.0.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
17
- "transformer.h.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
18
- "transformer.h.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
19
- "transformer.h.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
20
- "transformer.h.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
21
- "transformer.h.1.ln.bias": "model-00001-of-00002.safetensors",
22
- "transformer.h.1.ln.weight": "model-00001-of-00002.safetensors",
23
- "transformer.h.1.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
24
- "transformer.h.1.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
25
- "transformer.h.1.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
26
- "transformer.h.1.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
27
- "transformer.h.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
28
- "transformer.h.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
29
- "transformer.h.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
30
- "transformer.h.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
31
- "transformer.h.10.ln.bias": "model-00001-of-00002.safetensors",
32
- "transformer.h.10.ln.weight": "model-00001-of-00002.safetensors",
33
- "transformer.h.10.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
34
- "transformer.h.10.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
35
- "transformer.h.10.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
36
- "transformer.h.10.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
37
- "transformer.h.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
38
- "transformer.h.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
39
- "transformer.h.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
40
- "transformer.h.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
41
- "transformer.h.11.ln.bias": "model-00001-of-00002.safetensors",
42
- "transformer.h.11.ln.weight": "model-00001-of-00002.safetensors",
43
- "transformer.h.11.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
44
- "transformer.h.11.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
45
- "transformer.h.11.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
46
- "transformer.h.11.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
47
- "transformer.h.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
48
- "transformer.h.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
49
- "transformer.h.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
50
- "transformer.h.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
51
- "transformer.h.12.ln.bias": "model-00001-of-00002.safetensors",
52
- "transformer.h.12.ln.weight": "model-00001-of-00002.safetensors",
53
- "transformer.h.12.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
54
- "transformer.h.12.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
55
- "transformer.h.12.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
56
- "transformer.h.12.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
57
- "transformer.h.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
58
- "transformer.h.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
59
- "transformer.h.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
60
- "transformer.h.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
61
- "transformer.h.13.ln.bias": "model-00001-of-00002.safetensors",
62
- "transformer.h.13.ln.weight": "model-00001-of-00002.safetensors",
63
- "transformer.h.13.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
64
- "transformer.h.13.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
65
- "transformer.h.13.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
66
- "transformer.h.13.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
67
- "transformer.h.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
68
- "transformer.h.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
69
- "transformer.h.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
70
- "transformer.h.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
71
- "transformer.h.14.ln.bias": "model-00001-of-00002.safetensors",
72
- "transformer.h.14.ln.weight": "model-00001-of-00002.safetensors",
73
- "transformer.h.14.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
74
- "transformer.h.14.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
75
- "transformer.h.14.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
76
- "transformer.h.14.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
77
- "transformer.h.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
78
- "transformer.h.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
79
- "transformer.h.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
80
- "transformer.h.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
81
- "transformer.h.15.ln.bias": "model-00001-of-00002.safetensors",
82
- "transformer.h.15.ln.weight": "model-00001-of-00002.safetensors",
83
- "transformer.h.15.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
84
- "transformer.h.15.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
85
- "transformer.h.15.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
86
- "transformer.h.15.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
87
- "transformer.h.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
88
- "transformer.h.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
89
- "transformer.h.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
90
- "transformer.h.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
91
- "transformer.h.16.ln.bias": "model-00001-of-00002.safetensors",
92
- "transformer.h.16.ln.weight": "model-00001-of-00002.safetensors",
93
- "transformer.h.16.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
94
- "transformer.h.16.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
95
- "transformer.h.16.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
96
- "transformer.h.16.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
97
- "transformer.h.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
98
- "transformer.h.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
99
- "transformer.h.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
100
- "transformer.h.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
101
- "transformer.h.17.ln.bias": "model-00001-of-00002.safetensors",
102
- "transformer.h.17.ln.weight": "model-00001-of-00002.safetensors",
103
- "transformer.h.17.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
104
- "transformer.h.17.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
105
- "transformer.h.17.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
106
- "transformer.h.17.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
107
- "transformer.h.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
108
- "transformer.h.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
109
- "transformer.h.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
110
- "transformer.h.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
111
- "transformer.h.18.ln.bias": "model-00001-of-00002.safetensors",
112
- "transformer.h.18.ln.weight": "model-00001-of-00002.safetensors",
113
- "transformer.h.18.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
114
- "transformer.h.18.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
115
- "transformer.h.18.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
116
- "transformer.h.18.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
117
- "transformer.h.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
118
- "transformer.h.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
119
- "transformer.h.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
120
- "transformer.h.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
121
- "transformer.h.19.ln.bias": "model-00001-of-00002.safetensors",
122
- "transformer.h.19.ln.weight": "model-00001-of-00002.safetensors",
123
- "transformer.h.19.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
124
- "transformer.h.19.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
125
- "transformer.h.19.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
126
- "transformer.h.19.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
127
- "transformer.h.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
128
- "transformer.h.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
129
- "transformer.h.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
130
- "transformer.h.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
131
- "transformer.h.2.ln.bias": "model-00001-of-00002.safetensors",
132
- "transformer.h.2.ln.weight": "model-00001-of-00002.safetensors",
133
- "transformer.h.2.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
134
- "transformer.h.2.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
135
- "transformer.h.2.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
136
- "transformer.h.2.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
137
- "transformer.h.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
138
- "transformer.h.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
139
- "transformer.h.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
140
- "transformer.h.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
141
- "transformer.h.20.ln.bias": "model-00001-of-00002.safetensors",
142
- "transformer.h.20.ln.weight": "model-00001-of-00002.safetensors",
143
- "transformer.h.20.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
144
- "transformer.h.20.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
145
- "transformer.h.20.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
146
- "transformer.h.20.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
147
- "transformer.h.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
148
- "transformer.h.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
149
- "transformer.h.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
150
- "transformer.h.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
151
- "transformer.h.21.ln.bias": "model-00001-of-00002.safetensors",
152
- "transformer.h.21.ln.weight": "model-00001-of-00002.safetensors",
153
- "transformer.h.21.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
154
- "transformer.h.21.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
155
- "transformer.h.21.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
156
- "transformer.h.21.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
157
- "transformer.h.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
158
- "transformer.h.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
159
- "transformer.h.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
160
- "transformer.h.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
161
- "transformer.h.22.ln.bias": "model-00001-of-00002.safetensors",
162
- "transformer.h.22.ln.weight": "model-00001-of-00002.safetensors",
163
- "transformer.h.22.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
164
- "transformer.h.22.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
165
- "transformer.h.22.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
166
- "transformer.h.22.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
167
- "transformer.h.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
168
- "transformer.h.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
169
- "transformer.h.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
170
- "transformer.h.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
171
- "transformer.h.23.ln.bias": "model-00001-of-00002.safetensors",
172
- "transformer.h.23.ln.weight": "model-00001-of-00002.safetensors",
173
- "transformer.h.23.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
174
- "transformer.h.23.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
175
- "transformer.h.23.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
176
- "transformer.h.23.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
177
- "transformer.h.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
178
- "transformer.h.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
179
- "transformer.h.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
180
- "transformer.h.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
181
- "transformer.h.24.ln.bias": "model-00001-of-00002.safetensors",
182
- "transformer.h.24.ln.weight": "model-00001-of-00002.safetensors",
183
- "transformer.h.24.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
184
- "transformer.h.24.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
185
- "transformer.h.24.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
186
- "transformer.h.24.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
187
- "transformer.h.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
188
- "transformer.h.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
189
- "transformer.h.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
190
- "transformer.h.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
191
- "transformer.h.25.ln.bias": "model-00001-of-00002.safetensors",
192
- "transformer.h.25.ln.weight": "model-00001-of-00002.safetensors",
193
- "transformer.h.25.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
194
- "transformer.h.25.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
195
- "transformer.h.25.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
196
- "transformer.h.25.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
197
- "transformer.h.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
198
- "transformer.h.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
199
- "transformer.h.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
200
- "transformer.h.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
201
- "transformer.h.26.ln.bias": "model-00001-of-00002.safetensors",
202
- "transformer.h.26.ln.weight": "model-00001-of-00002.safetensors",
203
- "transformer.h.26.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
204
- "transformer.h.26.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
205
- "transformer.h.26.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
206
- "transformer.h.26.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
207
- "transformer.h.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
208
- "transformer.h.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
209
- "transformer.h.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
210
- "transformer.h.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
211
- "transformer.h.27.ln.bias": "model-00001-of-00002.safetensors",
212
- "transformer.h.27.ln.weight": "model-00001-of-00002.safetensors",
213
- "transformer.h.27.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
214
- "transformer.h.27.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
215
- "transformer.h.27.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
216
- "transformer.h.27.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
217
- "transformer.h.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
218
- "transformer.h.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
219
- "transformer.h.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
220
- "transformer.h.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
221
- "transformer.h.28.ln.bias": "model-00001-of-00002.safetensors",
222
- "transformer.h.28.ln.weight": "model-00001-of-00002.safetensors",
223
- "transformer.h.28.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
224
- "transformer.h.28.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
225
- "transformer.h.28.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
226
- "transformer.h.28.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
227
- "transformer.h.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
228
- "transformer.h.28.mlp.fc1.weight": "model-00001-of-00002.safetensors",
229
- "transformer.h.28.mlp.fc2.bias": "model-00001-of-00002.safetensors",
230
- "transformer.h.28.mlp.fc2.weight": "model-00001-of-00002.safetensors",
231
- "transformer.h.29.ln.bias": "model-00001-of-00002.safetensors",
232
- "transformer.h.29.ln.weight": "model-00001-of-00002.safetensors",
233
- "transformer.h.29.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
234
- "transformer.h.29.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
235
- "transformer.h.29.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
236
- "transformer.h.29.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
237
- "transformer.h.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
238
- "transformer.h.29.mlp.fc1.weight": "model-00001-of-00002.safetensors",
239
- "transformer.h.29.mlp.fc2.bias": "model-00001-of-00002.safetensors",
240
- "transformer.h.29.mlp.fc2.weight": "model-00001-of-00002.safetensors",
241
- "transformer.h.3.ln.bias": "model-00001-of-00002.safetensors",
242
- "transformer.h.3.ln.weight": "model-00001-of-00002.safetensors",
243
- "transformer.h.3.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
244
- "transformer.h.3.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
245
- "transformer.h.3.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
246
- "transformer.h.3.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
247
- "transformer.h.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
248
- "transformer.h.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
249
- "transformer.h.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
250
- "transformer.h.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
251
- "transformer.h.30.ln.bias": "model-00001-of-00002.safetensors",
252
- "transformer.h.30.ln.weight": "model-00001-of-00002.safetensors",
253
- "transformer.h.30.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
254
- "transformer.h.30.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
255
- "transformer.h.30.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
256
- "transformer.h.30.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
257
- "transformer.h.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
258
- "transformer.h.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
259
- "transformer.h.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
260
- "transformer.h.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
261
- "transformer.h.31.ln.bias": "model-00002-of-00002.safetensors",
262
- "transformer.h.31.ln.weight": "model-00002-of-00002.safetensors",
263
- "transformer.h.31.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
264
- "transformer.h.31.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
265
- "transformer.h.31.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
266
- "transformer.h.31.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
267
- "transformer.h.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
268
- "transformer.h.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
269
- "transformer.h.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
270
- "transformer.h.31.mlp.fc2.weight": "model-00002-of-00002.safetensors",
271
- "transformer.h.4.ln.bias": "model-00001-of-00002.safetensors",
272
- "transformer.h.4.ln.weight": "model-00001-of-00002.safetensors",
273
- "transformer.h.4.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
274
- "transformer.h.4.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
275
- "transformer.h.4.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
276
- "transformer.h.4.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
277
- "transformer.h.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
278
- "transformer.h.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
279
- "transformer.h.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
280
- "transformer.h.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
281
- "transformer.h.5.ln.bias": "model-00001-of-00002.safetensors",
282
- "transformer.h.5.ln.weight": "model-00001-of-00002.safetensors",
283
- "transformer.h.5.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
284
- "transformer.h.5.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
285
- "transformer.h.5.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
286
- "transformer.h.5.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
287
- "transformer.h.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
288
- "transformer.h.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
289
- "transformer.h.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
290
- "transformer.h.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
291
- "transformer.h.6.ln.bias": "model-00001-of-00002.safetensors",
292
- "transformer.h.6.ln.weight": "model-00001-of-00002.safetensors",
293
- "transformer.h.6.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
294
- "transformer.h.6.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
295
- "transformer.h.6.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
296
- "transformer.h.6.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
297
- "transformer.h.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
298
- "transformer.h.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
299
- "transformer.h.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
300
- "transformer.h.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
301
- "transformer.h.7.ln.bias": "model-00001-of-00002.safetensors",
302
- "transformer.h.7.ln.weight": "model-00001-of-00002.safetensors",
303
- "transformer.h.7.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
304
- "transformer.h.7.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
305
- "transformer.h.7.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
306
- "transformer.h.7.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
307
- "transformer.h.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
308
- "transformer.h.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
309
- "transformer.h.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
310
- "transformer.h.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
311
- "transformer.h.8.ln.bias": "model-00001-of-00002.safetensors",
312
- "transformer.h.8.ln.weight": "model-00001-of-00002.safetensors",
313
- "transformer.h.8.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
314
- "transformer.h.8.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
315
- "transformer.h.8.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
316
- "transformer.h.8.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
317
- "transformer.h.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
318
- "transformer.h.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
319
- "transformer.h.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
320
- "transformer.h.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
321
- "transformer.h.9.ln.bias": "model-00001-of-00002.safetensors",
322
- "transformer.h.9.ln.weight": "model-00001-of-00002.safetensors",
323
- "transformer.h.9.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
324
- "transformer.h.9.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
325
- "transformer.h.9.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
326
- "transformer.h.9.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
327
- "transformer.h.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
328
- "transformer.h.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
329
- "transformer.h.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
330
- "transformer.h.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
331
- "transformer.mm_projector.0.bias": "model-00002-of-00002.safetensors",
332
- "transformer.mm_projector.0.weight": "model-00002-of-00002.safetensors",
333
- "transformer.mm_projector.2.bias": "model-00002-of-00002.safetensors",
334
- "transformer.mm_projector.2.weight": "model-00002-of-00002.safetensors",
335
- "transformer.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00002-of-00002.safetensors",
336
- "transformer.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00002-of-00002.safetensors",
337
- "transformer.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00002-of-00002.safetensors",
338
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00002-of-00002.safetensors",
339
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00002-of-00002.safetensors",
340
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00002-of-00002.safetensors",
341
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00002-of-00002.safetensors",
342
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00002-of-00002.safetensors",
343
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00002-of-00002.safetensors",
344
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00002-of-00002.safetensors",
345
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00002-of-00002.safetensors",
346
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
347
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
348
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
349
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
350
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
351
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
352
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
353
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
354
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00002-of-00002.safetensors",
355
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00002-of-00002.safetensors",
356
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00002-of-00002.safetensors",
357
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00002-of-00002.safetensors",
358
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00002-of-00002.safetensors",
359
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00002-of-00002.safetensors",
360
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00002-of-00002.safetensors",
361
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00002-of-00002.safetensors",
362
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
363
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
364
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
365
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
366
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
367
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
368
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
369
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
370
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00002-of-00002.safetensors",
371
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00002-of-00002.safetensors",
372
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00002-of-00002.safetensors",
373
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00002-of-00002.safetensors",
374
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00002-of-00002.safetensors",
375
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00002-of-00002.safetensors",
376
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00002-of-00002.safetensors",
377
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00002-of-00002.safetensors",
378
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
379
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
380
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
381
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
382
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
383
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
384
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
385
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
386
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00002-of-00002.safetensors",
387
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00002-of-00002.safetensors",
388
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00002-of-00002.safetensors",
389
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00002-of-00002.safetensors",
390
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00002-of-00002.safetensors",
391
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00002-of-00002.safetensors",
392
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00002-of-00002.safetensors",
393
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00002-of-00002.safetensors",
394
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
395
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
396
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
397
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
398
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
399
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
400
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
401
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
402
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00002-of-00002.safetensors",
403
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00002-of-00002.safetensors",
404
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00002-of-00002.safetensors",
405
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00002-of-00002.safetensors",
406
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00002-of-00002.safetensors",
407
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00002-of-00002.safetensors",
408
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00002-of-00002.safetensors",
409
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00002-of-00002.safetensors",
410
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
411
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
412
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
413
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
414
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
415
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
416
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
417
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
418
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00002-of-00002.safetensors",
419
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00002-of-00002.safetensors",
420
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00002-of-00002.safetensors",
421
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00002-of-00002.safetensors",
422
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00002-of-00002.safetensors",
423
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00002-of-00002.safetensors",
424
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00002-of-00002.safetensors",
425
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00002-of-00002.safetensors",
426
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
427
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
428
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
429
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
430
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
431
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
432
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
433
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
434
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00002-of-00002.safetensors",
435
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00002-of-00002.safetensors",
436
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00002-of-00002.safetensors",
437
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00002-of-00002.safetensors",
438
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00002-of-00002.safetensors",
439
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00002-of-00002.safetensors",
440
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00002-of-00002.safetensors",
441
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00002-of-00002.safetensors",
442
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
443
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
444
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
445
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
446
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
447
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
448
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
449
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
450
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00002-of-00002.safetensors",
451
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00002-of-00002.safetensors",
452
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00002-of-00002.safetensors",
453
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00002-of-00002.safetensors",
454
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00002-of-00002.safetensors",
455
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00002-of-00002.safetensors",
456
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00002-of-00002.safetensors",
457
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00002-of-00002.safetensors",
458
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
459
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
460
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
461
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
462
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
463
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
464
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
465
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
466
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00002-of-00002.safetensors",
467
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00002-of-00002.safetensors",
468
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00002-of-00002.safetensors",
469
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00002-of-00002.safetensors",
470
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00002-of-00002.safetensors",
471
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00002-of-00002.safetensors",
472
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00002-of-00002.safetensors",
473
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00002-of-00002.safetensors",
474
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
475
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
476
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
477
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
478
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
479
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
480
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
481
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
482
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00002-of-00002.safetensors",
483
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00002-of-00002.safetensors",
484
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00002-of-00002.safetensors",
485
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00002-of-00002.safetensors",
486
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00002-of-00002.safetensors",
487
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00002-of-00002.safetensors",
488
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00002-of-00002.safetensors",
489
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00002-of-00002.safetensors",
490
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
491
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
492
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
493
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
494
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
495
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
496
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
497
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
498
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00002-of-00002.safetensors",
499
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00002-of-00002.safetensors",
500
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00002-of-00002.safetensors",
501
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00002-of-00002.safetensors",
502
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00002-of-00002.safetensors",
503
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00002-of-00002.safetensors",
504
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00002-of-00002.safetensors",
505
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00002-of-00002.safetensors",
506
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
507
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
508
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
509
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
510
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
511
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
512
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
513
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
514
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00002-of-00002.safetensors",
515
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00002-of-00002.safetensors",
516
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00002-of-00002.safetensors",
517
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00002-of-00002.safetensors",
518
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00002-of-00002.safetensors",
519
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00002-of-00002.safetensors",
520
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00002-of-00002.safetensors",
521
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00002-of-00002.safetensors",
522
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
523
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
524
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
525
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
526
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
527
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
528
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
529
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
530
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00002-of-00002.safetensors",
531
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00002-of-00002.safetensors",
532
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00002-of-00002.safetensors",
533
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00002-of-00002.safetensors",
534
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00002-of-00002.safetensors",
535
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00002-of-00002.safetensors",
536
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00002-of-00002.safetensors",
537
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00002-of-00002.safetensors",
538
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
539
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
540
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
541
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
542
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
543
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
544
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
545
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
546
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00002-of-00002.safetensors",
547
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00002-of-00002.safetensors",
548
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00002-of-00002.safetensors",
549
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00002-of-00002.safetensors",
550
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00002-of-00002.safetensors",
551
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00002-of-00002.safetensors",
552
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00002-of-00002.safetensors",
553
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00002-of-00002.safetensors",
554
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
555
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
556
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
557
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
558
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
559
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
560
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
561
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
562
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00002-of-00002.safetensors",
563
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00002-of-00002.safetensors",
564
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00002-of-00002.safetensors",
565
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00002-of-00002.safetensors",
566
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00002-of-00002.safetensors",
567
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00002-of-00002.safetensors",
568
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00002-of-00002.safetensors",
569
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00002-of-00002.safetensors",
570
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
571
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
572
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
573
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
574
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
575
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
576
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
577
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
578
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00002-of-00002.safetensors",
579
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00002-of-00002.safetensors",
580
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00002-of-00002.safetensors",
581
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00002-of-00002.safetensors",
582
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00002-of-00002.safetensors",
583
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00002-of-00002.safetensors",
584
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00002-of-00002.safetensors",
585
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00002-of-00002.safetensors",
586
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
587
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
588
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
589
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
590
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
591
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
592
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
593
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
594
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00002-of-00002.safetensors",
595
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00002-of-00002.safetensors",
596
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00002-of-00002.safetensors",
597
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00002-of-00002.safetensors",
598
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00002-of-00002.safetensors",
599
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00002-of-00002.safetensors",
600
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00002-of-00002.safetensors",
601
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00002-of-00002.safetensors",
602
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
603
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
604
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
605
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
606
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
607
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
608
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
609
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
610
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00002-of-00002.safetensors",
611
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00002-of-00002.safetensors",
612
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00002-of-00002.safetensors",
613
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00002-of-00002.safetensors",
614
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00002-of-00002.safetensors",
615
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00002-of-00002.safetensors",
616
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00002-of-00002.safetensors",
617
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00002-of-00002.safetensors",
618
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
619
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
620
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
621
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
622
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
623
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
624
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
625
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
626
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00002-of-00002.safetensors",
627
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00002-of-00002.safetensors",
628
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00002-of-00002.safetensors",
629
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00002-of-00002.safetensors",
630
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00002-of-00002.safetensors",
631
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00002-of-00002.safetensors",
632
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00002-of-00002.safetensors",
633
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00002-of-00002.safetensors",
634
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
635
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
636
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
637
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
638
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
639
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
640
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
641
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
642
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00002-of-00002.safetensors",
643
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00002-of-00002.safetensors",
644
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00002-of-00002.safetensors",
645
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00002-of-00002.safetensors",
646
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00002-of-00002.safetensors",
647
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00002-of-00002.safetensors",
648
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00002-of-00002.safetensors",
649
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00002-of-00002.safetensors",
650
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
651
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
652
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
653
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
654
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
655
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
656
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
657
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
658
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00002-of-00002.safetensors",
659
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00002-of-00002.safetensors",
660
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00002-of-00002.safetensors",
661
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00002-of-00002.safetensors",
662
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00002-of-00002.safetensors",
663
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00002-of-00002.safetensors",
664
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00002-of-00002.safetensors",
665
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00002-of-00002.safetensors",
666
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
667
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
668
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
669
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
670
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
671
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
672
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
673
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
674
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00002-of-00002.safetensors",
675
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00002-of-00002.safetensors",
676
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00002-of-00002.safetensors",
677
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00002-of-00002.safetensors",
678
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00002-of-00002.safetensors",
679
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00002-of-00002.safetensors",
680
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00002-of-00002.safetensors",
681
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00002-of-00002.safetensors",
682
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
683
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
684
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
685
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
686
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
687
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
688
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
689
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
690
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00002-of-00002.safetensors",
691
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00002-of-00002.safetensors",
692
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00002-of-00002.safetensors",
693
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00002-of-00002.safetensors",
694
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00002-of-00002.safetensors",
695
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00002-of-00002.safetensors",
696
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00002-of-00002.safetensors",
697
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00002-of-00002.safetensors",
698
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
699
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
700
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
701
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
702
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
703
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
704
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
705
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
706
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00002-of-00002.safetensors",
707
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00002-of-00002.safetensors",
708
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00002-of-00002.safetensors",
709
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00002-of-00002.safetensors",
710
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00002-of-00002.safetensors",
711
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00002-of-00002.safetensors",
712
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00002-of-00002.safetensors",
713
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00002-of-00002.safetensors",
714
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
715
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
716
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
717
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
718
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
719
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
720
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
721
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
722
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00002-of-00002.safetensors",
723
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00002-of-00002.safetensors",
724
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00002-of-00002.safetensors",
725
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00002-of-00002.safetensors",
726
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00002-of-00002.safetensors",
727
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00002-of-00002.safetensors",
728
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00002-of-00002.safetensors",
729
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00002-of-00002.safetensors",
730
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
731
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
732
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
733
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
734
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
735
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
736
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
737
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
738
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00002-of-00002.safetensors",
739
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00002-of-00002.safetensors",
740
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00002-of-00002.safetensors",
741
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00002-of-00002.safetensors",
742
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00002-of-00002.safetensors",
743
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00002-of-00002.safetensors",
744
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00002-of-00002.safetensors",
745
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00002-of-00002.safetensors",
746
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
747
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
748
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
749
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
750
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
751
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
752
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
753
- "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
754
- "transformer.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00002-of-00002.safetensors",
755
- "transformer.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00002-of-00002.safetensors"
756
- }
757
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
requirements.txt CHANGED
@@ -1,7 +1,2 @@
1
- torch
2
- torchvision
3
- transformers
4
- numpy
5
- pillow
6
- accelerate
7
- einops
 
1
+ transformers==4.37.2
2
+ accelerate
 
 
 
 
 
tokenizer-dd360/added_tokens.json DELETED
@@ -1,42 +0,0 @@
1
- {
2
- "\t\t": 50294,
3
- "\t\t\t": 50293,
4
- "\t\t\t\t": 50292,
5
- "\t\t\t\t\t": 50291,
6
- "\t\t\t\t\t\t": 50290,
7
- "\t\t\t\t\t\t\t": 50289,
8
- "\t\t\t\t\t\t\t\t": 50288,
9
- "\t\t\t\t\t\t\t\t\t": 50287,
10
- " ": 50286,
11
- " ": 50285,
12
- " ": 50284,
13
- " ": 50283,
14
- " ": 50282,
15
- " ": 50281,
16
- " ": 50280,
17
- " ": 50279,
18
- " ": 50278,
19
- " ": 50277,
20
- " ": 50276,
21
- " ": 50275,
22
- " ": 50274,
23
- " ": 50273,
24
- " ": 50272,
25
- " ": 50271,
26
- " ": 50270,
27
- " ": 50269,
28
- " ": 50268,
29
- " ": 50267,
30
- " ": 50266,
31
- " ": 50265,
32
- " ": 50264,
33
- " ": 50263,
34
- " ": 50262,
35
- " ": 50261,
36
- " ": 50260,
37
- " ": 50259,
38
- " ": 50258,
39
- " ": 50257,
40
- "</s>": 50295,
41
- "<image>": 50296
42
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer-dd360/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
tokenizer-dd360/special_tokens_map.json DELETED
@@ -1,23 +0,0 @@
1
- {
2
- "bos_token": {
3
- "content": "<|endoftext|>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "<|endoftext|>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "unk_token": {
17
- "content": "<|endoftext|>",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- }
23
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer-dd360/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
tokenizer-dd360/tokenizer_config.json DELETED
@@ -1,342 +0,0 @@
1
- {
2
- "add_bos_token": false,
3
- "add_prefix_space": false,
4
- "added_tokens_decoder": {
5
- "50256": {
6
- "content": "<|endoftext|>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "50257": {
14
- "content": " ",
15
- "lstrip": false,
16
- "normalized": true,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": false
20
- },
21
- "50258": {
22
- "content": " ",
23
- "lstrip": false,
24
- "normalized": true,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": false
28
- },
29
- "50259": {
30
- "content": " ",
31
- "lstrip": false,
32
- "normalized": true,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": false
36
- },
37
- "50260": {
38
- "content": " ",
39
- "lstrip": false,
40
- "normalized": true,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": false
44
- },
45
- "50261": {
46
- "content": " ",
47
- "lstrip": false,
48
- "normalized": true,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": false
52
- },
53
- "50262": {
54
- "content": " ",
55
- "lstrip": false,
56
- "normalized": true,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": false
60
- },
61
- "50263": {
62
- "content": " ",
63
- "lstrip": false,
64
- "normalized": true,
65
- "rstrip": false,
66
- "single_word": false,
67
- "special": false
68
- },
69
- "50264": {
70
- "content": " ",
71
- "lstrip": false,
72
- "normalized": true,
73
- "rstrip": false,
74
- "single_word": false,
75
- "special": false
76
- },
77
- "50265": {
78
- "content": " ",
79
- "lstrip": false,
80
- "normalized": true,
81
- "rstrip": false,
82
- "single_word": false,
83
- "special": false
84
- },
85
- "50266": {
86
- "content": " ",
87
- "lstrip": false,
88
- "normalized": true,
89
- "rstrip": false,
90
- "single_word": false,
91
- "special": false
92
- },
93
- "50267": {
94
- "content": " ",
95
- "lstrip": false,
96
- "normalized": true,
97
- "rstrip": false,
98
- "single_word": false,
99
- "special": false
100
- },
101
- "50268": {
102
- "content": " ",
103
- "lstrip": false,
104
- "normalized": true,
105
- "rstrip": false,
106
- "single_word": false,
107
- "special": false
108
- },
109
- "50269": {
110
- "content": " ",
111
- "lstrip": false,
112
- "normalized": true,
113
- "rstrip": false,
114
- "single_word": false,
115
- "special": false
116
- },
117
- "50270": {
118
- "content": " ",
119
- "lstrip": false,
120
- "normalized": true,
121
- "rstrip": false,
122
- "single_word": false,
123
- "special": false
124
- },
125
- "50271": {
126
- "content": " ",
127
- "lstrip": false,
128
- "normalized": true,
129
- "rstrip": false,
130
- "single_word": false,
131
- "special": false
132
- },
133
- "50272": {
134
- "content": " ",
135
- "lstrip": false,
136
- "normalized": true,
137
- "rstrip": false,
138
- "single_word": false,
139
- "special": false
140
- },
141
- "50273": {
142
- "content": " ",
143
- "lstrip": false,
144
- "normalized": true,
145
- "rstrip": false,
146
- "single_word": false,
147
- "special": false
148
- },
149
- "50274": {
150
- "content": " ",
151
- "lstrip": false,
152
- "normalized": true,
153
- "rstrip": false,
154
- "single_word": false,
155
- "special": false
156
- },
157
- "50275": {
158
- "content": " ",
159
- "lstrip": false,
160
- "normalized": true,
161
- "rstrip": false,
162
- "single_word": false,
163
- "special": false
164
- },
165
- "50276": {
166
- "content": " ",
167
- "lstrip": false,
168
- "normalized": true,
169
- "rstrip": false,
170
- "single_word": false,
171
- "special": false
172
- },
173
- "50277": {
174
- "content": " ",
175
- "lstrip": false,
176
- "normalized": true,
177
- "rstrip": false,
178
- "single_word": false,
179
- "special": false
180
- },
181
- "50278": {
182
- "content": " ",
183
- "lstrip": false,
184
- "normalized": true,
185
- "rstrip": false,
186
- "single_word": false,
187
- "special": false
188
- },
189
- "50279": {
190
- "content": " ",
191
- "lstrip": false,
192
- "normalized": true,
193
- "rstrip": false,
194
- "single_word": false,
195
- "special": false
196
- },
197
- "50280": {
198
- "content": " ",
199
- "lstrip": false,
200
- "normalized": true,
201
- "rstrip": false,
202
- "single_word": false,
203
- "special": false
204
- },
205
- "50281": {
206
- "content": " ",
207
- "lstrip": false,
208
- "normalized": true,
209
- "rstrip": false,
210
- "single_word": false,
211
- "special": false
212
- },
213
- "50282": {
214
- "content": " ",
215
- "lstrip": false,
216
- "normalized": true,
217
- "rstrip": false,
218
- "single_word": false,
219
- "special": false
220
- },
221
- "50283": {
222
- "content": " ",
223
- "lstrip": false,
224
- "normalized": true,
225
- "rstrip": false,
226
- "single_word": false,
227
- "special": false
228
- },
229
- "50284": {
230
- "content": " ",
231
- "lstrip": false,
232
- "normalized": true,
233
- "rstrip": false,
234
- "single_word": false,
235
- "special": false
236
- },
237
- "50285": {
238
- "content": " ",
239
- "lstrip": false,
240
- "normalized": true,
241
- "rstrip": false,
242
- "single_word": false,
243
- "special": false
244
- },
245
- "50286": {
246
- "content": " ",
247
- "lstrip": false,
248
- "normalized": true,
249
- "rstrip": false,
250
- "single_word": false,
251
- "special": false
252
- },
253
- "50287": {
254
- "content": "\t\t\t\t\t\t\t\t\t",
255
- "lstrip": false,
256
- "normalized": true,
257
- "rstrip": false,
258
- "single_word": false,
259
- "special": false
260
- },
261
- "50288": {
262
- "content": "\t\t\t\t\t\t\t\t",
263
- "lstrip": false,
264
- "normalized": true,
265
- "rstrip": false,
266
- "single_word": false,
267
- "special": false
268
- },
269
- "50289": {
270
- "content": "\t\t\t\t\t\t\t",
271
- "lstrip": false,
272
- "normalized": true,
273
- "rstrip": false,
274
- "single_word": false,
275
- "special": false
276
- },
277
- "50290": {
278
- "content": "\t\t\t\t\t\t",
279
- "lstrip": false,
280
- "normalized": true,
281
- "rstrip": false,
282
- "single_word": false,
283
- "special": false
284
- },
285
- "50291": {
286
- "content": "\t\t\t\t\t",
287
- "lstrip": false,
288
- "normalized": true,
289
- "rstrip": false,
290
- "single_word": false,
291
- "special": false
292
- },
293
- "50292": {
294
- "content": "\t\t\t\t",
295
- "lstrip": false,
296
- "normalized": true,
297
- "rstrip": false,
298
- "single_word": false,
299
- "special": false
300
- },
301
- "50293": {
302
- "content": "\t\t\t",
303
- "lstrip": false,
304
- "normalized": true,
305
- "rstrip": false,
306
- "single_word": false,
307
- "special": false
308
- },
309
- "50294": {
310
- "content": "\t\t",
311
- "lstrip": false,
312
- "normalized": true,
313
- "rstrip": false,
314
- "single_word": false,
315
- "special": false
316
- },
317
- "50295": {
318
- "content": "</s>",
319
- "lstrip": false,
320
- "normalized": false,
321
- "rstrip": false,
322
- "single_word": false,
323
- "special": true
324
- },
325
- "50296": {
326
- "content": "<image>",
327
- "lstrip": false,
328
- "normalized": false,
329
- "rstrip": false,
330
- "single_word": false,
331
- "special": true
332
- }
333
- },
334
- "bos_token": "<|endoftext|>",
335
- "clean_up_tokenization_spaces": true,
336
- "eos_token": "<|endoftext|>",
337
- "errors": "replace",
338
- "model_max_length": 3072,
339
- "pad_token": null,
340
- "tokenizer_class": "CodeGenTokenizer",
341
- "unk_token": "<|endoftext|>"
342
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer-dd360/vocab.json DELETED
The diff for this file is too large to render. See raw diff