Hugging Face's logo

LanguageBind
/
MoE-LLaVA-Qwen-1.8B-4e

Text Generation
Transformers
PyTorch
moe_llava_qwen
custom_code
Inference Endpoints
Model card Files Community
2
LanguageBind commited on
Commit
e4532ec
•
1 Parent(s): b8501bc

Upload 8 files

Browse files
Files changed (8) hide show
  1. config.json +106 -0
  2. generation_config.json +15 -0
  3. model-00001-of-00002.safetensors +3 -0
  4. model-00002-of-00002.safetensors +3 -0
  5. model.safetensors.index.json +717 -0
  6. qwen.tiktoken +0 -0
  7. special_tokens_map.json +17 -0
  8. tokenizer_config.json +17 -0
config.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./checkpoints/llavaqwen-2b-other",
3
+ "architectures": [
4
+ "MoELLaVAQWenForCausalLM"
5
+ ],
6
+ "attn_dropout_prob": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "Qwen/Qwen-1_8B--configuration_qwen.QWenConfig",
9
+ "AutoModelForCausalLM": "Qwen/Qwen-1_8B--modeling_qwen.QWenLMHeadModel"
10
+ },
11
+ "bf16": true,
12
+ "emb_dropout_prob": 0.0,
13
+ "fp16": false,
14
+ "fp32": false,
15
+ "freeze_mm_mlp_adapter": false,
16
+ "hidden_size": 2048,
17
+ "image_aspect_ratio": "pad",
18
+ "image_projector_type": "mlp2x_gelu",
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 11008,
21
+ "kv_channels": 128,
22
+ "layer_norm_epsilon": 1e-06,
23
+ "max_position_embeddings": 8192,
24
+ "mm_hidden_size": 1024,
25
+ "mm_image_tower": "openai/clip-vit-large-patch14-336",
26
+ "mm_projector_lr": null,
27
+ "mm_use_im_patch_token": false,
28
+ "mm_use_im_start_end": false,
29
+ "mm_video_tower": null,
30
+ "mm_vision_select_feature": "patch",
31
+ "mm_vision_select_layer": -2,
32
+ "model_type": "moe_llava_qwen",
33
+ "moe": {
34
+ "capacity_factor": 1.0,
35
+ "ep_size": 1,
36
+ "eval_capacity_factor": 2.0,
37
+ "min_capacity": 0,
38
+ "moe_enable": true,
39
+ "moe_layers_idx": [
40
+ 0,
41
+ 2,
42
+ 4,
43
+ 6,
44
+ 8,
45
+ 10,
46
+ 12,
47
+ 14,
48
+ 16,
49
+ 18,
50
+ 20,
51
+ 22
52
+ ],
53
+ "moe_mode": "sparse",
54
+ "num_experts": [
55
+ 4,
56
+ 4,
57
+ 4,
58
+ 4,
59
+ 4,
60
+ 4,
61
+ 4,
62
+ 4,
63
+ 4,
64
+ 4,
65
+ 4,
66
+ 4
67
+ ],
68
+ "router_aux_loss_coef": 0.01,
69
+ "top_k_experts": 2,
70
+ "train_modules": [
71
+ "mlp.w1",
72
+ "mlp.w2",
73
+ "mlp.c_proj",
74
+ "wg"
75
+ ],
76
+ "use_residual": false
77
+ },
78
+ "no_bias": true,
79
+ "num_attention_heads": 16,
80
+ "num_hidden_layers": 24,
81
+ "onnx_safe": null,
82
+ "pad_token_id": 151646,
83
+ "rotary_emb_base": 10000,
84
+ "rotary_pct": 1.0,
85
+ "scale_attn_weights": true,
86
+ "seq_length": 8192,
87
+ "softmax_in_fp32": false,
88
+ "tie_word_embeddings": false,
89
+ "tokenizer_class": "QWenTokenizer",
90
+ "tokenizer_padding_side": "right",
91
+ "torch_dtype": "bfloat16",
92
+ "transformers_version": "4.36.2",
93
+ "tune_mm_mlp_adapter": false,
94
+ "use_cache": true,
95
+ "use_cache_kernel": false,
96
+ "use_cache_quantization": false,
97
+ "use_dynamic_ntk": true,
98
+ "use_flash_attn": true,
99
+ "use_logn_attn": true,
100
+ "use_mm_proj": true,
101
+ "video_global_proj": false,
102
+ "video_projector_type": "linear",
103
+ "video_spatial_proj": false,
104
+ "video_temproal_proj": false,
105
+ "vocab_size": 151936
106
+ }
generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chat_format": "raw",
3
+ "do_sample": true,
4
+ "eos_token_id": 151643,
5
+ "max_new_tokens": 512,
6
+ "pad_token_id": 151643,
7
+ "stop_words_ids": [
8
+ [
9
+ 151643
10
+ ]
11
+ ],
12
+ "top_k": 0,
13
+ "top_p": 0.8,
14
+ "transformers_version": "4.36.2"
15
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fd954df57f4f48b05d4915a1a50351029c3bfa1edb070ac8fa795c7ecd423ee
3
+ size 4979813608
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e60ca1f8a6edf0ee9be27809db241bbc5fd8cc3780d094189f87dc5c5c4b3fd4
3
+ size 1748543672
model.safetensors.index.json ADDED
@@ -0,0 +1,717 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6728253440
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "transformer.h.0.attn.c_attn.bias": "model-00001-of-00002.safetensors",
8
+ "transformer.h.0.attn.c_attn.weight": "model-00001-of-00002.safetensors",
9
+ "transformer.h.0.attn.c_proj.weight": "model-00001-of-00002.safetensors",
10
+ "transformer.h.0.ln_1.weight": "model-00001-of-00002.safetensors",
11
+ "transformer.h.0.ln_2.weight": "model-00001-of-00002.safetensors",
12
+ "transformer.h.0.mlp.deepspeed_moe.experts.deepspeed_experts.0.c_proj.weight": "model-00001-of-00002.safetensors",
13
+ "transformer.h.0.mlp.deepspeed_moe.experts.deepspeed_experts.0.w1.weight": "model-00001-of-00002.safetensors",
14
+ "transformer.h.0.mlp.deepspeed_moe.experts.deepspeed_experts.0.w2.weight": "model-00001-of-00002.safetensors",
15
+ "transformer.h.0.mlp.deepspeed_moe.experts.deepspeed_experts.1.c_proj.weight": "model-00001-of-00002.safetensors",
16
+ "transformer.h.0.mlp.deepspeed_moe.experts.deepspeed_experts.1.w1.weight": "model-00001-of-00002.safetensors",
17
+ "transformer.h.0.mlp.deepspeed_moe.experts.deepspeed_experts.1.w2.weight": "model-00001-of-00002.safetensors",
18
+ "transformer.h.0.mlp.deepspeed_moe.experts.deepspeed_experts.2.c_proj.weight": "model-00001-of-00002.safetensors",
19
+ "transformer.h.0.mlp.deepspeed_moe.experts.deepspeed_experts.2.w1.weight": "model-00001-of-00002.safetensors",
20
+ "transformer.h.0.mlp.deepspeed_moe.experts.deepspeed_experts.2.w2.weight": "model-00001-of-00002.safetensors",
21
+ "transformer.h.0.mlp.deepspeed_moe.experts.deepspeed_experts.3.c_proj.weight": "model-00001-of-00002.safetensors",
22
+ "transformer.h.0.mlp.deepspeed_moe.experts.deepspeed_experts.3.w1.weight": "model-00001-of-00002.safetensors",
23
+ "transformer.h.0.mlp.deepspeed_moe.experts.deepspeed_experts.3.w2.weight": "model-00001-of-00002.safetensors",
24
+ "transformer.h.0.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
25
+ "transformer.h.1.attn.c_attn.bias": "model-00001-of-00002.safetensors",
26
+ "transformer.h.1.attn.c_attn.weight": "model-00001-of-00002.safetensors",
27
+ "transformer.h.1.attn.c_proj.weight": "model-00001-of-00002.safetensors",
28
+ "transformer.h.1.ln_1.weight": "model-00001-of-00002.safetensors",
29
+ "transformer.h.1.ln_2.weight": "model-00001-of-00002.safetensors",
30
+ "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
31
+ "transformer.h.1.mlp.w1.weight": "model-00001-of-00002.safetensors",
32
+ "transformer.h.1.mlp.w2.weight": "model-00001-of-00002.safetensors",
33
+ "transformer.h.10.attn.c_attn.bias": "model-00001-of-00002.safetensors",
34
+ "transformer.h.10.attn.c_attn.weight": "model-00001-of-00002.safetensors",
35
+ "transformer.h.10.attn.c_proj.weight": "model-00001-of-00002.safetensors",
36
+ "transformer.h.10.ln_1.weight": "model-00001-of-00002.safetensors",
37
+ "transformer.h.10.ln_2.weight": "model-00001-of-00002.safetensors",
38
+ "transformer.h.10.mlp.deepspeed_moe.experts.deepspeed_experts.0.c_proj.weight": "model-00001-of-00002.safetensors",
39
+ "transformer.h.10.mlp.deepspeed_moe.experts.deepspeed_experts.0.w1.weight": "model-00001-of-00002.safetensors",
40
+ "transformer.h.10.mlp.deepspeed_moe.experts.deepspeed_experts.0.w2.weight": "model-00001-of-00002.safetensors",
41
+ "transformer.h.10.mlp.deepspeed_moe.experts.deepspeed_experts.1.c_proj.weight": "model-00001-of-00002.safetensors",
42
+ "transformer.h.10.mlp.deepspeed_moe.experts.deepspeed_experts.1.w1.weight": "model-00001-of-00002.safetensors",
43
+ "transformer.h.10.mlp.deepspeed_moe.experts.deepspeed_experts.1.w2.weight": "model-00001-of-00002.safetensors",
44
+ "transformer.h.10.mlp.deepspeed_moe.experts.deepspeed_experts.2.c_proj.weight": "model-00001-of-00002.safetensors",
45
+ "transformer.h.10.mlp.deepspeed_moe.experts.deepspeed_experts.2.w1.weight": "model-00001-of-00002.safetensors",
46
+ "transformer.h.10.mlp.deepspeed_moe.experts.deepspeed_experts.2.w2.weight": "model-00001-of-00002.safetensors",
47
+ "transformer.h.10.mlp.deepspeed_moe.experts.deepspeed_experts.3.c_proj.weight": "model-00001-of-00002.safetensors",
48
+ "transformer.h.10.mlp.deepspeed_moe.experts.deepspeed_experts.3.w1.weight": "model-00001-of-00002.safetensors",
49
+ "transformer.h.10.mlp.deepspeed_moe.experts.deepspeed_experts.3.w2.weight": "model-00001-of-00002.safetensors",
50
+ "transformer.h.10.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
51
+ "transformer.h.11.attn.c_attn.bias": "model-00001-of-00002.safetensors",
52
+ "transformer.h.11.attn.c_attn.weight": "model-00001-of-00002.safetensors",
53
+ "transformer.h.11.attn.c_proj.weight": "model-00001-of-00002.safetensors",
54
+ "transformer.h.11.ln_1.weight": "model-00001-of-00002.safetensors",
55
+ "transformer.h.11.ln_2.weight": "model-00001-of-00002.safetensors",
56
+ "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
57
+ "transformer.h.11.mlp.w1.weight": "model-00001-of-00002.safetensors",
58
+ "transformer.h.11.mlp.w2.weight": "model-00001-of-00002.safetensors",
59
+ "transformer.h.12.attn.c_attn.bias": "model-00001-of-00002.safetensors",
60
+ "transformer.h.12.attn.c_attn.weight": "model-00001-of-00002.safetensors",
61
+ "transformer.h.12.attn.c_proj.weight": "model-00001-of-00002.safetensors",
62
+ "transformer.h.12.ln_1.weight": "model-00001-of-00002.safetensors",
63
+ "transformer.h.12.ln_2.weight": "model-00001-of-00002.safetensors",
64
+ "transformer.h.12.mlp.deepspeed_moe.experts.deepspeed_experts.0.c_proj.weight": "model-00001-of-00002.safetensors",
65
+ "transformer.h.12.mlp.deepspeed_moe.experts.deepspeed_experts.0.w1.weight": "model-00001-of-00002.safetensors",
66
+ "transformer.h.12.mlp.deepspeed_moe.experts.deepspeed_experts.0.w2.weight": "model-00001-of-00002.safetensors",
67
+ "transformer.h.12.mlp.deepspeed_moe.experts.deepspeed_experts.1.c_proj.weight": "model-00001-of-00002.safetensors",
68
+ "transformer.h.12.mlp.deepspeed_moe.experts.deepspeed_experts.1.w1.weight": "model-00001-of-00002.safetensors",
69
+ "transformer.h.12.mlp.deepspeed_moe.experts.deepspeed_experts.1.w2.weight": "model-00001-of-00002.safetensors",
70
+ "transformer.h.12.mlp.deepspeed_moe.experts.deepspeed_experts.2.c_proj.weight": "model-00001-of-00002.safetensors",
71
+ "transformer.h.12.mlp.deepspeed_moe.experts.deepspeed_experts.2.w1.weight": "model-00001-of-00002.safetensors",
72
+ "transformer.h.12.mlp.deepspeed_moe.experts.deepspeed_experts.2.w2.weight": "model-00001-of-00002.safetensors",
73
+ "transformer.h.12.mlp.deepspeed_moe.experts.deepspeed_experts.3.c_proj.weight": "model-00001-of-00002.safetensors",
74
+ "transformer.h.12.mlp.deepspeed_moe.experts.deepspeed_experts.3.w1.weight": "model-00001-of-00002.safetensors",
75
+ "transformer.h.12.mlp.deepspeed_moe.experts.deepspeed_experts.3.w2.weight": "model-00001-of-00002.safetensors",
76
+ "transformer.h.12.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
77
+ "transformer.h.13.attn.c_attn.bias": "model-00001-of-00002.safetensors",
78
+ "transformer.h.13.attn.c_attn.weight": "model-00001-of-00002.safetensors",
79
+ "transformer.h.13.attn.c_proj.weight": "model-00001-of-00002.safetensors",
80
+ "transformer.h.13.ln_1.weight": "model-00001-of-00002.safetensors",
81
+ "transformer.h.13.ln_2.weight": "model-00001-of-00002.safetensors",
82
+ "transformer.h.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
83
+ "transformer.h.13.mlp.w1.weight": "model-00001-of-00002.safetensors",
84
+ "transformer.h.13.mlp.w2.weight": "model-00001-of-00002.safetensors",
85
+ "transformer.h.14.attn.c_attn.bias": "model-00001-of-00002.safetensors",
86
+ "transformer.h.14.attn.c_attn.weight": "model-00001-of-00002.safetensors",
87
+ "transformer.h.14.attn.c_proj.weight": "model-00001-of-00002.safetensors",
88
+ "transformer.h.14.ln_1.weight": "model-00001-of-00002.safetensors",
89
+ "transformer.h.14.ln_2.weight": "model-00001-of-00002.safetensors",
90
+ "transformer.h.14.mlp.deepspeed_moe.experts.deepspeed_experts.0.c_proj.weight": "model-00001-of-00002.safetensors",
91
+ "transformer.h.14.mlp.deepspeed_moe.experts.deepspeed_experts.0.w1.weight": "model-00001-of-00002.safetensors",
92
+ "transformer.h.14.mlp.deepspeed_moe.experts.deepspeed_experts.0.w2.weight": "model-00001-of-00002.safetensors",
93
+ "transformer.h.14.mlp.deepspeed_moe.experts.deepspeed_experts.1.c_proj.weight": "model-00001-of-00002.safetensors",
94
+ "transformer.h.14.mlp.deepspeed_moe.experts.deepspeed_experts.1.w1.weight": "model-00001-of-00002.safetensors",
95
+ "transformer.h.14.mlp.deepspeed_moe.experts.deepspeed_experts.1.w2.weight": "model-00001-of-00002.safetensors",
96
+ "transformer.h.14.mlp.deepspeed_moe.experts.deepspeed_experts.2.c_proj.weight": "model-00001-of-00002.safetensors",
97
+ "transformer.h.14.mlp.deepspeed_moe.experts.deepspeed_experts.2.w1.weight": "model-00001-of-00002.safetensors",
98
+ "transformer.h.14.mlp.deepspeed_moe.experts.deepspeed_experts.2.w2.weight": "model-00001-of-00002.safetensors",
99
+ "transformer.h.14.mlp.deepspeed_moe.experts.deepspeed_experts.3.c_proj.weight": "model-00001-of-00002.safetensors",
100
+ "transformer.h.14.mlp.deepspeed_moe.experts.deepspeed_experts.3.w1.weight": "model-00001-of-00002.safetensors",
101
+ "transformer.h.14.mlp.deepspeed_moe.experts.deepspeed_experts.3.w2.weight": "model-00001-of-00002.safetensors",
102
+ "transformer.h.14.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
103
+ "transformer.h.15.attn.c_attn.bias": "model-00001-of-00002.safetensors",
104
+ "transformer.h.15.attn.c_attn.weight": "model-00001-of-00002.safetensors",
105
+ "transformer.h.15.attn.c_proj.weight": "model-00001-of-00002.safetensors",
106
+ "transformer.h.15.ln_1.weight": "model-00001-of-00002.safetensors",
107
+ "transformer.h.15.ln_2.weight": "model-00001-of-00002.safetensors",
108
+ "transformer.h.15.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
109
+ "transformer.h.15.mlp.w1.weight": "model-00001-of-00002.safetensors",
110
+ "transformer.h.15.mlp.w2.weight": "model-00001-of-00002.safetensors",
111
+ "transformer.h.16.attn.c_attn.bias": "model-00001-of-00002.safetensors",
112
+ "transformer.h.16.attn.c_attn.weight": "model-00001-of-00002.safetensors",
113
+ "transformer.h.16.attn.c_proj.weight": "model-00001-of-00002.safetensors",
114
+ "transformer.h.16.ln_1.weight": "model-00001-of-00002.safetensors",
115
+ "transformer.h.16.ln_2.weight": "model-00001-of-00002.safetensors",
116
+ "transformer.h.16.mlp.deepspeed_moe.experts.deepspeed_experts.0.c_proj.weight": "model-00001-of-00002.safetensors",
117
+ "transformer.h.16.mlp.deepspeed_moe.experts.deepspeed_experts.0.w1.weight": "model-00001-of-00002.safetensors",
118
+ "transformer.h.16.mlp.deepspeed_moe.experts.deepspeed_experts.0.w2.weight": "model-00001-of-00002.safetensors",
119
+ "transformer.h.16.mlp.deepspeed_moe.experts.deepspeed_experts.1.c_proj.weight": "model-00001-of-00002.safetensors",
120
+ "transformer.h.16.mlp.deepspeed_moe.experts.deepspeed_experts.1.w1.weight": "model-00001-of-00002.safetensors",
121
+ "transformer.h.16.mlp.deepspeed_moe.experts.deepspeed_experts.1.w2.weight": "model-00001-of-00002.safetensors",
122
+ "transformer.h.16.mlp.deepspeed_moe.experts.deepspeed_experts.2.c_proj.weight": "model-00001-of-00002.safetensors",
123
+ "transformer.h.16.mlp.deepspeed_moe.experts.deepspeed_experts.2.w1.weight": "model-00001-of-00002.safetensors",
124
+ "transformer.h.16.mlp.deepspeed_moe.experts.deepspeed_experts.2.w2.weight": "model-00001-of-00002.safetensors",
125
+ "transformer.h.16.mlp.deepspeed_moe.experts.deepspeed_experts.3.c_proj.weight": "model-00001-of-00002.safetensors",
126
+ "transformer.h.16.mlp.deepspeed_moe.experts.deepspeed_experts.3.w1.weight": "model-00001-of-00002.safetensors",
127
+ "transformer.h.16.mlp.deepspeed_moe.experts.deepspeed_experts.3.w2.weight": "model-00001-of-00002.safetensors",
128
+ "transformer.h.16.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
129
+ "transformer.h.17.attn.c_attn.bias": "model-00001-of-00002.safetensors",
130
+ "transformer.h.17.attn.c_attn.weight": "model-00001-of-00002.safetensors",
131
+ "transformer.h.17.attn.c_proj.weight": "model-00001-of-00002.safetensors",
132
+ "transformer.h.17.ln_1.weight": "model-00001-of-00002.safetensors",
133
+ "transformer.h.17.ln_2.weight": "model-00001-of-00002.safetensors",
134
+ "transformer.h.17.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
135
+ "transformer.h.17.mlp.w1.weight": "model-00001-of-00002.safetensors",
136
+ "transformer.h.17.mlp.w2.weight": "model-00001-of-00002.safetensors",
137
+ "transformer.h.18.attn.c_attn.bias": "model-00001-of-00002.safetensors",
138
+ "transformer.h.18.attn.c_attn.weight": "model-00001-of-00002.safetensors",
139
+ "transformer.h.18.attn.c_proj.weight": "model-00001-of-00002.safetensors",
140
+ "transformer.h.18.ln_1.weight": "model-00001-of-00002.safetensors",
141
+ "transformer.h.18.ln_2.weight": "model-00001-of-00002.safetensors",
142
+ "transformer.h.18.mlp.deepspeed_moe.experts.deepspeed_experts.0.c_proj.weight": "model-00001-of-00002.safetensors",
143
+ "transformer.h.18.mlp.deepspeed_moe.experts.deepspeed_experts.0.w1.weight": "model-00001-of-00002.safetensors",
144
+ "transformer.h.18.mlp.deepspeed_moe.experts.deepspeed_experts.0.w2.weight": "model-00001-of-00002.safetensors",
145
+ "transformer.h.18.mlp.deepspeed_moe.experts.deepspeed_experts.1.c_proj.weight": "model-00001-of-00002.safetensors",
146
+ "transformer.h.18.mlp.deepspeed_moe.experts.deepspeed_experts.1.w1.weight": "model-00001-of-00002.safetensors",
147
+ "transformer.h.18.mlp.deepspeed_moe.experts.deepspeed_experts.1.w2.weight": "model-00001-of-00002.safetensors",
148
+ "transformer.h.18.mlp.deepspeed_moe.experts.deepspeed_experts.2.c_proj.weight": "model-00001-of-00002.safetensors",
149
+ "transformer.h.18.mlp.deepspeed_moe.experts.deepspeed_experts.2.w1.weight": "model-00001-of-00002.safetensors",
150
+ "transformer.h.18.mlp.deepspeed_moe.experts.deepspeed_experts.2.w2.weight": "model-00001-of-00002.safetensors",
151
+ "transformer.h.18.mlp.deepspeed_moe.experts.deepspeed_experts.3.c_proj.weight": "model-00001-of-00002.safetensors",
152
+ "transformer.h.18.mlp.deepspeed_moe.experts.deepspeed_experts.3.w1.weight": "model-00001-of-00002.safetensors",
153
+ "transformer.h.18.mlp.deepspeed_moe.experts.deepspeed_experts.3.w2.weight": "model-00001-of-00002.safetensors",
154
+ "transformer.h.18.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
155
+ "transformer.h.19.attn.c_attn.bias": "model-00001-of-00002.safetensors",
156
+ "transformer.h.19.attn.c_attn.weight": "model-00001-of-00002.safetensors",
157
+ "transformer.h.19.attn.c_proj.weight": "model-00001-of-00002.safetensors",
158
+ "transformer.h.19.ln_1.weight": "model-00001-of-00002.safetensors",
159
+ "transformer.h.19.ln_2.weight": "model-00001-of-00002.safetensors",
160
+ "transformer.h.19.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
161
+ "transformer.h.19.mlp.w1.weight": "model-00001-of-00002.safetensors",
162
+ "transformer.h.19.mlp.w2.weight": "model-00001-of-00002.safetensors",
163
+ "transformer.h.2.attn.c_attn.bias": "model-00001-of-00002.safetensors",
164
+ "transformer.h.2.attn.c_attn.weight": "model-00001-of-00002.safetensors",
165
+ "transformer.h.2.attn.c_proj.weight": "model-00001-of-00002.safetensors",
166
+ "transformer.h.2.ln_1.weight": "model-00001-of-00002.safetensors",
167
+ "transformer.h.2.ln_2.weight": "model-00001-of-00002.safetensors",
168
+ "transformer.h.2.mlp.deepspeed_moe.experts.deepspeed_experts.0.c_proj.weight": "model-00001-of-00002.safetensors",
169
+ "transformer.h.2.mlp.deepspeed_moe.experts.deepspeed_experts.0.w1.weight": "model-00001-of-00002.safetensors",
170
+ "transformer.h.2.mlp.deepspeed_moe.experts.deepspeed_experts.0.w2.weight": "model-00001-of-00002.safetensors",
171
+ "transformer.h.2.mlp.deepspeed_moe.experts.deepspeed_experts.1.c_proj.weight": "model-00001-of-00002.safetensors",
172
+ "transformer.h.2.mlp.deepspeed_moe.experts.deepspeed_experts.1.w1.weight": "model-00001-of-00002.safetensors",
173
+ "transformer.h.2.mlp.deepspeed_moe.experts.deepspeed_experts.1.w2.weight": "model-00001-of-00002.safetensors",
174
+ "transformer.h.2.mlp.deepspeed_moe.experts.deepspeed_experts.2.c_proj.weight": "model-00001-of-00002.safetensors",
175
+ "transformer.h.2.mlp.deepspeed_moe.experts.deepspeed_experts.2.w1.weight": "model-00001-of-00002.safetensors",
176
+ "transformer.h.2.mlp.deepspeed_moe.experts.deepspeed_experts.2.w2.weight": "model-00001-of-00002.safetensors",
177
+ "transformer.h.2.mlp.deepspeed_moe.experts.deepspeed_experts.3.c_proj.weight": "model-00001-of-00002.safetensors",
178
+ "transformer.h.2.mlp.deepspeed_moe.experts.deepspeed_experts.3.w1.weight": "model-00001-of-00002.safetensors",
179
+ "transformer.h.2.mlp.deepspeed_moe.experts.deepspeed_experts.3.w2.weight": "model-00001-of-00002.safetensors",
180
+ "transformer.h.2.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
181
+ "transformer.h.20.attn.c_attn.bias": "model-00001-of-00002.safetensors",
182
+ "transformer.h.20.attn.c_attn.weight": "model-00001-of-00002.safetensors",
183
+ "transformer.h.20.attn.c_proj.weight": "model-00001-of-00002.safetensors",
184
+ "transformer.h.20.ln_1.weight": "model-00001-of-00002.safetensors",
185
+ "transformer.h.20.ln_2.weight": "model-00001-of-00002.safetensors",
186
+ "transformer.h.20.mlp.deepspeed_moe.experts.deepspeed_experts.0.c_proj.weight": "model-00001-of-00002.safetensors",
187
+ "transformer.h.20.mlp.deepspeed_moe.experts.deepspeed_experts.0.w1.weight": "model-00001-of-00002.safetensors",
188
+ "transformer.h.20.mlp.deepspeed_moe.experts.deepspeed_experts.0.w2.weight": "model-00001-of-00002.safetensors",
189
+ "transformer.h.20.mlp.deepspeed_moe.experts.deepspeed_experts.1.c_proj.weight": "model-00001-of-00002.safetensors",
190
+ "transformer.h.20.mlp.deepspeed_moe.experts.deepspeed_experts.1.w1.weight": "model-00001-of-00002.safetensors",
191
+ "transformer.h.20.mlp.deepspeed_moe.experts.deepspeed_experts.1.w2.weight": "model-00001-of-00002.safetensors",
192
+ "transformer.h.20.mlp.deepspeed_moe.experts.deepspeed_experts.2.c_proj.weight": "model-00001-of-00002.safetensors",
193
+ "transformer.h.20.mlp.deepspeed_moe.experts.deepspeed_experts.2.w1.weight": "model-00001-of-00002.safetensors",
194
+ "transformer.h.20.mlp.deepspeed_moe.experts.deepspeed_experts.2.w2.weight": "model-00001-of-00002.safetensors",
195
+ "transformer.h.20.mlp.deepspeed_moe.experts.deepspeed_experts.3.c_proj.weight": "model-00001-of-00002.safetensors",
196
+ "transformer.h.20.mlp.deepspeed_moe.experts.deepspeed_experts.3.w1.weight": "model-00001-of-00002.safetensors",
197
+ "transformer.h.20.mlp.deepspeed_moe.experts.deepspeed_experts.3.w2.weight": "model-00001-of-00002.safetensors",
198
+ "transformer.h.20.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
199
+ "transformer.h.21.attn.c_attn.bias": "model-00002-of-00002.safetensors",
200
+ "transformer.h.21.attn.c_attn.weight": "model-00002-of-00002.safetensors",
201
+ "transformer.h.21.attn.c_proj.weight": "model-00002-of-00002.safetensors",
202
+ "transformer.h.21.ln_1.weight": "model-00001-of-00002.safetensors",
203
+ "transformer.h.21.ln_2.weight": "model-00002-of-00002.safetensors",
204
+ "transformer.h.21.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
205
+ "transformer.h.21.mlp.w1.weight": "model-00002-of-00002.safetensors",
206
+ "transformer.h.21.mlp.w2.weight": "model-00002-of-00002.safetensors",
207
+ "transformer.h.22.attn.c_attn.bias": "model-00002-of-00002.safetensors",
208
+ "transformer.h.22.attn.c_attn.weight": "model-00002-of-00002.safetensors",
209
+ "transformer.h.22.attn.c_proj.weight": "model-00002-of-00002.safetensors",
210
+ "transformer.h.22.ln_1.weight": "model-00002-of-00002.safetensors",
211
+ "transformer.h.22.ln_2.weight": "model-00002-of-00002.safetensors",
212
+ "transformer.h.22.mlp.deepspeed_moe.experts.deepspeed_experts.0.c_proj.weight": "model-00002-of-00002.safetensors",
213
+ "transformer.h.22.mlp.deepspeed_moe.experts.deepspeed_experts.0.w1.weight": "model-00002-of-00002.safetensors",
214
+ "transformer.h.22.mlp.deepspeed_moe.experts.deepspeed_experts.0.w2.weight": "model-00002-of-00002.safetensors",
215
+ "transformer.h.22.mlp.deepspeed_moe.experts.deepspeed_experts.1.c_proj.weight": "model-00002-of-00002.safetensors",
216
+ "transformer.h.22.mlp.deepspeed_moe.experts.deepspeed_experts.1.w1.weight": "model-00002-of-00002.safetensors",
217
+ "transformer.h.22.mlp.deepspeed_moe.experts.deepspeed_experts.1.w2.weight": "model-00002-of-00002.safetensors",
218
+ "transformer.h.22.mlp.deepspeed_moe.experts.deepspeed_experts.2.c_proj.weight": "model-00002-of-00002.safetensors",
219
+ "transformer.h.22.mlp.deepspeed_moe.experts.deepspeed_experts.2.w1.weight": "model-00002-of-00002.safetensors",
220
+ "transformer.h.22.mlp.deepspeed_moe.experts.deepspeed_experts.2.w2.weight": "model-00002-of-00002.safetensors",
221
+ "transformer.h.22.mlp.deepspeed_moe.experts.deepspeed_experts.3.c_proj.weight": "model-00002-of-00002.safetensors",
222
+ "transformer.h.22.mlp.deepspeed_moe.experts.deepspeed_experts.3.w1.weight": "model-00002-of-00002.safetensors",
223
+ "transformer.h.22.mlp.deepspeed_moe.experts.deepspeed_experts.3.w2.weight": "model-00002-of-00002.safetensors",
224
+ "transformer.h.22.mlp.deepspeed_moe.gate.wg.weight": "model-00002-of-00002.safetensors",
225
+ "transformer.h.23.attn.c_attn.bias": "model-00002-of-00002.safetensors",
226
+ "transformer.h.23.attn.c_attn.weight": "model-00002-of-00002.safetensors",
227
+ "transformer.h.23.attn.c_proj.weight": "model-00002-of-00002.safetensors",
228
+ "transformer.h.23.ln_1.weight": "model-00002-of-00002.safetensors",
229
+ "transformer.h.23.ln_2.weight": "model-00002-of-00002.safetensors",
230
+ "transformer.h.23.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
231
+ "transformer.h.23.mlp.w1.weight": "model-00002-of-00002.safetensors",
232
+ "transformer.h.23.mlp.w2.weight": "model-00002-of-00002.safetensors",
233
+ "transformer.h.3.attn.c_attn.bias": "model-00001-of-00002.safetensors",
234
+ "transformer.h.3.attn.c_attn.weight": "model-00001-of-00002.safetensors",
235
+ "transformer.h.3.attn.c_proj.weight": "model-00001-of-00002.safetensors",
236
+ "transformer.h.3.ln_1.weight": "model-00001-of-00002.safetensors",
237
+ "transformer.h.3.ln_2.weight": "model-00001-of-00002.safetensors",
238
+ "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
239
+ "transformer.h.3.mlp.w1.weight": "model-00001-of-00002.safetensors",
240
+ "transformer.h.3.mlp.w2.weight": "model-00001-of-00002.safetensors",
241
+ "transformer.h.4.attn.c_attn.bias": "model-00001-of-00002.safetensors",
242
+ "transformer.h.4.attn.c_attn.weight": "model-00001-of-00002.safetensors",
243
+ "transformer.h.4.attn.c_proj.weight": "model-00001-of-00002.safetensors",
244
+ "transformer.h.4.ln_1.weight": "model-00001-of-00002.safetensors",
245
+ "transformer.h.4.ln_2.weight": "model-00001-of-00002.safetensors",
246
+ "transformer.h.4.mlp.deepspeed_moe.experts.deepspeed_experts.0.c_proj.weight": "model-00001-of-00002.safetensors",
247
+ "transformer.h.4.mlp.deepspeed_moe.experts.deepspeed_experts.0.w1.weight": "model-00001-of-00002.safetensors",
248
+ "transformer.h.4.mlp.deepspeed_moe.experts.deepspeed_experts.0.w2.weight": "model-00001-of-00002.safetensors",
249
+ "transformer.h.4.mlp.deepspeed_moe.experts.deepspeed_experts.1.c_proj.weight": "model-00001-of-00002.safetensors",
250
+ "transformer.h.4.mlp.deepspeed_moe.experts.deepspeed_experts.1.w1.weight": "model-00001-of-00002.safetensors",
251
+ "transformer.h.4.mlp.deepspeed_moe.experts.deepspeed_experts.1.w2.weight": "model-00001-of-00002.safetensors",
252
+ "transformer.h.4.mlp.deepspeed_moe.experts.deepspeed_experts.2.c_proj.weight": "model-00001-of-00002.safetensors",
253
+ "transformer.h.4.mlp.deepspeed_moe.experts.deepspeed_experts.2.w1.weight": "model-00001-of-00002.safetensors",
254
+ "transformer.h.4.mlp.deepspeed_moe.experts.deepspeed_experts.2.w2.weight": "model-00001-of-00002.safetensors",
255
+ "transformer.h.4.mlp.deepspeed_moe.experts.deepspeed_experts.3.c_proj.weight": "model-00001-of-00002.safetensors",
256
+ "transformer.h.4.mlp.deepspeed_moe.experts.deepspeed_experts.3.w1.weight": "model-00001-of-00002.safetensors",
257
+ "transformer.h.4.mlp.deepspeed_moe.experts.deepspeed_experts.3.w2.weight": "model-00001-of-00002.safetensors",
258
+ "transformer.h.4.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
259
+ "transformer.h.5.attn.c_attn.bias": "model-00001-of-00002.safetensors",
260
+ "transformer.h.5.attn.c_attn.weight": "model-00001-of-00002.safetensors",
261
+ "transformer.h.5.attn.c_proj.weight": "model-00001-of-00002.safetensors",
262
+ "transformer.h.5.ln_1.weight": "model-00001-of-00002.safetensors",
263
+ "transformer.h.5.ln_2.weight": "model-00001-of-00002.safetensors",
264
+ "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
265
+ "transformer.h.5.mlp.w1.weight": "model-00001-of-00002.safetensors",
266
+ "transformer.h.5.mlp.w2.weight": "model-00001-of-00002.safetensors",
267
+ "transformer.h.6.attn.c_attn.bias": "model-00001-of-00002.safetensors",
268
+ "transformer.h.6.attn.c_attn.weight": "model-00001-of-00002.safetensors",
269
+ "transformer.h.6.attn.c_proj.weight": "model-00001-of-00002.safetensors",
270
+ "transformer.h.6.ln_1.weight": "model-00001-of-00002.safetensors",
271
+ "transformer.h.6.ln_2.weight": "model-00001-of-00002.safetensors",
272
+ "transformer.h.6.mlp.deepspeed_moe.experts.deepspeed_experts.0.c_proj.weight": "model-00001-of-00002.safetensors",
273
+ "transformer.h.6.mlp.deepspeed_moe.experts.deepspeed_experts.0.w1.weight": "model-00001-of-00002.safetensors",
274
+ "transformer.h.6.mlp.deepspeed_moe.experts.deepspeed_experts.0.w2.weight": "model-00001-of-00002.safetensors",
275
+ "transformer.h.6.mlp.deepspeed_moe.experts.deepspeed_experts.1.c_proj.weight": "model-00001-of-00002.safetensors",
276
+ "transformer.h.6.mlp.deepspeed_moe.experts.deepspeed_experts.1.w1.weight": "model-00001-of-00002.safetensors",
277
+ "transformer.h.6.mlp.deepspeed_moe.experts.deepspeed_experts.1.w2.weight": "model-00001-of-00002.safetensors",
278
+ "transformer.h.6.mlp.deepspeed_moe.experts.deepspeed_experts.2.c_proj.weight": "model-00001-of-00002.safetensors",
279
+ "transformer.h.6.mlp.deepspeed_moe.experts.deepspeed_experts.2.w1.weight": "model-00001-of-00002.safetensors",
280
+ "transformer.h.6.mlp.deepspeed_moe.experts.deepspeed_experts.2.w2.weight": "model-00001-of-00002.safetensors",
281
+ "transformer.h.6.mlp.deepspeed_moe.experts.deepspeed_experts.3.c_proj.weight": "model-00001-of-00002.safetensors",
282
+ "transformer.h.6.mlp.deepspeed_moe.experts.deepspeed_experts.3.w1.weight": "model-00001-of-00002.safetensors",
283
+ "transformer.h.6.mlp.deepspeed_moe.experts.deepspeed_experts.3.w2.weight": "model-00001-of-00002.safetensors",
284
+ "transformer.h.6.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
285
+ "transformer.h.7.attn.c_attn.bias": "model-00001-of-00002.safetensors",
286
+ "transformer.h.7.attn.c_attn.weight": "model-00001-of-00002.safetensors",
287
+ "transformer.h.7.attn.c_proj.weight": "model-00001-of-00002.safetensors",
288
+ "transformer.h.7.ln_1.weight": "model-00001-of-00002.safetensors",
289
+ "transformer.h.7.ln_2.weight": "model-00001-of-00002.safetensors",
290
+ "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
291
+ "transformer.h.7.mlp.w1.weight": "model-00001-of-00002.safetensors",
292
+ "transformer.h.7.mlp.w2.weight": "model-00001-of-00002.safetensors",
293
+ "transformer.h.8.attn.c_attn.bias": "model-00001-of-00002.safetensors",
294
+ "transformer.h.8.attn.c_attn.weight": "model-00001-of-00002.safetensors",
295
+ "transformer.h.8.attn.c_proj.weight": "model-00001-of-00002.safetensors",
296
+ "transformer.h.8.ln_1.weight": "model-00001-of-00002.safetensors",
297
+ "transformer.h.8.ln_2.weight": "model-00001-of-00002.safetensors",
298
+ "transformer.h.8.mlp.deepspeed_moe.experts.deepspeed_experts.0.c_proj.weight": "model-00001-of-00002.safetensors",
299
+ "transformer.h.8.mlp.deepspeed_moe.experts.deepspeed_experts.0.w1.weight": "model-00001-of-00002.safetensors",
300
+ "transformer.h.8.mlp.deepspeed_moe.experts.deepspeed_experts.0.w2.weight": "model-00001-of-00002.safetensors",
301
+ "transformer.h.8.mlp.deepspeed_moe.experts.deepspeed_experts.1.c_proj.weight": "model-00001-of-00002.safetensors",
302
+ "transformer.h.8.mlp.deepspeed_moe.experts.deepspeed_experts.1.w1.weight": "model-00001-of-00002.safetensors",
303
+ "transformer.h.8.mlp.deepspeed_moe.experts.deepspeed_experts.1.w2.weight": "model-00001-of-00002.safetensors",
304
+ "transformer.h.8.mlp.deepspeed_moe.experts.deepspeed_experts.2.c_proj.weight": "model-00001-of-00002.safetensors",
305
+ "transformer.h.8.mlp.deepspeed_moe.experts.deepspeed_experts.2.w1.weight": "model-00001-of-00002.safetensors",
306
+ "transformer.h.8.mlp.deepspeed_moe.experts.deepspeed_experts.2.w2.weight": "model-00001-of-00002.safetensors",
307
+ "transformer.h.8.mlp.deepspeed_moe.experts.deepspeed_experts.3.c_proj.weight": "model-00001-of-00002.safetensors",
308
+ "transformer.h.8.mlp.deepspeed_moe.experts.deepspeed_experts.3.w1.weight": "model-00001-of-00002.safetensors",
309
+ "transformer.h.8.mlp.deepspeed_moe.experts.deepspeed_experts.3.w2.weight": "model-00001-of-00002.safetensors",
310
+ "transformer.h.8.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
311
+ "transformer.h.9.attn.c_attn.bias": "model-00001-of-00002.safetensors",
312
+ "transformer.h.9.attn.c_attn.weight": "model-00001-of-00002.safetensors",
313
+ "transformer.h.9.attn.c_proj.weight": "model-00001-of-00002.safetensors",
314
+ "transformer.h.9.ln_1.weight": "model-00001-of-00002.safetensors",
315
+ "transformer.h.9.ln_2.weight": "model-00001-of-00002.safetensors",
316
+ "transformer.h.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
317
+ "transformer.h.9.mlp.w1.weight": "model-00001-of-00002.safetensors",
318
+ "transformer.h.9.mlp.w2.weight": "model-00001-of-00002.safetensors",
319
+ "transformer.image_tower.image_tower.vision_model.embeddings.class_embedding": "model-00002-of-00002.safetensors",
320
+ "transformer.image_tower.image_tower.vision_model.embeddings.patch_embedding.weight": "model-00002-of-00002.safetensors",
321
+ "transformer.image_tower.image_tower.vision_model.embeddings.position_embedding.weight": "model-00002-of-00002.safetensors",
322
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00002-of-00002.safetensors",
323
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00002-of-00002.safetensors",
324
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00002-of-00002.safetensors",
325
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00002-of-00002.safetensors",
326
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00002-of-00002.safetensors",
327
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00002-of-00002.safetensors",
328
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00002-of-00002.safetensors",
329
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00002-of-00002.safetensors",
330
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
331
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
332
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
333
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
334
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
335
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
336
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
337
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
338
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00002-of-00002.safetensors",
339
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00002-of-00002.safetensors",
340
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00002-of-00002.safetensors",
341
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00002-of-00002.safetensors",
342
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00002-of-00002.safetensors",
343
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00002-of-00002.safetensors",
344
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00002-of-00002.safetensors",
345
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00002-of-00002.safetensors",
346
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
347
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
348
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
349
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
350
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
351
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
352
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
353
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
354
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00002-of-00002.safetensors",
355
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00002-of-00002.safetensors",
356
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00002-of-00002.safetensors",
357
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00002-of-00002.safetensors",
358
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00002-of-00002.safetensors",
359
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00002-of-00002.safetensors",
360
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00002-of-00002.safetensors",
361
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00002-of-00002.safetensors",
362
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
363
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
364
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
365
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
366
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
367
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
368
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
369
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
370
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00002-of-00002.safetensors",
371
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00002-of-00002.safetensors",
372
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00002-of-00002.safetensors",
373
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00002-of-00002.safetensors",
374
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00002-of-00002.safetensors",
375
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00002-of-00002.safetensors",
376
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00002-of-00002.safetensors",
377
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00002-of-00002.safetensors",
378
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
379
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
380
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
381
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
382
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
383
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
384
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
385
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
386
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00002-of-00002.safetensors",
387
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00002-of-00002.safetensors",
388
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00002-of-00002.safetensors",
389
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00002-of-00002.safetensors",
390
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00002-of-00002.safetensors",
391
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00002-of-00002.safetensors",
392
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00002-of-00002.safetensors",
393
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00002-of-00002.safetensors",
394
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
395
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
396
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
397
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
398
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
399
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
400
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
401
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
402
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00002-of-00002.safetensors",
403
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00002-of-00002.safetensors",
404
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00002-of-00002.safetensors",
405
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00002-of-00002.safetensors",
406
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00002-of-00002.safetensors",
407
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00002-of-00002.safetensors",
408
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00002-of-00002.safetensors",
409
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00002-of-00002.safetensors",
410
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
411
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
412
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
413
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
414
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
415
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
416
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
417
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
418
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00002-of-00002.safetensors",
419
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00002-of-00002.safetensors",
420
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00002-of-00002.safetensors",
421
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00002-of-00002.safetensors",
422
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00002-of-00002.safetensors",
423
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00002-of-00002.safetensors",
424
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00002-of-00002.safetensors",
425
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00002-of-00002.safetensors",
426
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
427
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
428
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
429
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
430
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
431
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
432
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
433
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
434
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00002-of-00002.safetensors",
435
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00002-of-00002.safetensors",
436
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00002-of-00002.safetensors",
437
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00002-of-00002.safetensors",
438
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00002-of-00002.safetensors",
439
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00002-of-00002.safetensors",
440
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00002-of-00002.safetensors",
441
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00002-of-00002.safetensors",
442
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
443
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
444
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
445
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
446
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
447
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
448
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
449
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
450
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00002-of-00002.safetensors",
451
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00002-of-00002.safetensors",
452
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00002-of-00002.safetensors",
453
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00002-of-00002.safetensors",
454
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00002-of-00002.safetensors",
455
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00002-of-00002.safetensors",
456
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00002-of-00002.safetensors",
457
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00002-of-00002.safetensors",
458
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
459
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
460
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
461
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
462
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
463
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
464
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
465
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
466
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00002-of-00002.safetensors",
467
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00002-of-00002.safetensors",
468
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00002-of-00002.safetensors",
469
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00002-of-00002.safetensors",
470
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00002-of-00002.safetensors",
471
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00002-of-00002.safetensors",
472
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00002-of-00002.safetensors",
473
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00002-of-00002.safetensors",
474
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
475
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
476
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
477
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
478
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
479
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
480
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
481
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
482
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00002-of-00002.safetensors",
483
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00002-of-00002.safetensors",
484
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00002-of-00002.safetensors",
485
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00002-of-00002.safetensors",
486
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00002-of-00002.safetensors",
487
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00002-of-00002.safetensors",
488
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00002-of-00002.safetensors",
489
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00002-of-00002.safetensors",
490
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
491
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
492
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
493
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
494
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
495
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
496
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
497
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
498
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00002-of-00002.safetensors",
499
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00002-of-00002.safetensors",
500
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00002-of-00002.safetensors",
501
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00002-of-00002.safetensors",
502
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00002-of-00002.safetensors",
503
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00002-of-00002.safetensors",
504
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00002-of-00002.safetensors",
505
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00002-of-00002.safetensors",
506
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
507
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
508
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
509
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
510
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
511
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
512
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
513
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
514
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00002-of-00002.safetensors",
515
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00002-of-00002.safetensors",
516
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00002-of-00002.safetensors",
517
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00002-of-00002.safetensors",
518
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00002-of-00002.safetensors",
519
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00002-of-00002.safetensors",
520
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00002-of-00002.safetensors",
521
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00002-of-00002.safetensors",
522
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
523
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
524
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
525
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
526
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
527
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
528
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
529
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
530
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00002-of-00002.safetensors",
531
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00002-of-00002.safetensors",
532
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00002-of-00002.safetensors",
533
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00002-of-00002.safetensors",
534
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00002-of-00002.safetensors",
535
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00002-of-00002.safetensors",
536
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00002-of-00002.safetensors",
537
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00002-of-00002.safetensors",
538
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
539
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
540
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
541
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
542
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
543
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
544
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
545
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
546
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00002-of-00002.safetensors",
547
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00002-of-00002.safetensors",
548
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00002-of-00002.safetensors",
549
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00002-of-00002.safetensors",
550
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00002-of-00002.safetensors",
551
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00002-of-00002.safetensors",
552
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00002-of-00002.safetensors",
553
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00002-of-00002.safetensors",
554
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
555
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
556
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
557
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
558
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
559
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
560
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
561
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
562
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00002-of-00002.safetensors",
563
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00002-of-00002.safetensors",
564
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00002-of-00002.safetensors",
565
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00002-of-00002.safetensors",
566
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00002-of-00002.safetensors",
567
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00002-of-00002.safetensors",
568
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00002-of-00002.safetensors",
569
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00002-of-00002.safetensors",
570
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
571
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
572
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
573
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
574
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
575
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
576
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
577
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
578
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00002-of-00002.safetensors",
579
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00002-of-00002.safetensors",
580
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00002-of-00002.safetensors",
581
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00002-of-00002.safetensors",
582
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00002-of-00002.safetensors",
583
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00002-of-00002.safetensors",
584
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00002-of-00002.safetensors",
585
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00002-of-00002.safetensors",
586
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
587
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
588
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
589
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
590
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
591
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
592
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
593
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
594
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00002-of-00002.safetensors",
595
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00002-of-00002.safetensors",
596
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00002-of-00002.safetensors",
597
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00002-of-00002.safetensors",
598
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00002-of-00002.safetensors",
599
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00002-of-00002.safetensors",
600
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00002-of-00002.safetensors",
601
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00002-of-00002.safetensors",
602
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
603
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
604
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
605
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
606
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
607
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
608
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
609
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
610
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00002-of-00002.safetensors",
611
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00002-of-00002.safetensors",
612
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00002-of-00002.safetensors",
613
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00002-of-00002.safetensors",
614
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00002-of-00002.safetensors",
615
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00002-of-00002.safetensors",
616
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00002-of-00002.safetensors",
617
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00002-of-00002.safetensors",
618
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
619
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
620
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
621
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
622
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
623
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
624
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
625
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
626
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00002-of-00002.safetensors",
627
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00002-of-00002.safetensors",
628
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00002-of-00002.safetensors",
629
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00002-of-00002.safetensors",
630
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00002-of-00002.safetensors",
631
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00002-of-00002.safetensors",
632
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00002-of-00002.safetensors",
633
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00002-of-00002.safetensors",
634
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
635
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
636
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
637
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
638
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
639
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
640
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
641
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
642
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00002-of-00002.safetensors",
643
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00002-of-00002.safetensors",
644
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00002-of-00002.safetensors",
645
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00002-of-00002.safetensors",
646
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00002-of-00002.safetensors",
647
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00002-of-00002.safetensors",
648
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00002-of-00002.safetensors",
649
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00002-of-00002.safetensors",
650
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
651
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
652
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
653
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
654
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
655
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
656
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
657
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
658
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00002-of-00002.safetensors",
659
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00002-of-00002.safetensors",
660
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00002-of-00002.safetensors",
661
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00002-of-00002.safetensors",
662
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00002-of-00002.safetensors",
663
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00002-of-00002.safetensors",
664
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00002-of-00002.safetensors",
665
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00002-of-00002.safetensors",
666
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
667
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
668
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
669
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
670
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
671
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
672
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
673
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
674
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00002-of-00002.safetensors",
675
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00002-of-00002.safetensors",
676
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00002-of-00002.safetensors",
677
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00002-of-00002.safetensors",
678
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00002-of-00002.safetensors",
679
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00002-of-00002.safetensors",
680
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00002-of-00002.safetensors",
681
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00002-of-00002.safetensors",
682
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
683
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
684
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
685
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
686
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
687
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
688
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
689
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
690
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00002-of-00002.safetensors",
691
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00002-of-00002.safetensors",
692
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00002-of-00002.safetensors",
693
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00002-of-00002.safetensors",
694
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00002-of-00002.safetensors",
695
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00002-of-00002.safetensors",
696
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00002-of-00002.safetensors",
697
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00002-of-00002.safetensors",
698
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
699
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
700
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
701
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
702
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
703
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
704
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
705
+ "transformer.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
706
+ "transformer.image_tower.image_tower.vision_model.post_layernorm.bias": "model-00002-of-00002.safetensors",
707
+ "transformer.image_tower.image_tower.vision_model.post_layernorm.weight": "model-00002-of-00002.safetensors",
708
+ "transformer.image_tower.image_tower.vision_model.pre_layrnorm.bias": "model-00002-of-00002.safetensors",
709
+ "transformer.image_tower.image_tower.vision_model.pre_layrnorm.weight": "model-00002-of-00002.safetensors",
710
+ "transformer.ln_f.weight": "model-00002-of-00002.safetensors",
711
+ "transformer.mm_projector.image_spatial_proj.0.bias": "model-00002-of-00002.safetensors",
712
+ "transformer.mm_projector.image_spatial_proj.0.weight": "model-00002-of-00002.safetensors",
713
+ "transformer.mm_projector.image_spatial_proj.2.bias": "model-00002-of-00002.safetensors",
714
+ "transformer.mm_projector.image_spatial_proj.2.weight": "model-00002-of-00002.safetensors",
715
+ "transformer.wte.weight": "model-00001-of-00002.safetensors"
716
+ }
717
+ }
qwen.tiktoken ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": "<|extra_0|>",
10
+ "unk_token": {
11
+ "content": "<|extra_0|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {},
3
+ "auto_map": {
4
+ "AutoTokenizer": [
5
+ "Qwen/Qwen-1_8B--tokenization_qwen.QWenTokenizer",
6
+ null
7
+ ]
8
+ },
9
+ "clean_up_tokenization_spaces": true,
10
+ "eos_token": "<|endoftext|>",
11
+ "model_max_length": 2048,
12
+ "pad_token": "<|extra_0|>",
13
+ "padding_side": "right",
14
+ "tokenizer_class": "QWenTokenizer",
15
+ "unk_token": "<|extra_0|>",
16
+ "use_fast": false
17
+ }