Hugging Face's logo

LanguageBind
/
MoE-LLaVA-StableLM-1.6B-4e

Text Generation
Transformers
Safetensors
moe_llava_stablelm
custom_code
Inference Endpoints
Model card Files Community
1
LanguageBind commited on
Commit
52a4f7e
•
1 Parent(s): 0dc1480

Upload 8 files

Browse files
Files changed (8) hide show
  1. arcade100k.tiktoken +0 -0
  2. config.json +96 -0
  3. generation_config.json +6 -0
  4. model-00001-of-00002.safetensors +3 -0
  5. model-00002-of-00002.safetensors +3 -0
  6. model.safetensors.index.json +862 -0
  7. special_tokens_map.json +5 -0
  8. tokenizer_config.json +18 -0
arcade100k.tiktoken ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./checkpoints/llavastablelm-2b-other",
3
+ "architectures": [
4
+ "MoELLaVAStablelmForCausalLM"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "stabilityai/stablelm-2-1_6b--configuration_stablelm_epoch.StableLMEpochConfig",
8
+ "AutoModelForCausalLM": "stabilityai/stablelm-2-1_6b--modeling_stablelm_epoch.StableLMEpochForCausalLM"
9
+ },
10
+ "bos_token_id": 100257,
11
+ "eos_token_id": 100257,
12
+ "freeze_mm_mlp_adapter": false,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 2048,
15
+ "image_aspect_ratio": "pad",
16
+ "image_projector_type": "mlp2x_gelu",
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 5632,
19
+ "max_position_embeddings": 4096,
20
+ "mm_hidden_size": 1024,
21
+ "mm_image_tower": "openai/clip-vit-large-patch14-336",
22
+ "mm_projector_lr": null,
23
+ "mm_use_im_patch_token": false,
24
+ "mm_use_im_start_end": false,
25
+ "mm_video_tower": null,
26
+ "mm_vision_select_feature": "patch",
27
+ "mm_vision_select_layer": -2,
28
+ "model_type": "moe_llava_stablelm",
29
+ "moe": {
30
+ "capacity_factor": 1.0,
31
+ "ep_size": 1,
32
+ "eval_capacity_factor": 2.0,
33
+ "min_capacity": 0,
34
+ "moe_enable": true,
35
+ "moe_layers_idx": [
36
+ 0,
37
+ 2,
38
+ 4,
39
+ 6,
40
+ 8,
41
+ 10,
42
+ 12,
43
+ 14,
44
+ 16,
45
+ 18,
46
+ 20,
47
+ 22
48
+ ],
49
+ "moe_mode": "sparse",
50
+ "num_experts": [
51
+ 4,
52
+ 4,
53
+ 4,
54
+ 4,
55
+ 4,
56
+ 4,
57
+ 4,
58
+ 4,
59
+ 4,
60
+ 4,
61
+ 4,
62
+ 4
63
+ ],
64
+ "router_aux_loss_coef": 0.01,
65
+ "top_k_experts": 2,
66
+ "train_modules": [
67
+ "gate_proj",
68
+ "up_proj",
69
+ "down_proj",
70
+ "wg"
71
+ ],
72
+ "use_residual": false
73
+ },
74
+ "norm_eps": 1e-05,
75
+ "num_attention_heads": 32,
76
+ "num_heads": 32,
77
+ "num_hidden_layers": 24,
78
+ "num_key_value_heads": 32,
79
+ "pad_token_id": 100280,
80
+ "rope_pct": 0.25,
81
+ "rope_theta": 10000,
82
+ "rotary_scaling_factor": 1.0,
83
+ "tie_word_embeddings": false,
84
+ "tokenizer_padding_side": "right",
85
+ "torch_dtype": "bfloat16",
86
+ "transformers_version": "4.36.2",
87
+ "tune_mm_mlp_adapter": false,
88
+ "use_cache": true,
89
+ "use_mm_proj": true,
90
+ "use_qkv_bias": true,
91
+ "video_global_proj": false,
92
+ "video_projector_type": "linear",
93
+ "video_spatial_proj": false,
94
+ "video_temproal_proj": false,
95
+ "vocab_size": 100352
96
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 100257,
4
+ "eos_token_id": 100257,
5
+ "transformers_version": "4.36.2"
6
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2aa12427cef426a1d8d41be3301259de91820e36a32d8d838ab3954e9df1722a
3
+ size 4990018720
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:854a74f562c7815c30fbccf3c9aab44b75b47daf141f94d8c791679cf57bbb10
3
+ size 1410350160
model.safetensors.index.json ADDED
@@ -0,0 +1,862 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6400249856
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.image_tower.image_tower.vision_model.embeddings.class_embedding": "model-00002-of-00002.safetensors",
9
+ "model.image_tower.image_tower.vision_model.embeddings.patch_embedding.weight": "model-00002-of-00002.safetensors",
10
+ "model.image_tower.image_tower.vision_model.embeddings.position_embedding.weight": "model-00002-of-00002.safetensors",
11
+ "model.image_tower.image_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00002-of-00002.safetensors",
12
+ "model.image_tower.image_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00002-of-00002.safetensors",
13
+ "model.image_tower.image_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00002-of-00002.safetensors",
14
+ "model.image_tower.image_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00002-of-00002.safetensors",
15
+ "model.image_tower.image_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00002-of-00002.safetensors",
16
+ "model.image_tower.image_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00002-of-00002.safetensors",
17
+ "model.image_tower.image_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00002-of-00002.safetensors",
18
+ "model.image_tower.image_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00002-of-00002.safetensors",
19
+ "model.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
20
+ "model.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
21
+ "model.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
22
+ "model.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
23
+ "model.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
24
+ "model.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
25
+ "model.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
26
+ "model.image_tower.image_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
27
+ "model.image_tower.image_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00002-of-00002.safetensors",
28
+ "model.image_tower.image_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00002-of-00002.safetensors",
29
+ "model.image_tower.image_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00002-of-00002.safetensors",
30
+ "model.image_tower.image_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00002-of-00002.safetensors",
31
+ "model.image_tower.image_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00002-of-00002.safetensors",
32
+ "model.image_tower.image_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00002-of-00002.safetensors",
33
+ "model.image_tower.image_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00002-of-00002.safetensors",
34
+ "model.image_tower.image_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00002-of-00002.safetensors",
35
+ "model.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
36
+ "model.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
37
+ "model.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
38
+ "model.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
39
+ "model.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
40
+ "model.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
41
+ "model.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
42
+ "model.image_tower.image_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
43
+ "model.image_tower.image_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00002-of-00002.safetensors",
44
+ "model.image_tower.image_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00002-of-00002.safetensors",
45
+ "model.image_tower.image_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00002-of-00002.safetensors",
46
+ "model.image_tower.image_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00002-of-00002.safetensors",
47
+ "model.image_tower.image_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00002-of-00002.safetensors",
48
+ "model.image_tower.image_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00002-of-00002.safetensors",
49
+ "model.image_tower.image_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00002-of-00002.safetensors",
50
+ "model.image_tower.image_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00002-of-00002.safetensors",
51
+ "model.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
52
+ "model.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
53
+ "model.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
54
+ "model.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
55
+ "model.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
56
+ "model.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
57
+ "model.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
58
+ "model.image_tower.image_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
59
+ "model.image_tower.image_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00002-of-00002.safetensors",
60
+ "model.image_tower.image_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00002-of-00002.safetensors",
61
+ "model.image_tower.image_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00002-of-00002.safetensors",
62
+ "model.image_tower.image_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00002-of-00002.safetensors",
63
+ "model.image_tower.image_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00002-of-00002.safetensors",
64
+ "model.image_tower.image_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00002-of-00002.safetensors",
65
+ "model.image_tower.image_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00002-of-00002.safetensors",
66
+ "model.image_tower.image_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00002-of-00002.safetensors",
67
+ "model.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
68
+ "model.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
69
+ "model.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
70
+ "model.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
71
+ "model.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
72
+ "model.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
73
+ "model.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
74
+ "model.image_tower.image_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
75
+ "model.image_tower.image_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00002-of-00002.safetensors",
76
+ "model.image_tower.image_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00002-of-00002.safetensors",
77
+ "model.image_tower.image_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00002-of-00002.safetensors",
78
+ "model.image_tower.image_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00002-of-00002.safetensors",
79
+ "model.image_tower.image_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00002-of-00002.safetensors",
80
+ "model.image_tower.image_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00002-of-00002.safetensors",
81
+ "model.image_tower.image_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00002-of-00002.safetensors",
82
+ "model.image_tower.image_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00002-of-00002.safetensors",
83
+ "model.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
84
+ "model.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
85
+ "model.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
86
+ "model.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
87
+ "model.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
88
+ "model.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
89
+ "model.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
90
+ "model.image_tower.image_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
91
+ "model.image_tower.image_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00002-of-00002.safetensors",
92
+ "model.image_tower.image_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00002-of-00002.safetensors",
93
+ "model.image_tower.image_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00002-of-00002.safetensors",
94
+ "model.image_tower.image_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00002-of-00002.safetensors",
95
+ "model.image_tower.image_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00002-of-00002.safetensors",
96
+ "model.image_tower.image_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00002-of-00002.safetensors",
97
+ "model.image_tower.image_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00002-of-00002.safetensors",
98
+ "model.image_tower.image_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00002-of-00002.safetensors",
99
+ "model.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
100
+ "model.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
101
+ "model.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
102
+ "model.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
103
+ "model.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
104
+ "model.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
105
+ "model.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
106
+ "model.image_tower.image_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
107
+ "model.image_tower.image_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00002-of-00002.safetensors",
108
+ "model.image_tower.image_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00002-of-00002.safetensors",
109
+ "model.image_tower.image_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00002-of-00002.safetensors",
110
+ "model.image_tower.image_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00002-of-00002.safetensors",
111
+ "model.image_tower.image_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00002-of-00002.safetensors",
112
+ "model.image_tower.image_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00002-of-00002.safetensors",
113
+ "model.image_tower.image_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00002-of-00002.safetensors",
114
+ "model.image_tower.image_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00002-of-00002.safetensors",
115
+ "model.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
116
+ "model.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
117
+ "model.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
118
+ "model.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
119
+ "model.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
120
+ "model.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
121
+ "model.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
122
+ "model.image_tower.image_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
123
+ "model.image_tower.image_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00002-of-00002.safetensors",
124
+ "model.image_tower.image_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00002-of-00002.safetensors",
125
+ "model.image_tower.image_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00002-of-00002.safetensors",
126
+ "model.image_tower.image_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00002-of-00002.safetensors",
127
+ "model.image_tower.image_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00002-of-00002.safetensors",
128
+ "model.image_tower.image_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00002-of-00002.safetensors",
129
+ "model.image_tower.image_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00002-of-00002.safetensors",
130
+ "model.image_tower.image_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00002-of-00002.safetensors",
131
+ "model.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
132
+ "model.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
133
+ "model.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
134
+ "model.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
135
+ "model.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
136
+ "model.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
137
+ "model.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
138
+ "model.image_tower.image_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
139
+ "model.image_tower.image_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00002-of-00002.safetensors",
140
+ "model.image_tower.image_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00002-of-00002.safetensors",
141
+ "model.image_tower.image_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00002-of-00002.safetensors",
142
+ "model.image_tower.image_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00002-of-00002.safetensors",
143
+ "model.image_tower.image_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00002-of-00002.safetensors",
144
+ "model.image_tower.image_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00002-of-00002.safetensors",
145
+ "model.image_tower.image_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00002-of-00002.safetensors",
146
+ "model.image_tower.image_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00002-of-00002.safetensors",
147
+ "model.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
148
+ "model.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
149
+ "model.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
150
+ "model.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
151
+ "model.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
152
+ "model.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
153
+ "model.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
154
+ "model.image_tower.image_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
155
+ "model.image_tower.image_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00002-of-00002.safetensors",
156
+ "model.image_tower.image_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00002-of-00002.safetensors",
157
+ "model.image_tower.image_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00002-of-00002.safetensors",
158
+ "model.image_tower.image_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00002-of-00002.safetensors",
159
+ "model.image_tower.image_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00002-of-00002.safetensors",
160
+ "model.image_tower.image_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00002-of-00002.safetensors",
161
+ "model.image_tower.image_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00002-of-00002.safetensors",
162
+ "model.image_tower.image_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00002-of-00002.safetensors",
163
+ "model.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
164
+ "model.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
165
+ "model.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
166
+ "model.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
167
+ "model.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
168
+ "model.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
169
+ "model.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
170
+ "model.image_tower.image_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
171
+ "model.image_tower.image_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00002-of-00002.safetensors",
172
+ "model.image_tower.image_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00002-of-00002.safetensors",
173
+ "model.image_tower.image_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00002-of-00002.safetensors",
174
+ "model.image_tower.image_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00002-of-00002.safetensors",
175
+ "model.image_tower.image_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00002-of-00002.safetensors",
176
+ "model.image_tower.image_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00002-of-00002.safetensors",
177
+ "model.image_tower.image_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00002-of-00002.safetensors",
178
+ "model.image_tower.image_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00002-of-00002.safetensors",
179
+ "model.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
180
+ "model.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
181
+ "model.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
182
+ "model.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
183
+ "model.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
184
+ "model.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
185
+ "model.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
186
+ "model.image_tower.image_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.image_tower.image_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00002-of-00002.safetensors",
188
+ "model.image_tower.image_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00002-of-00002.safetensors",
189
+ "model.image_tower.image_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00002-of-00002.safetensors",
190
+ "model.image_tower.image_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00002-of-00002.safetensors",
191
+ "model.image_tower.image_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00002-of-00002.safetensors",
192
+ "model.image_tower.image_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00002-of-00002.safetensors",
193
+ "model.image_tower.image_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00002-of-00002.safetensors",
194
+ "model.image_tower.image_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00002-of-00002.safetensors",
195
+ "model.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
196
+ "model.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
197
+ "model.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
198
+ "model.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
199
+ "model.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
200
+ "model.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
201
+ "model.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
202
+ "model.image_tower.image_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
203
+ "model.image_tower.image_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00002-of-00002.safetensors",
204
+ "model.image_tower.image_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00002-of-00002.safetensors",
205
+ "model.image_tower.image_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00002-of-00002.safetensors",
206
+ "model.image_tower.image_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00002-of-00002.safetensors",
207
+ "model.image_tower.image_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00002-of-00002.safetensors",
208
+ "model.image_tower.image_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00002-of-00002.safetensors",
209
+ "model.image_tower.image_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00002-of-00002.safetensors",
210
+ "model.image_tower.image_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00002-of-00002.safetensors",
211
+ "model.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
212
+ "model.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
213
+ "model.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
214
+ "model.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
215
+ "model.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
216
+ "model.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
217
+ "model.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
218
+ "model.image_tower.image_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
219
+ "model.image_tower.image_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00002-of-00002.safetensors",
220
+ "model.image_tower.image_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00002-of-00002.safetensors",
221
+ "model.image_tower.image_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00002-of-00002.safetensors",
222
+ "model.image_tower.image_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00002-of-00002.safetensors",
223
+ "model.image_tower.image_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00002-of-00002.safetensors",
224
+ "model.image_tower.image_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00002-of-00002.safetensors",
225
+ "model.image_tower.image_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00002-of-00002.safetensors",
226
+ "model.image_tower.image_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00002-of-00002.safetensors",
227
+ "model.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
228
+ "model.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
229
+ "model.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
230
+ "model.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
231
+ "model.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
232
+ "model.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
233
+ "model.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
234
+ "model.image_tower.image_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
235
+ "model.image_tower.image_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00002-of-00002.safetensors",
236
+ "model.image_tower.image_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00002-of-00002.safetensors",
237
+ "model.image_tower.image_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00002-of-00002.safetensors",
238
+ "model.image_tower.image_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00002-of-00002.safetensors",
239
+ "model.image_tower.image_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00002-of-00002.safetensors",
240
+ "model.image_tower.image_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00002-of-00002.safetensors",
241
+ "model.image_tower.image_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00002-of-00002.safetensors",
242
+ "model.image_tower.image_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00002-of-00002.safetensors",
243
+ "model.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
244
+ "model.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
245
+ "model.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
246
+ "model.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
247
+ "model.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
248
+ "model.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
249
+ "model.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
250
+ "model.image_tower.image_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
251
+ "model.image_tower.image_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00002-of-00002.safetensors",
252
+ "model.image_tower.image_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00002-of-00002.safetensors",
253
+ "model.image_tower.image_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00002-of-00002.safetensors",
254
+ "model.image_tower.image_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00002-of-00002.safetensors",
255
+ "model.image_tower.image_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00002-of-00002.safetensors",
256
+ "model.image_tower.image_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00002-of-00002.safetensors",
257
+ "model.image_tower.image_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00002-of-00002.safetensors",
258
+ "model.image_tower.image_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00002-of-00002.safetensors",
259
+ "model.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
260
+ "model.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
261
+ "model.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
262
+ "model.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
263
+ "model.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
264
+ "model.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
265
+ "model.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
266
+ "model.image_tower.image_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
267
+ "model.image_tower.image_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00002-of-00002.safetensors",
268
+ "model.image_tower.image_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00002-of-00002.safetensors",
269
+ "model.image_tower.image_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00002-of-00002.safetensors",
270
+ "model.image_tower.image_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00002-of-00002.safetensors",
271
+ "model.image_tower.image_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00002-of-00002.safetensors",
272
+ "model.image_tower.image_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00002-of-00002.safetensors",
273
+ "model.image_tower.image_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00002-of-00002.safetensors",
274
+ "model.image_tower.image_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00002-of-00002.safetensors",
275
+ "model.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
276
+ "model.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
277
+ "model.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
278
+ "model.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
279
+ "model.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
280
+ "model.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
281
+ "model.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
282
+ "model.image_tower.image_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
283
+ "model.image_tower.image_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00002-of-00002.safetensors",
284
+ "model.image_tower.image_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00002-of-00002.safetensors",
285
+ "model.image_tower.image_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00002-of-00002.safetensors",
286
+ "model.image_tower.image_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00002-of-00002.safetensors",
287
+ "model.image_tower.image_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00002-of-00002.safetensors",
288
+ "model.image_tower.image_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00002-of-00002.safetensors",
289
+ "model.image_tower.image_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00002-of-00002.safetensors",
290
+ "model.image_tower.image_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00002-of-00002.safetensors",
291
+ "model.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
292
+ "model.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
293
+ "model.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
294
+ "model.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
295
+ "model.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
296
+ "model.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
297
+ "model.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
298
+ "model.image_tower.image_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
299
+ "model.image_tower.image_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00002-of-00002.safetensors",
300
+ "model.image_tower.image_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00002-of-00002.safetensors",
301
+ "model.image_tower.image_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00002-of-00002.safetensors",
302
+ "model.image_tower.image_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00002-of-00002.safetensors",
303
+ "model.image_tower.image_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00002-of-00002.safetensors",
304
+ "model.image_tower.image_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00002-of-00002.safetensors",
305
+ "model.image_tower.image_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00002-of-00002.safetensors",
306
+ "model.image_tower.image_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00002-of-00002.safetensors",
307
+ "model.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
308
+ "model.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
309
+ "model.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
310
+ "model.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
311
+ "model.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
312
+ "model.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
313
+ "model.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
314
+ "model.image_tower.image_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
315
+ "model.image_tower.image_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00002-of-00002.safetensors",
316
+ "model.image_tower.image_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00002-of-00002.safetensors",
317
+ "model.image_tower.image_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00002-of-00002.safetensors",
318
+ "model.image_tower.image_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00002-of-00002.safetensors",
319
+ "model.image_tower.image_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00002-of-00002.safetensors",
320
+ "model.image_tower.image_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00002-of-00002.safetensors",
321
+ "model.image_tower.image_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00002-of-00002.safetensors",
322
+ "model.image_tower.image_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00002-of-00002.safetensors",
323
+ "model.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
324
+ "model.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
325
+ "model.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
326
+ "model.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
327
+ "model.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
328
+ "model.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
329
+ "model.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
330
+ "model.image_tower.image_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
331
+ "model.image_tower.image_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00002-of-00002.safetensors",
332
+ "model.image_tower.image_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00002-of-00002.safetensors",
333
+ "model.image_tower.image_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00002-of-00002.safetensors",
334
+ "model.image_tower.image_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00002-of-00002.safetensors",
335
+ "model.image_tower.image_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00002-of-00002.safetensors",
336
+ "model.image_tower.image_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00002-of-00002.safetensors",
337
+ "model.image_tower.image_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00002-of-00002.safetensors",
338
+ "model.image_tower.image_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00002-of-00002.safetensors",
339
+ "model.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
340
+ "model.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
341
+ "model.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
342
+ "model.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
343
+ "model.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
344
+ "model.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
345
+ "model.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
346
+ "model.image_tower.image_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
347
+ "model.image_tower.image_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00002-of-00002.safetensors",
348
+ "model.image_tower.image_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00002-of-00002.safetensors",
349
+ "model.image_tower.image_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00002-of-00002.safetensors",
350
+ "model.image_tower.image_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00002-of-00002.safetensors",
351
+ "model.image_tower.image_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00002-of-00002.safetensors",
352
+ "model.image_tower.image_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00002-of-00002.safetensors",
353
+ "model.image_tower.image_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00002-of-00002.safetensors",
354
+ "model.image_tower.image_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00002-of-00002.safetensors",
355
+ "model.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
356
+ "model.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
357
+ "model.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
358
+ "model.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
359
+ "model.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
360
+ "model.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
361
+ "model.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
362
+ "model.image_tower.image_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
363
+ "model.image_tower.image_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00002-of-00002.safetensors",
364
+ "model.image_tower.image_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00002-of-00002.safetensors",
365
+ "model.image_tower.image_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00002-of-00002.safetensors",
366
+ "model.image_tower.image_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00002-of-00002.safetensors",
367
+ "model.image_tower.image_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00002-of-00002.safetensors",
368
+ "model.image_tower.image_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00002-of-00002.safetensors",
369
+ "model.image_tower.image_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00002-of-00002.safetensors",
370
+ "model.image_tower.image_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00002-of-00002.safetensors",
371
+ "model.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
372
+ "model.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
373
+ "model.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
374
+ "model.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
375
+ "model.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
376
+ "model.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
377
+ "model.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
378
+ "model.image_tower.image_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
379
+ "model.image_tower.image_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00002-of-00002.safetensors",
380
+ "model.image_tower.image_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00002-of-00002.safetensors",
381
+ "model.image_tower.image_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00002-of-00002.safetensors",
382
+ "model.image_tower.image_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00002-of-00002.safetensors",
383
+ "model.image_tower.image_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00002-of-00002.safetensors",
384
+ "model.image_tower.image_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00002-of-00002.safetensors",
385
+ "model.image_tower.image_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00002-of-00002.safetensors",
386
+ "model.image_tower.image_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00002-of-00002.safetensors",
387
+ "model.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
388
+ "model.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
389
+ "model.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
390
+ "model.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
391
+ "model.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
392
+ "model.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
393
+ "model.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
394
+ "model.image_tower.image_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
395
+ "model.image_tower.image_tower.vision_model.post_layernorm.bias": "model-00002-of-00002.safetensors",
396
+ "model.image_tower.image_tower.vision_model.post_layernorm.weight": "model-00002-of-00002.safetensors",
397
+ "model.image_tower.image_tower.vision_model.pre_layrnorm.bias": "model-00002-of-00002.safetensors",
398
+ "model.image_tower.image_tower.vision_model.pre_layrnorm.weight": "model-00002-of-00002.safetensors",
399
+ "model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
400
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
401
+ "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
402
+ "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
403
+ "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
404
+ "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
405
+ "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
406
+ "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
407
+ "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
408
+ "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
409
+ "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
410
+ "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
411
+ "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
412
+ "model.layers.0.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
413
+ "model.layers.0.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
414
+ "model.layers.0.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
415
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
416
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
417
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
418
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
419
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
420
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
421
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
422
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
423
+ "model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
424
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
425
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
426
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
427
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
428
+ "model.layers.1.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
429
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
430
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
431
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
432
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
433
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
434
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
435
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
436
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
437
+ "model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
438
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
439
+ "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
440
+ "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
441
+ "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
442
+ "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
443
+ "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
444
+ "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
445
+ "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
446
+ "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
447
+ "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
448
+ "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
449
+ "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
450
+ "model.layers.10.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
451
+ "model.layers.10.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
452
+ "model.layers.10.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
453
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
454
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
455
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
456
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
457
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
458
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
459
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
460
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
461
+ "model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
462
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
463
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
464
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
465
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
466
+ "model.layers.11.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
467
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
468
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
469
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
470
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
471
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
472
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
473
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
474
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
475
+ "model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
476
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
477
+ "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
478
+ "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
479
+ "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
480
+ "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
481
+ "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
482
+ "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
483
+ "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
484
+ "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
485
+ "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
486
+ "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
487
+ "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
488
+ "model.layers.12.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
489
+ "model.layers.12.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
490
+ "model.layers.12.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
491
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
492
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
493
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
494
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
495
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
496
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
497
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
498
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
499
+ "model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
500
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
501
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
502
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
503
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
504
+ "model.layers.13.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
505
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
506
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
507
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
508
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
509
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
510
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
511
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
512
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
513
+ "model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
514
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
515
+ "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
516
+ "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
517
+ "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
518
+ "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
519
+ "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
520
+ "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
521
+ "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
522
+ "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
523
+ "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
524
+ "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
525
+ "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
526
+ "model.layers.14.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
527
+ "model.layers.14.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
528
+ "model.layers.14.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
529
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
530
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
531
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
532
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
533
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
534
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
535
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
536
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
537
+ "model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
538
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
539
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
540
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
541
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
542
+ "model.layers.15.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
543
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
544
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
545
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
546
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
547
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
548
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
549
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
550
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
551
+ "model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
552
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
553
+ "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
554
+ "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
555
+ "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
556
+ "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
557
+ "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
558
+ "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
559
+ "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
560
+ "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
561
+ "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
562
+ "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
563
+ "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
564
+ "model.layers.16.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
565
+ "model.layers.16.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
566
+ "model.layers.16.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
567
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
568
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
569
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
570
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
571
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
572
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
573
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
574
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
575
+ "model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
576
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
577
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
578
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
579
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
580
+ "model.layers.17.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
581
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
582
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
583
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
584
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
585
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
586
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
587
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
588
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
589
+ "model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
590
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
591
+ "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
592
+ "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
593
+ "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
594
+ "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
595
+ "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
596
+ "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
597
+ "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
598
+ "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
599
+ "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
600
+ "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
601
+ "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
602
+ "model.layers.18.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
603
+ "model.layers.18.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
604
+ "model.layers.18.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
605
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
606
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
607
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
608
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
609
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
610
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
611
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
612
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
613
+ "model.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
614
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
615
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
616
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
617
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
618
+ "model.layers.19.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
619
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
620
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
621
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
622
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
623
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
624
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
625
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
626
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
627
+ "model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
628
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
629
+ "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
630
+ "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
631
+ "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
632
+ "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
633
+ "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
634
+ "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
635
+ "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
636
+ "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
637
+ "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
638
+ "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
639
+ "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
640
+ "model.layers.2.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
641
+ "model.layers.2.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
642
+ "model.layers.2.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
643
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
644
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
645
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
646
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
647
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
648
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
649
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
650
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
651
+ "model.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
652
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
653
+ "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
654
+ "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
655
+ "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
656
+ "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
657
+ "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
658
+ "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
659
+ "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
660
+ "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
661
+ "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
662
+ "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
663
+ "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
664
+ "model.layers.20.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
665
+ "model.layers.20.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
666
+ "model.layers.20.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
667
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
668
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
669
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
670
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
671
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
672
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
673
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
674
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
675
+ "model.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
676
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
677
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
678
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
679
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
680
+ "model.layers.21.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
681
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
682
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
683
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
684
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
685
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
686
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
687
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
688
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
689
+ "model.layers.22.input_layernorm.bias": "model-00002-of-00002.safetensors",
690
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
691
+ "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00002-of-00002.safetensors",
692
+ "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00002-of-00002.safetensors",
693
+ "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00002-of-00002.safetensors",
694
+ "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00002-of-00002.safetensors",
695
+ "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00002-of-00002.safetensors",
696
+ "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00002-of-00002.safetensors",
697
+ "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00002-of-00002.safetensors",
698
+ "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00002-of-00002.safetensors",
699
+ "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00002-of-00002.safetensors",
700
+ "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00002-of-00002.safetensors",
701
+ "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00002-of-00002.safetensors",
702
+ "model.layers.22.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00002-of-00002.safetensors",
703
+ "model.layers.22.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
704
+ "model.layers.22.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
705
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
706
+ "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
707
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
708
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
709
+ "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
710
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
711
+ "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
712
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
713
+ "model.layers.23.input_layernorm.bias": "model-00002-of-00002.safetensors",
714
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
715
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
716
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
717
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
718
+ "model.layers.23.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
719
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
720
+ "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
721
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
722
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
723
+ "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
724
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
725
+ "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
726
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
727
+ "model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
728
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
729
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
730
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
731
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
732
+ "model.layers.3.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
733
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
734
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
735
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
736
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
737
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
738
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
739
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
740
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
741
+ "model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
742
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
743
+ "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
744
+ "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
745
+ "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
746
+ "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
747
+ "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
748
+ "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
749
+ "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
750
+ "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
751
+ "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
752
+ "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
753
+ "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
754
+ "model.layers.4.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
755
+ "model.layers.4.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
756
+ "model.layers.4.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
757
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
758
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
759
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
760
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
761
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
762
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
763
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
764
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
765
+ "model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
766
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
767
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
768
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
769
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
770
+ "model.layers.5.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
771
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
772
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
773
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
774
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
775
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
776
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
777
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
778
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
779
+ "model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
780
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
781
+ "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
782
+ "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
783
+ "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
784
+ "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
785
+ "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
786
+ "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
787
+ "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
788
+ "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
789
+ "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
790
+ "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
791
+ "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
792
+ "model.layers.6.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
793
+ "model.layers.6.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
794
+ "model.layers.6.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
795
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
796
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
797
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
798
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
799
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
800
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
801
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
802
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
803
+ "model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
804
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
805
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
806
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
807
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
808
+ "model.layers.7.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
809
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
810
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
811
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
812
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
813
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
814
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
815
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
816
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
817
+ "model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
818
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
819
+ "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.0.down_proj.weight": "model-00001-of-00002.safetensors",
820
+ "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.0.gate_proj.weight": "model-00001-of-00002.safetensors",
821
+ "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.0.up_proj.weight": "model-00001-of-00002.safetensors",
822
+ "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.1.down_proj.weight": "model-00001-of-00002.safetensors",
823
+ "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.1.gate_proj.weight": "model-00001-of-00002.safetensors",
824
+ "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.1.up_proj.weight": "model-00001-of-00002.safetensors",
825
+ "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.2.down_proj.weight": "model-00001-of-00002.safetensors",
826
+ "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.2.gate_proj.weight": "model-00001-of-00002.safetensors",
827
+ "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.2.up_proj.weight": "model-00001-of-00002.safetensors",
828
+ "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.3.down_proj.weight": "model-00001-of-00002.safetensors",
829
+ "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.3.gate_proj.weight": "model-00001-of-00002.safetensors",
830
+ "model.layers.8.mlp.deepspeed_moe.experts.deepspeed_experts.3.up_proj.weight": "model-00001-of-00002.safetensors",
831
+ "model.layers.8.mlp.deepspeed_moe.gate.wg.weight": "model-00001-of-00002.safetensors",
832
+ "model.layers.8.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
833
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
834
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
835
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
836
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
837
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
838
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
839
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
840
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
841
+ "model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
842
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
843
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
844
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
845
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
846
+ "model.layers.9.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
847
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
848
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
849
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
850
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
851
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
852
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
853
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
854
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
855
+ "model.mm_projector.image_spatial_proj.0.bias": "model-00002-of-00002.safetensors",
856
+ "model.mm_projector.image_spatial_proj.0.weight": "model-00002-of-00002.safetensors",
857
+ "model.mm_projector.image_spatial_proj.2.bias": "model-00002-of-00002.safetensors",
858
+ "model.mm_projector.image_spatial_proj.2.weight": "model-00002-of-00002.safetensors",
859
+ "model.norm.bias": "model-00002-of-00002.safetensors",
860
+ "model.norm.weight": "model-00002-of-00002.safetensors"
861
+ }
862
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "<|endoftext|>",
3
+ "pad_token": "<|reg0|>",
4
+ "unk_token": "<|reg0|>"
5
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {},
3
+ "auto_map": {
4
+ "AutoTokenizer": [
5
+ "stabilityai/stablelm-2-1_6b--tokenization_arcade100k.Arcade100kTokenizer",
6
+ null
7
+ ]
8
+ },
9
+ "clean_up_tokenization_spaces": true,
10
+ "eos_token": "<|endoftext|>",
11
+ "errors": "replace",
12
+ "model_max_length": 2048,
13
+ "pad_token": "<|reg0|>",
14
+ "padding_side": "right",
15
+ "tokenizer_class": "Arcade100kTokenizer",
16
+ "unk_token": "<|reg0|>",
17
+ "use_fast": false
18
+ }