Hugging Face's logo

mlx-community
/
deepseek-vl2-tiny-4bit

Image-Text-to-Text
Transformers
Safetensors
MLX
deepseek_vl_v2
conversational
Model card Files
xet
Community
1
prince-canuma commited on
Commit
4772de7
·
verified ·
1 Parent(s): 3433f25

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. README.md +22 -0
  2. chat_template.json +3 -0
  3. config.json +155 -0
  4. model.safetensors +3 -0
  5. model.safetensors.index.json +922 -0
  6. processor_config.json +116 -0
  7. special_tokens_map.json +39 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +0 -0
README.md ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ license_name: deepseek
4
+ license_link: https://github.com/deepseek-ai/DeepSeek-LLM/blob/HEAD/LICENSE-MODEL
5
+ pipeline_tag: image-text-to-text
6
+ library_name: transformers
7
+ tags:
8
+ - mlx
9
+ ---
10
+
11
+ # mlx-community/deepseek-vl2-tiny-4bit
12
+ This model was converted to MLX format from [`prince-canuma/deepseek-vl2-tiny`]() using mlx-vlm version **0.1.5**.
13
+ Refer to the [original model card](https://huggingface.co/prince-canuma/deepseek-vl2-tiny) for more details on the model.
14
+ ## Use with mlx
15
+
16
+ ```bash
17
+ pip install -U mlx-vlm
18
+ ```
19
+
20
+ ```bash
21
+ python -m mlx_vlm.generate --model mlx-community/deepseek-vl2-tiny-4bit --max-tokens 100 --temp 0.0
22
+ ```
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}<|User|>:{% elif message['role'] == 'assistant' %}<|Assistant|>{% endif %} {{message['content']}}\n\n{% endfor %}{% if add_generation_prompt %}<|Assistant|>:{% endif %}"
3
+ }
config.json ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "candidate_resolutions": [
3
+ [
4
+ 384,
5
+ 384
6
+ ],
7
+ [
8
+ 384,
9
+ 768
10
+ ],
11
+ [
12
+ 768,
13
+ 384
14
+ ],
15
+ [
16
+ 384,
17
+ 1152
18
+ ],
19
+ [
20
+ 1152,
21
+ 384
22
+ ],
23
+ [
24
+ 384,
25
+ 1536
26
+ ],
27
+ [
28
+ 1536,
29
+ 384
30
+ ],
31
+ [
32
+ 768,
33
+ 768
34
+ ],
35
+ [
36
+ 384,
37
+ 1920
38
+ ],
39
+ [
40
+ 1920,
41
+ 384
42
+ ],
43
+ [
44
+ 384,
45
+ 2304
46
+ ],
47
+ [
48
+ 2304,
49
+ 384
50
+ ],
51
+ [
52
+ 768,
53
+ 1152
54
+ ],
55
+ [
56
+ 1152,
57
+ 768
58
+ ],
59
+ [
60
+ 384,
61
+ 2688
62
+ ],
63
+ [
64
+ 2688,
65
+ 384
66
+ ],
67
+ [
68
+ 384,
69
+ 3072
70
+ ],
71
+ [
72
+ 3072,
73
+ 384
74
+ ],
75
+ [
76
+ 768,
77
+ 1536
78
+ ],
79
+ [
80
+ 1536,
81
+ 768
82
+ ],
83
+ [
84
+ 384,
85
+ 3456
86
+ ],
87
+ [
88
+ 3456,
89
+ 384
90
+ ],
91
+ [
92
+ 1152,
93
+ 1152
94
+ ]
95
+ ],
96
+ "global_view_pos": "head",
97
+ "language_config": {
98
+ "architectures": [
99
+ "DeepseekV2ForCausalLM"
100
+ ],
101
+ "auto_map": {
102
+ "AutoConfig": "configuration_deepseek.DeepseekV2Config",
103
+ "AutoModel": "modeling_deepseek.DeepseekV2Model",
104
+ "AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM"
105
+ },
106
+ "bos_token_id": 0,
107
+ "eos_token_id": 1,
108
+ "first_k_dense_replace": 1,
109
+ "hidden_size": 1280,
110
+ "intermediate_size": 6848,
111
+ "kv_lora_rank": null,
112
+ "lm_head": true,
113
+ "max_position_embeddings": 4096,
114
+ "model_type": "deepseek_v2",
115
+ "moe_intermediate_size": 896,
116
+ "n_group": 1,
117
+ "n_routed_experts": 64,
118
+ "n_shared_experts": 2,
119
+ "num_attention_heads": 10,
120
+ "num_experts_per_tok": 6,
121
+ "num_hidden_layers": 12,
122
+ "num_key_value_heads": 10,
123
+ "q_lora_rank": null,
124
+ "qk_nope_head_dim": 0,
125
+ "qk_rope_head_dim": 0,
126
+ "rm_head": false,
127
+ "topk_group": 1,
128
+ "topk_method": "greedy",
129
+ "torch_dtype": "bfloat16",
130
+ "use_mla": false,
131
+ "v_head_dim": 0,
132
+ "vocab_size": 129280
133
+ },
134
+ "model_type": "deepseek_vl_v2",
135
+ "projector_config": {
136
+ "model_type": "mlp_projector",
137
+ "n_embed": 1280
138
+ },
139
+ "quantization": {
140
+ "group_size": 64,
141
+ "bits": 4
142
+ },
143
+ "tile_tag": "2D",
144
+ "torch_dtype": "bfloat16",
145
+ "transformers_version": "4.38.2",
146
+ "vision_config": {
147
+ "layers": 27,
148
+ "mlp_ratio": 3.7362,
149
+ "model_name": "siglip_so400m_patch14_384",
150
+ "model_type": "vision",
151
+ "patch_size": 14,
152
+ "width": 1152,
153
+ "skip_vision_non_divisible": true
154
+ }
155
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7afb62609eae2cfa0d1b79cbf9e72c2c80fd376ba783e730d24d89e47ce5a35
3
+ size 2099712075
model.safetensors.index.json ADDED
@@ -0,0 +1,922 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 2099598464
4
+ },
5
+ "weight_map": {
6
+ "image_newline": "model.safetensors",
7
+ "language_model.lm_head.biases": "model.safetensors",
8
+ "language_model.lm_head.scales": "model.safetensors",
9
+ "language_model.lm_head.weight": "model.safetensors",
10
+ "language_model.model.embed_tokens.biases": "model.safetensors",
11
+ "language_model.model.embed_tokens.scales": "model.safetensors",
12
+ "language_model.model.embed_tokens.weight": "model.safetensors",
13
+ "language_model.model.layers.0.input_layernorm.weight": "model.safetensors",
14
+ "language_model.model.layers.0.mlp.down_proj.biases": "model.safetensors",
15
+ "language_model.model.layers.0.mlp.down_proj.scales": "model.safetensors",
16
+ "language_model.model.layers.0.mlp.down_proj.weight": "model.safetensors",
17
+ "language_model.model.layers.0.mlp.gate_proj.biases": "model.safetensors",
18
+ "language_model.model.layers.0.mlp.gate_proj.scales": "model.safetensors",
19
+ "language_model.model.layers.0.mlp.gate_proj.weight": "model.safetensors",
20
+ "language_model.model.layers.0.mlp.up_proj.biases": "model.safetensors",
21
+ "language_model.model.layers.0.mlp.up_proj.scales": "model.safetensors",
22
+ "language_model.model.layers.0.mlp.up_proj.weight": "model.safetensors",
23
+ "language_model.model.layers.0.post_attention_layernorm.weight": "model.safetensors",
24
+ "language_model.model.layers.0.self_attn.k_proj.biases": "model.safetensors",
25
+ "language_model.model.layers.0.self_attn.k_proj.scales": "model.safetensors",
26
+ "language_model.model.layers.0.self_attn.k_proj.weight": "model.safetensors",
27
+ "language_model.model.layers.0.self_attn.o_proj.biases": "model.safetensors",
28
+ "language_model.model.layers.0.self_attn.o_proj.scales": "model.safetensors",
29
+ "language_model.model.layers.0.self_attn.o_proj.weight": "model.safetensors",
30
+ "language_model.model.layers.0.self_attn.q_proj.biases": "model.safetensors",
31
+ "language_model.model.layers.0.self_attn.q_proj.scales": "model.safetensors",
32
+ "language_model.model.layers.0.self_attn.q_proj.weight": "model.safetensors",
33
+ "language_model.model.layers.0.self_attn.v_proj.biases": "model.safetensors",
34
+ "language_model.model.layers.0.self_attn.v_proj.scales": "model.safetensors",
35
+ "language_model.model.layers.0.self_attn.v_proj.weight": "model.safetensors",
36
+ "language_model.model.layers.1.input_layernorm.weight": "model.safetensors",
37
+ "language_model.model.layers.1.mlp.gate.weight": "model.safetensors",
38
+ "language_model.model.layers.1.mlp.shared_experts.down_proj.biases": "model.safetensors",
39
+ "language_model.model.layers.1.mlp.shared_experts.down_proj.scales": "model.safetensors",
40
+ "language_model.model.layers.1.mlp.shared_experts.down_proj.weight": "model.safetensors",
41
+ "language_model.model.layers.1.mlp.shared_experts.gate_proj.biases": "model.safetensors",
42
+ "language_model.model.layers.1.mlp.shared_experts.gate_proj.scales": "model.safetensors",
43
+ "language_model.model.layers.1.mlp.shared_experts.gate_proj.weight": "model.safetensors",
44
+ "language_model.model.layers.1.mlp.shared_experts.up_proj.biases": "model.safetensors",
45
+ "language_model.model.layers.1.mlp.shared_experts.up_proj.scales": "model.safetensors",
46
+ "language_model.model.layers.1.mlp.shared_experts.up_proj.weight": "model.safetensors",
47
+ "language_model.model.layers.1.mlp.switch_mlp.down_proj.biases": "model.safetensors",
48
+ "language_model.model.layers.1.mlp.switch_mlp.down_proj.scales": "model.safetensors",
49
+ "language_model.model.layers.1.mlp.switch_mlp.down_proj.weight": "model.safetensors",
50
+ "language_model.model.layers.1.mlp.switch_mlp.gate_proj.biases": "model.safetensors",
51
+ "language_model.model.layers.1.mlp.switch_mlp.gate_proj.scales": "model.safetensors",
52
+ "language_model.model.layers.1.mlp.switch_mlp.gate_proj.weight": "model.safetensors",
53
+ "language_model.model.layers.1.mlp.switch_mlp.up_proj.biases": "model.safetensors",
54
+ "language_model.model.layers.1.mlp.switch_mlp.up_proj.scales": "model.safetensors",
55
+ "language_model.model.layers.1.mlp.switch_mlp.up_proj.weight": "model.safetensors",
56
+ "language_model.model.layers.1.post_attention_layernorm.weight": "model.safetensors",
57
+ "language_model.model.layers.1.self_attn.k_proj.biases": "model.safetensors",
58
+ "language_model.model.layers.1.self_attn.k_proj.scales": "model.safetensors",
59
+ "language_model.model.layers.1.self_attn.k_proj.weight": "model.safetensors",
60
+ "language_model.model.layers.1.self_attn.o_proj.biases": "model.safetensors",
61
+ "language_model.model.layers.1.self_attn.o_proj.scales": "model.safetensors",
62
+ "language_model.model.layers.1.self_attn.o_proj.weight": "model.safetensors",
63
+ "language_model.model.layers.1.self_attn.q_proj.biases": "model.safetensors",
64
+ "language_model.model.layers.1.self_attn.q_proj.scales": "model.safetensors",
65
+ "language_model.model.layers.1.self_attn.q_proj.weight": "model.safetensors",
66
+ "language_model.model.layers.1.self_attn.v_proj.biases": "model.safetensors",
67
+ "language_model.model.layers.1.self_attn.v_proj.scales": "model.safetensors",
68
+ "language_model.model.layers.1.self_attn.v_proj.weight": "model.safetensors",
69
+ "language_model.model.layers.10.input_layernorm.weight": "model.safetensors",
70
+ "language_model.model.layers.10.mlp.gate.weight": "model.safetensors",
71
+ "language_model.model.layers.10.mlp.shared_experts.down_proj.biases": "model.safetensors",
72
+ "language_model.model.layers.10.mlp.shared_experts.down_proj.scales": "model.safetensors",
73
+ "language_model.model.layers.10.mlp.shared_experts.down_proj.weight": "model.safetensors",
74
+ "language_model.model.layers.10.mlp.shared_experts.gate_proj.biases": "model.safetensors",
75
+ "language_model.model.layers.10.mlp.shared_experts.gate_proj.scales": "model.safetensors",
76
+ "language_model.model.layers.10.mlp.shared_experts.gate_proj.weight": "model.safetensors",
77
+ "language_model.model.layers.10.mlp.shared_experts.up_proj.biases": "model.safetensors",
78
+ "language_model.model.layers.10.mlp.shared_experts.up_proj.scales": "model.safetensors",
79
+ "language_model.model.layers.10.mlp.shared_experts.up_proj.weight": "model.safetensors",
80
+ "language_model.model.layers.10.mlp.switch_mlp.down_proj.biases": "model.safetensors",
81
+ "language_model.model.layers.10.mlp.switch_mlp.down_proj.scales": "model.safetensors",
82
+ "language_model.model.layers.10.mlp.switch_mlp.down_proj.weight": "model.safetensors",
83
+ "language_model.model.layers.10.mlp.switch_mlp.gate_proj.biases": "model.safetensors",
84
+ "language_model.model.layers.10.mlp.switch_mlp.gate_proj.scales": "model.safetensors",
85
+ "language_model.model.layers.10.mlp.switch_mlp.gate_proj.weight": "model.safetensors",
86
+ "language_model.model.layers.10.mlp.switch_mlp.up_proj.biases": "model.safetensors",
87
+ "language_model.model.layers.10.mlp.switch_mlp.up_proj.scales": "model.safetensors",
88
+ "language_model.model.layers.10.mlp.switch_mlp.up_proj.weight": "model.safetensors",
89
+ "language_model.model.layers.10.post_attention_layernorm.weight": "model.safetensors",
90
+ "language_model.model.layers.10.self_attn.k_proj.biases": "model.safetensors",
91
+ "language_model.model.layers.10.self_attn.k_proj.scales": "model.safetensors",
92
+ "language_model.model.layers.10.self_attn.k_proj.weight": "model.safetensors",
93
+ "language_model.model.layers.10.self_attn.o_proj.biases": "model.safetensors",
94
+ "language_model.model.layers.10.self_attn.o_proj.scales": "model.safetensors",
95
+ "language_model.model.layers.10.self_attn.o_proj.weight": "model.safetensors",
96
+ "language_model.model.layers.10.self_attn.q_proj.biases": "model.safetensors",
97
+ "language_model.model.layers.10.self_attn.q_proj.scales": "model.safetensors",
98
+ "language_model.model.layers.10.self_attn.q_proj.weight": "model.safetensors",
99
+ "language_model.model.layers.10.self_attn.v_proj.biases": "model.safetensors",
100
+ "language_model.model.layers.10.self_attn.v_proj.scales": "model.safetensors",
101
+ "language_model.model.layers.10.self_attn.v_proj.weight": "model.safetensors",
102
+ "language_model.model.layers.11.input_layernorm.weight": "model.safetensors",
103
+ "language_model.model.layers.11.mlp.gate.weight": "model.safetensors",
104
+ "language_model.model.layers.11.mlp.shared_experts.down_proj.biases": "model.safetensors",
105
+ "language_model.model.layers.11.mlp.shared_experts.down_proj.scales": "model.safetensors",
106
+ "language_model.model.layers.11.mlp.shared_experts.down_proj.weight": "model.safetensors",
107
+ "language_model.model.layers.11.mlp.shared_experts.gate_proj.biases": "model.safetensors",
108
+ "language_model.model.layers.11.mlp.shared_experts.gate_proj.scales": "model.safetensors",
109
+ "language_model.model.layers.11.mlp.shared_experts.gate_proj.weight": "model.safetensors",
110
+ "language_model.model.layers.11.mlp.shared_experts.up_proj.biases": "model.safetensors",
111
+ "language_model.model.layers.11.mlp.shared_experts.up_proj.scales": "model.safetensors",
112
+ "language_model.model.layers.11.mlp.shared_experts.up_proj.weight": "model.safetensors",
113
+ "language_model.model.layers.11.mlp.switch_mlp.down_proj.biases": "model.safetensors",
114
+ "language_model.model.layers.11.mlp.switch_mlp.down_proj.scales": "model.safetensors",
115
+ "language_model.model.layers.11.mlp.switch_mlp.down_proj.weight": "model.safetensors",
116
+ "language_model.model.layers.11.mlp.switch_mlp.gate_proj.biases": "model.safetensors",
117
+ "language_model.model.layers.11.mlp.switch_mlp.gate_proj.scales": "model.safetensors",
118
+ "language_model.model.layers.11.mlp.switch_mlp.gate_proj.weight": "model.safetensors",
119
+ "language_model.model.layers.11.mlp.switch_mlp.up_proj.biases": "model.safetensors",
120
+ "language_model.model.layers.11.mlp.switch_mlp.up_proj.scales": "model.safetensors",
121
+ "language_model.model.layers.11.mlp.switch_mlp.up_proj.weight": "model.safetensors",
122
+ "language_model.model.layers.11.post_attention_layernorm.weight": "model.safetensors",
123
+ "language_model.model.layers.11.self_attn.k_proj.biases": "model.safetensors",
124
+ "language_model.model.layers.11.self_attn.k_proj.scales": "model.safetensors",
125
+ "language_model.model.layers.11.self_attn.k_proj.weight": "model.safetensors",
126
+ "language_model.model.layers.11.self_attn.o_proj.biases": "model.safetensors",
127
+ "language_model.model.layers.11.self_attn.o_proj.scales": "model.safetensors",
128
+ "language_model.model.layers.11.self_attn.o_proj.weight": "model.safetensors",
129
+ "language_model.model.layers.11.self_attn.q_proj.biases": "model.safetensors",
130
+ "language_model.model.layers.11.self_attn.q_proj.scales": "model.safetensors",
131
+ "language_model.model.layers.11.self_attn.q_proj.weight": "model.safetensors",
132
+ "language_model.model.layers.11.self_attn.v_proj.biases": "model.safetensors",
133
+ "language_model.model.layers.11.self_attn.v_proj.scales": "model.safetensors",
134
+ "language_model.model.layers.11.self_attn.v_proj.weight": "model.safetensors",
135
+ "language_model.model.layers.2.input_layernorm.weight": "model.safetensors",
136
+ "language_model.model.layers.2.mlp.gate.weight": "model.safetensors",
137
+ "language_model.model.layers.2.mlp.shared_experts.down_proj.biases": "model.safetensors",
138
+ "language_model.model.layers.2.mlp.shared_experts.down_proj.scales": "model.safetensors",
139
+ "language_model.model.layers.2.mlp.shared_experts.down_proj.weight": "model.safetensors",
140
+ "language_model.model.layers.2.mlp.shared_experts.gate_proj.biases": "model.safetensors",
141
+ "language_model.model.layers.2.mlp.shared_experts.gate_proj.scales": "model.safetensors",
142
+ "language_model.model.layers.2.mlp.shared_experts.gate_proj.weight": "model.safetensors",
143
+ "language_model.model.layers.2.mlp.shared_experts.up_proj.biases": "model.safetensors",
144
+ "language_model.model.layers.2.mlp.shared_experts.up_proj.scales": "model.safetensors",
145
+ "language_model.model.layers.2.mlp.shared_experts.up_proj.weight": "model.safetensors",
146
+ "language_model.model.layers.2.mlp.switch_mlp.down_proj.biases": "model.safetensors",
147
+ "language_model.model.layers.2.mlp.switch_mlp.down_proj.scales": "model.safetensors",
148
+ "language_model.model.layers.2.mlp.switch_mlp.down_proj.weight": "model.safetensors",
149
+ "language_model.model.layers.2.mlp.switch_mlp.gate_proj.biases": "model.safetensors",
150
+ "language_model.model.layers.2.mlp.switch_mlp.gate_proj.scales": "model.safetensors",
151
+ "language_model.model.layers.2.mlp.switch_mlp.gate_proj.weight": "model.safetensors",
152
+ "language_model.model.layers.2.mlp.switch_mlp.up_proj.biases": "model.safetensors",
153
+ "language_model.model.layers.2.mlp.switch_mlp.up_proj.scales": "model.safetensors",
154
+ "language_model.model.layers.2.mlp.switch_mlp.up_proj.weight": "model.safetensors",
155
+ "language_model.model.layers.2.post_attention_layernorm.weight": "model.safetensors",
156
+ "language_model.model.layers.2.self_attn.k_proj.biases": "model.safetensors",
157
+ "language_model.model.layers.2.self_attn.k_proj.scales": "model.safetensors",
158
+ "language_model.model.layers.2.self_attn.k_proj.weight": "model.safetensors",
159
+ "language_model.model.layers.2.self_attn.o_proj.biases": "model.safetensors",
160
+ "language_model.model.layers.2.self_attn.o_proj.scales": "model.safetensors",
161
+ "language_model.model.layers.2.self_attn.o_proj.weight": "model.safetensors",
162
+ "language_model.model.layers.2.self_attn.q_proj.biases": "model.safetensors",
163
+ "language_model.model.layers.2.self_attn.q_proj.scales": "model.safetensors",
164
+ "language_model.model.layers.2.self_attn.q_proj.weight": "model.safetensors",
165
+ "language_model.model.layers.2.self_attn.v_proj.biases": "model.safetensors",
166
+ "language_model.model.layers.2.self_attn.v_proj.scales": "model.safetensors",
167
+ "language_model.model.layers.2.self_attn.v_proj.weight": "model.safetensors",
168
+ "language_model.model.layers.3.input_layernorm.weight": "model.safetensors",
169
+ "language_model.model.layers.3.mlp.gate.weight": "model.safetensors",
170
+ "language_model.model.layers.3.mlp.shared_experts.down_proj.biases": "model.safetensors",
171
+ "language_model.model.layers.3.mlp.shared_experts.down_proj.scales": "model.safetensors",
172
+ "language_model.model.layers.3.mlp.shared_experts.down_proj.weight": "model.safetensors",
173
+ "language_model.model.layers.3.mlp.shared_experts.gate_proj.biases": "model.safetensors",
174
+ "language_model.model.layers.3.mlp.shared_experts.gate_proj.scales": "model.safetensors",
175
+ "language_model.model.layers.3.mlp.shared_experts.gate_proj.weight": "model.safetensors",
176
+ "language_model.model.layers.3.mlp.shared_experts.up_proj.biases": "model.safetensors",
177
+ "language_model.model.layers.3.mlp.shared_experts.up_proj.scales": "model.safetensors",
178
+ "language_model.model.layers.3.mlp.shared_experts.up_proj.weight": "model.safetensors",
179
+ "language_model.model.layers.3.mlp.switch_mlp.down_proj.biases": "model.safetensors",
180
+ "language_model.model.layers.3.mlp.switch_mlp.down_proj.scales": "model.safetensors",
181
+ "language_model.model.layers.3.mlp.switch_mlp.down_proj.weight": "model.safetensors",
182
+ "language_model.model.layers.3.mlp.switch_mlp.gate_proj.biases": "model.safetensors",
183
+ "language_model.model.layers.3.mlp.switch_mlp.gate_proj.scales": "model.safetensors",
184
+ "language_model.model.layers.3.mlp.switch_mlp.gate_proj.weight": "model.safetensors",
185
+ "language_model.model.layers.3.mlp.switch_mlp.up_proj.biases": "model.safetensors",
186
+ "language_model.model.layers.3.mlp.switch_mlp.up_proj.scales": "model.safetensors",
187
+ "language_model.model.layers.3.mlp.switch_mlp.up_proj.weight": "model.safetensors",
188
+ "language_model.model.layers.3.post_attention_layernorm.weight": "model.safetensors",
189
+ "language_model.model.layers.3.self_attn.k_proj.biases": "model.safetensors",
190
+ "language_model.model.layers.3.self_attn.k_proj.scales": "model.safetensors",
191
+ "language_model.model.layers.3.self_attn.k_proj.weight": "model.safetensors",
192
+ "language_model.model.layers.3.self_attn.o_proj.biases": "model.safetensors",
193
+ "language_model.model.layers.3.self_attn.o_proj.scales": "model.safetensors",
194
+ "language_model.model.layers.3.self_attn.o_proj.weight": "model.safetensors",
195
+ "language_model.model.layers.3.self_attn.q_proj.biases": "model.safetensors",
196
+ "language_model.model.layers.3.self_attn.q_proj.scales": "model.safetensors",
197
+ "language_model.model.layers.3.self_attn.q_proj.weight": "model.safetensors",
198
+ "language_model.model.layers.3.self_attn.v_proj.biases": "model.safetensors",
199
+ "language_model.model.layers.3.self_attn.v_proj.scales": "model.safetensors",
200
+ "language_model.model.layers.3.self_attn.v_proj.weight": "model.safetensors",
201
+ "language_model.model.layers.4.input_layernorm.weight": "model.safetensors",
202
+ "language_model.model.layers.4.mlp.gate.weight": "model.safetensors",
203
+ "language_model.model.layers.4.mlp.shared_experts.down_proj.biases": "model.safetensors",
204
+ "language_model.model.layers.4.mlp.shared_experts.down_proj.scales": "model.safetensors",
205
+ "language_model.model.layers.4.mlp.shared_experts.down_proj.weight": "model.safetensors",
206
+ "language_model.model.layers.4.mlp.shared_experts.gate_proj.biases": "model.safetensors",
207
+ "language_model.model.layers.4.mlp.shared_experts.gate_proj.scales": "model.safetensors",
208
+ "language_model.model.layers.4.mlp.shared_experts.gate_proj.weight": "model.safetensors",
209
+ "language_model.model.layers.4.mlp.shared_experts.up_proj.biases": "model.safetensors",
210
+ "language_model.model.layers.4.mlp.shared_experts.up_proj.scales": "model.safetensors",
211
+ "language_model.model.layers.4.mlp.shared_experts.up_proj.weight": "model.safetensors",
212
+ "language_model.model.layers.4.mlp.switch_mlp.down_proj.biases": "model.safetensors",
213
+ "language_model.model.layers.4.mlp.switch_mlp.down_proj.scales": "model.safetensors",
214
+ "language_model.model.layers.4.mlp.switch_mlp.down_proj.weight": "model.safetensors",
215
+ "language_model.model.layers.4.mlp.switch_mlp.gate_proj.biases": "model.safetensors",
216
+ "language_model.model.layers.4.mlp.switch_mlp.gate_proj.scales": "model.safetensors",
217
+ "language_model.model.layers.4.mlp.switch_mlp.gate_proj.weight": "model.safetensors",
218
+ "language_model.model.layers.4.mlp.switch_mlp.up_proj.biases": "model.safetensors",
219
+ "language_model.model.layers.4.mlp.switch_mlp.up_proj.scales": "model.safetensors",
220
+ "language_model.model.layers.4.mlp.switch_mlp.up_proj.weight": "model.safetensors",
221
+ "language_model.model.layers.4.post_attention_layernorm.weight": "model.safetensors",
222
+ "language_model.model.layers.4.self_attn.k_proj.biases": "model.safetensors",
223
+ "language_model.model.layers.4.self_attn.k_proj.scales": "model.safetensors",
224
+ "language_model.model.layers.4.self_attn.k_proj.weight": "model.safetensors",
225
+ "language_model.model.layers.4.self_attn.o_proj.biases": "model.safetensors",
226
+ "language_model.model.layers.4.self_attn.o_proj.scales": "model.safetensors",
227
+ "language_model.model.layers.4.self_attn.o_proj.weight": "model.safetensors",
228
+ "language_model.model.layers.4.self_attn.q_proj.biases": "model.safetensors",
229
+ "language_model.model.layers.4.self_attn.q_proj.scales": "model.safetensors",
230
+ "language_model.model.layers.4.self_attn.q_proj.weight": "model.safetensors",
231
+ "language_model.model.layers.4.self_attn.v_proj.biases": "model.safetensors",
232
+ "language_model.model.layers.4.self_attn.v_proj.scales": "model.safetensors",
233
+ "language_model.model.layers.4.self_attn.v_proj.weight": "model.safetensors",
234
+ "language_model.model.layers.5.input_layernorm.weight": "model.safetensors",
235
+ "language_model.model.layers.5.mlp.gate.weight": "model.safetensors",
236
+ "language_model.model.layers.5.mlp.shared_experts.down_proj.biases": "model.safetensors",
237
+ "language_model.model.layers.5.mlp.shared_experts.down_proj.scales": "model.safetensors",
238
+ "language_model.model.layers.5.mlp.shared_experts.down_proj.weight": "model.safetensors",
239
+ "language_model.model.layers.5.mlp.shared_experts.gate_proj.biases": "model.safetensors",
240
+ "language_model.model.layers.5.mlp.shared_experts.gate_proj.scales": "model.safetensors",
241
+ "language_model.model.layers.5.mlp.shared_experts.gate_proj.weight": "model.safetensors",
242
+ "language_model.model.layers.5.mlp.shared_experts.up_proj.biases": "model.safetensors",
243
+ "language_model.model.layers.5.mlp.shared_experts.up_proj.scales": "model.safetensors",
244
+ "language_model.model.layers.5.mlp.shared_experts.up_proj.weight": "model.safetensors",
245
+ "language_model.model.layers.5.mlp.switch_mlp.down_proj.biases": "model.safetensors",
246
+ "language_model.model.layers.5.mlp.switch_mlp.down_proj.scales": "model.safetensors",
247
+ "language_model.model.layers.5.mlp.switch_mlp.down_proj.weight": "model.safetensors",
248
+ "language_model.model.layers.5.mlp.switch_mlp.gate_proj.biases": "model.safetensors",
249
+ "language_model.model.layers.5.mlp.switch_mlp.gate_proj.scales": "model.safetensors",
250
+ "language_model.model.layers.5.mlp.switch_mlp.gate_proj.weight": "model.safetensors",
251
+ "language_model.model.layers.5.mlp.switch_mlp.up_proj.biases": "model.safetensors",
252
+ "language_model.model.layers.5.mlp.switch_mlp.up_proj.scales": "model.safetensors",
253
+ "language_model.model.layers.5.mlp.switch_mlp.up_proj.weight": "model.safetensors",
254
+ "language_model.model.layers.5.post_attention_layernorm.weight": "model.safetensors",
255
+ "language_model.model.layers.5.self_attn.k_proj.biases": "model.safetensors",
256
+ "language_model.model.layers.5.self_attn.k_proj.scales": "model.safetensors",
257
+ "language_model.model.layers.5.self_attn.k_proj.weight": "model.safetensors",
258
+ "language_model.model.layers.5.self_attn.o_proj.biases": "model.safetensors",
259
+ "language_model.model.layers.5.self_attn.o_proj.scales": "model.safetensors",
260
+ "language_model.model.layers.5.self_attn.o_proj.weight": "model.safetensors",
261
+ "language_model.model.layers.5.self_attn.q_proj.biases": "model.safetensors",
262
+ "language_model.model.layers.5.self_attn.q_proj.scales": "model.safetensors",
263
+ "language_model.model.layers.5.self_attn.q_proj.weight": "model.safetensors",
264
+ "language_model.model.layers.5.self_attn.v_proj.biases": "model.safetensors",
265
+ "language_model.model.layers.5.self_attn.v_proj.scales": "model.safetensors",
266
+ "language_model.model.layers.5.self_attn.v_proj.weight": "model.safetensors",
267
+ "language_model.model.layers.6.input_layernorm.weight": "model.safetensors",
268
+ "language_model.model.layers.6.mlp.gate.weight": "model.safetensors",
269
+ "language_model.model.layers.6.mlp.shared_experts.down_proj.biases": "model.safetensors",
270
+ "language_model.model.layers.6.mlp.shared_experts.down_proj.scales": "model.safetensors",
271
+ "language_model.model.layers.6.mlp.shared_experts.down_proj.weight": "model.safetensors",
272
+ "language_model.model.layers.6.mlp.shared_experts.gate_proj.biases": "model.safetensors",
273
+ "language_model.model.layers.6.mlp.shared_experts.gate_proj.scales": "model.safetensors",
274
+ "language_model.model.layers.6.mlp.shared_experts.gate_proj.weight": "model.safetensors",
275
+ "language_model.model.layers.6.mlp.shared_experts.up_proj.biases": "model.safetensors",
276
+ "language_model.model.layers.6.mlp.shared_experts.up_proj.scales": "model.safetensors",
277
+ "language_model.model.layers.6.mlp.shared_experts.up_proj.weight": "model.safetensors",
278
+ "language_model.model.layers.6.mlp.switch_mlp.down_proj.biases": "model.safetensors",
279
+ "language_model.model.layers.6.mlp.switch_mlp.down_proj.scales": "model.safetensors",
280
+ "language_model.model.layers.6.mlp.switch_mlp.down_proj.weight": "model.safetensors",
281
+ "language_model.model.layers.6.mlp.switch_mlp.gate_proj.biases": "model.safetensors",
282
+ "language_model.model.layers.6.mlp.switch_mlp.gate_proj.scales": "model.safetensors",
283
+ "language_model.model.layers.6.mlp.switch_mlp.gate_proj.weight": "model.safetensors",
284
+ "language_model.model.layers.6.mlp.switch_mlp.up_proj.biases": "model.safetensors",
285
+ "language_model.model.layers.6.mlp.switch_mlp.up_proj.scales": "model.safetensors",
286
+ "language_model.model.layers.6.mlp.switch_mlp.up_proj.weight": "model.safetensors",
287
+ "language_model.model.layers.6.post_attention_layernorm.weight": "model.safetensors",
288
+ "language_model.model.layers.6.self_attn.k_proj.biases": "model.safetensors",
289
+ "language_model.model.layers.6.self_attn.k_proj.scales": "model.safetensors",
290
+ "language_model.model.layers.6.self_attn.k_proj.weight": "model.safetensors",
291
+ "language_model.model.layers.6.self_attn.o_proj.biases": "model.safetensors",
292
+ "language_model.model.layers.6.self_attn.o_proj.scales": "model.safetensors",
293
+ "language_model.model.layers.6.self_attn.o_proj.weight": "model.safetensors",
294
+ "language_model.model.layers.6.self_attn.q_proj.biases": "model.safetensors",
295
+ "language_model.model.layers.6.self_attn.q_proj.scales": "model.safetensors",
296
+ "language_model.model.layers.6.self_attn.q_proj.weight": "model.safetensors",
297
+ "language_model.model.layers.6.self_attn.v_proj.biases": "model.safetensors",
298
+ "language_model.model.layers.6.self_attn.v_proj.scales": "model.safetensors",
299
+ "language_model.model.layers.6.self_attn.v_proj.weight": "model.safetensors",
300
+ "language_model.model.layers.7.input_layernorm.weight": "model.safetensors",
301
+ "language_model.model.layers.7.mlp.gate.weight": "model.safetensors",
302
+ "language_model.model.layers.7.mlp.shared_experts.down_proj.biases": "model.safetensors",
303
+ "language_model.model.layers.7.mlp.shared_experts.down_proj.scales": "model.safetensors",
304
+ "language_model.model.layers.7.mlp.shared_experts.down_proj.weight": "model.safetensors",
305
+ "language_model.model.layers.7.mlp.shared_experts.gate_proj.biases": "model.safetensors",
306
+ "language_model.model.layers.7.mlp.shared_experts.gate_proj.scales": "model.safetensors",
307
+ "language_model.model.layers.7.mlp.shared_experts.gate_proj.weight": "model.safetensors",
308
+ "language_model.model.layers.7.mlp.shared_experts.up_proj.biases": "model.safetensors",
309
+ "language_model.model.layers.7.mlp.shared_experts.up_proj.scales": "model.safetensors",
310
+ "language_model.model.layers.7.mlp.shared_experts.up_proj.weight": "model.safetensors",
311
+ "language_model.model.layers.7.mlp.switch_mlp.down_proj.biases": "model.safetensors",
312
+ "language_model.model.layers.7.mlp.switch_mlp.down_proj.scales": "model.safetensors",
313
+ "language_model.model.layers.7.mlp.switch_mlp.down_proj.weight": "model.safetensors",
314
+ "language_model.model.layers.7.mlp.switch_mlp.gate_proj.biases": "model.safetensors",
315
+ "language_model.model.layers.7.mlp.switch_mlp.gate_proj.scales": "model.safetensors",
316
+ "language_model.model.layers.7.mlp.switch_mlp.gate_proj.weight": "model.safetensors",
317
+ "language_model.model.layers.7.mlp.switch_mlp.up_proj.biases": "model.safetensors",
318
+ "language_model.model.layers.7.mlp.switch_mlp.up_proj.scales": "model.safetensors",
319
+ "language_model.model.layers.7.mlp.switch_mlp.up_proj.weight": "model.safetensors",
320
+ "language_model.model.layers.7.post_attention_layernorm.weight": "model.safetensors",
321
+ "language_model.model.layers.7.self_attn.k_proj.biases": "model.safetensors",
322
+ "language_model.model.layers.7.self_attn.k_proj.scales": "model.safetensors",
323
+ "language_model.model.layers.7.self_attn.k_proj.weight": "model.safetensors",
324
+ "language_model.model.layers.7.self_attn.o_proj.biases": "model.safetensors",
325
+ "language_model.model.layers.7.self_attn.o_proj.scales": "model.safetensors",
326
+ "language_model.model.layers.7.self_attn.o_proj.weight": "model.safetensors",
327
+ "language_model.model.layers.7.self_attn.q_proj.biases": "model.safetensors",
328
+ "language_model.model.layers.7.self_attn.q_proj.scales": "model.safetensors",
329
+ "language_model.model.layers.7.self_attn.q_proj.weight": "model.safetensors",
330
+ "language_model.model.layers.7.self_attn.v_proj.biases": "model.safetensors",
331
+ "language_model.model.layers.7.self_attn.v_proj.scales": "model.safetensors",
332
+ "language_model.model.layers.7.self_attn.v_proj.weight": "model.safetensors",
333
+ "language_model.model.layers.8.input_layernorm.weight": "model.safetensors",
334
+ "language_model.model.layers.8.mlp.gate.weight": "model.safetensors",
335
+ "language_model.model.layers.8.mlp.shared_experts.down_proj.biases": "model.safetensors",
336
+ "language_model.model.layers.8.mlp.shared_experts.down_proj.scales": "model.safetensors",
337
+ "language_model.model.layers.8.mlp.shared_experts.down_proj.weight": "model.safetensors",
338
+ "language_model.model.layers.8.mlp.shared_experts.gate_proj.biases": "model.safetensors",
339
+ "language_model.model.layers.8.mlp.shared_experts.gate_proj.scales": "model.safetensors",
340
+ "language_model.model.layers.8.mlp.shared_experts.gate_proj.weight": "model.safetensors",
341
+ "language_model.model.layers.8.mlp.shared_experts.up_proj.biases": "model.safetensors",
342
+ "language_model.model.layers.8.mlp.shared_experts.up_proj.scales": "model.safetensors",
343
+ "language_model.model.layers.8.mlp.shared_experts.up_proj.weight": "model.safetensors",
344
+ "language_model.model.layers.8.mlp.switch_mlp.down_proj.biases": "model.safetensors",
345
+ "language_model.model.layers.8.mlp.switch_mlp.down_proj.scales": "model.safetensors",
346
+ "language_model.model.layers.8.mlp.switch_mlp.down_proj.weight": "model.safetensors",
347
+ "language_model.model.layers.8.mlp.switch_mlp.gate_proj.biases": "model.safetensors",
348
+ "language_model.model.layers.8.mlp.switch_mlp.gate_proj.scales": "model.safetensors",
349
+ "language_model.model.layers.8.mlp.switch_mlp.gate_proj.weight": "model.safetensors",
350
+ "language_model.model.layers.8.mlp.switch_mlp.up_proj.biases": "model.safetensors",
351
+ "language_model.model.layers.8.mlp.switch_mlp.up_proj.scales": "model.safetensors",
352
+ "language_model.model.layers.8.mlp.switch_mlp.up_proj.weight": "model.safetensors",
353
+ "language_model.model.layers.8.post_attention_layernorm.weight": "model.safetensors",
354
+ "language_model.model.layers.8.self_attn.k_proj.biases": "model.safetensors",
355
+ "language_model.model.layers.8.self_attn.k_proj.scales": "model.safetensors",
356
+ "language_model.model.layers.8.self_attn.k_proj.weight": "model.safetensors",
357
+ "language_model.model.layers.8.self_attn.o_proj.biases": "model.safetensors",
358
+ "language_model.model.layers.8.self_attn.o_proj.scales": "model.safetensors",
359
+ "language_model.model.layers.8.self_attn.o_proj.weight": "model.safetensors",
360
+ "language_model.model.layers.8.self_attn.q_proj.biases": "model.safetensors",
361
+ "language_model.model.layers.8.self_attn.q_proj.scales": "model.safetensors",
362
+ "language_model.model.layers.8.self_attn.q_proj.weight": "model.safetensors",
363
+ "language_model.model.layers.8.self_attn.v_proj.biases": "model.safetensors",
364
+ "language_model.model.layers.8.self_attn.v_proj.scales": "model.safetensors",
365
+ "language_model.model.layers.8.self_attn.v_proj.weight": "model.safetensors",
366
+ "language_model.model.layers.9.input_layernorm.weight": "model.safetensors",
367
+ "language_model.model.layers.9.mlp.gate.weight": "model.safetensors",
368
+ "language_model.model.layers.9.mlp.shared_experts.down_proj.biases": "model.safetensors",
369
+ "language_model.model.layers.9.mlp.shared_experts.down_proj.scales": "model.safetensors",
370
+ "language_model.model.layers.9.mlp.shared_experts.down_proj.weight": "model.safetensors",
371
+ "language_model.model.layers.9.mlp.shared_experts.gate_proj.biases": "model.safetensors",
372
+ "language_model.model.layers.9.mlp.shared_experts.gate_proj.scales": "model.safetensors",
373
+ "language_model.model.layers.9.mlp.shared_experts.gate_proj.weight": "model.safetensors",
374
+ "language_model.model.layers.9.mlp.shared_experts.up_proj.biases": "model.safetensors",
375
+ "language_model.model.layers.9.mlp.shared_experts.up_proj.scales": "model.safetensors",
376
+ "language_model.model.layers.9.mlp.shared_experts.up_proj.weight": "model.safetensors",
377
+ "language_model.model.layers.9.mlp.switch_mlp.down_proj.biases": "model.safetensors",
378
+ "language_model.model.layers.9.mlp.switch_mlp.down_proj.scales": "model.safetensors",
379
+ "language_model.model.layers.9.mlp.switch_mlp.down_proj.weight": "model.safetensors",
380
+ "language_model.model.layers.9.mlp.switch_mlp.gate_proj.biases": "model.safetensors",
381
+ "language_model.model.layers.9.mlp.switch_mlp.gate_proj.scales": "model.safetensors",
382
+ "language_model.model.layers.9.mlp.switch_mlp.gate_proj.weight": "model.safetensors",
383
+ "language_model.model.layers.9.mlp.switch_mlp.up_proj.biases": "model.safetensors",
384
+ "language_model.model.layers.9.mlp.switch_mlp.up_proj.scales": "model.safetensors",
385
+ "language_model.model.layers.9.mlp.switch_mlp.up_proj.weight": "model.safetensors",
386
+ "language_model.model.layers.9.post_attention_layernorm.weight": "model.safetensors",
387
+ "language_model.model.layers.9.self_attn.k_proj.biases": "model.safetensors",
388
+ "language_model.model.layers.9.self_attn.k_proj.scales": "model.safetensors",
389
+ "language_model.model.layers.9.self_attn.k_proj.weight": "model.safetensors",
390
+ "language_model.model.layers.9.self_attn.o_proj.biases": "model.safetensors",
391
+ "language_model.model.layers.9.self_attn.o_proj.scales": "model.safetensors",
392
+ "language_model.model.layers.9.self_attn.o_proj.weight": "model.safetensors",
393
+ "language_model.model.layers.9.self_attn.q_proj.biases": "model.safetensors",
394
+ "language_model.model.layers.9.self_attn.q_proj.scales": "model.safetensors",
395
+ "language_model.model.layers.9.self_attn.q_proj.weight": "model.safetensors",
396
+ "language_model.model.layers.9.self_attn.v_proj.biases": "model.safetensors",
397
+ "language_model.model.layers.9.self_attn.v_proj.scales": "model.safetensors",
398
+ "language_model.model.layers.9.self_attn.v_proj.weight": "model.safetensors",
399
+ "language_model.model.norm.weight": "model.safetensors",
400
+ "projector.layers.0.bias": "model.safetensors",
401
+ "projector.layers.0.biases": "model.safetensors",
402
+ "projector.layers.0.scales": "model.safetensors",
403
+ "projector.layers.0.weight": "model.safetensors",
404
+ "projector.layers.2.bias": "model.safetensors",
405
+ "projector.layers.2.biases": "model.safetensors",
406
+ "projector.layers.2.scales": "model.safetensors",
407
+ "projector.layers.2.weight": "model.safetensors",
408
+ "view_separator": "model.safetensors",
409
+ "vision.vision_tower.attn_pool.kv.bias": "model.safetensors",
410
+ "vision.vision_tower.attn_pool.kv.biases": "model.safetensors",
411
+ "vision.vision_tower.attn_pool.kv.scales": "model.safetensors",
412
+ "vision.vision_tower.attn_pool.kv.weight": "model.safetensors",
413
+ "vision.vision_tower.attn_pool.latent": "model.safetensors",
414
+ "vision.vision_tower.attn_pool.mlp.fc1.bias": "model.safetensors",
415
+ "vision.vision_tower.attn_pool.mlp.fc1.biases": "model.safetensors",
416
+ "vision.vision_tower.attn_pool.mlp.fc1.scales": "model.safetensors",
417
+ "vision.vision_tower.attn_pool.mlp.fc1.weight": "model.safetensors",
418
+ "vision.vision_tower.attn_pool.mlp.fc2.bias": "model.safetensors",
419
+ "vision.vision_tower.attn_pool.mlp.fc2.weight": "model.safetensors",
420
+ "vision.vision_tower.attn_pool.norm.bias": "model.safetensors",
421
+ "vision.vision_tower.attn_pool.norm.weight": "model.safetensors",
422
+ "vision.vision_tower.attn_pool.proj.bias": "model.safetensors",
423
+ "vision.vision_tower.attn_pool.proj.biases": "model.safetensors",
424
+ "vision.vision_tower.attn_pool.proj.scales": "model.safetensors",
425
+ "vision.vision_tower.attn_pool.proj.weight": "model.safetensors",
426
+ "vision.vision_tower.attn_pool.q.bias": "model.safetensors",
427
+ "vision.vision_tower.attn_pool.q.biases": "model.safetensors",
428
+ "vision.vision_tower.attn_pool.q.scales": "model.safetensors",
429
+ "vision.vision_tower.attn_pool.q.weight": "model.safetensors",
430
+ "vision.vision_tower.blocks.0.attn.proj.bias": "model.safetensors",
431
+ "vision.vision_tower.blocks.0.attn.proj.biases": "model.safetensors",
432
+ "vision.vision_tower.blocks.0.attn.proj.scales": "model.safetensors",
433
+ "vision.vision_tower.blocks.0.attn.proj.weight": "model.safetensors",
434
+ "vision.vision_tower.blocks.0.attn.qkv.bias": "model.safetensors",
435
+ "vision.vision_tower.blocks.0.attn.qkv.biases": "model.safetensors",
436
+ "vision.vision_tower.blocks.0.attn.qkv.scales": "model.safetensors",
437
+ "vision.vision_tower.blocks.0.attn.qkv.weight": "model.safetensors",
438
+ "vision.vision_tower.blocks.0.mlp.fc1.bias": "model.safetensors",
439
+ "vision.vision_tower.blocks.0.mlp.fc1.biases": "model.safetensors",
440
+ "vision.vision_tower.blocks.0.mlp.fc1.scales": "model.safetensors",
441
+ "vision.vision_tower.blocks.0.mlp.fc1.weight": "model.safetensors",
442
+ "vision.vision_tower.blocks.0.mlp.fc2.bias": "model.safetensors",
443
+ "vision.vision_tower.blocks.0.mlp.fc2.weight": "model.safetensors",
444
+ "vision.vision_tower.blocks.0.norm1.bias": "model.safetensors",
445
+ "vision.vision_tower.blocks.0.norm1.weight": "model.safetensors",
446
+ "vision.vision_tower.blocks.0.norm2.bias": "model.safetensors",
447
+ "vision.vision_tower.blocks.0.norm2.weight": "model.safetensors",
448
+ "vision.vision_tower.blocks.1.attn.proj.bias": "model.safetensors",
449
+ "vision.vision_tower.blocks.1.attn.proj.biases": "model.safetensors",
450
+ "vision.vision_tower.blocks.1.attn.proj.scales": "model.safetensors",
451
+ "vision.vision_tower.blocks.1.attn.proj.weight": "model.safetensors",
452
+ "vision.vision_tower.blocks.1.attn.qkv.bias": "model.safetensors",
453
+ "vision.vision_tower.blocks.1.attn.qkv.biases": "model.safetensors",
454
+ "vision.vision_tower.blocks.1.attn.qkv.scales": "model.safetensors",
455
+ "vision.vision_tower.blocks.1.attn.qkv.weight": "model.safetensors",
456
+ "vision.vision_tower.blocks.1.mlp.fc1.bias": "model.safetensors",
457
+ "vision.vision_tower.blocks.1.mlp.fc1.biases": "model.safetensors",
458
+ "vision.vision_tower.blocks.1.mlp.fc1.scales": "model.safetensors",
459
+ "vision.vision_tower.blocks.1.mlp.fc1.weight": "model.safetensors",
460
+ "vision.vision_tower.blocks.1.mlp.fc2.bias": "model.safetensors",
461
+ "vision.vision_tower.blocks.1.mlp.fc2.weight": "model.safetensors",
462
+ "vision.vision_tower.blocks.1.norm1.bias": "model.safetensors",
463
+ "vision.vision_tower.blocks.1.norm1.weight": "model.safetensors",
464
+ "vision.vision_tower.blocks.1.norm2.bias": "model.safetensors",
465
+ "vision.vision_tower.blocks.1.norm2.weight": "model.safetensors",
466
+ "vision.vision_tower.blocks.10.attn.proj.bias": "model.safetensors",
467
+ "vision.vision_tower.blocks.10.attn.proj.biases": "model.safetensors",
468
+ "vision.vision_tower.blocks.10.attn.proj.scales": "model.safetensors",
469
+ "vision.vision_tower.blocks.10.attn.proj.weight": "model.safetensors",
470
+ "vision.vision_tower.blocks.10.attn.qkv.bias": "model.safetensors",
471
+ "vision.vision_tower.blocks.10.attn.qkv.biases": "model.safetensors",
472
+ "vision.vision_tower.blocks.10.attn.qkv.scales": "model.safetensors",
473
+ "vision.vision_tower.blocks.10.attn.qkv.weight": "model.safetensors",
474
+ "vision.vision_tower.blocks.10.mlp.fc1.bias": "model.safetensors",
475
+ "vision.vision_tower.blocks.10.mlp.fc1.biases": "model.safetensors",
476
+ "vision.vision_tower.blocks.10.mlp.fc1.scales": "model.safetensors",
477
+ "vision.vision_tower.blocks.10.mlp.fc1.weight": "model.safetensors",
478
+ "vision.vision_tower.blocks.10.mlp.fc2.bias": "model.safetensors",
479
+ "vision.vision_tower.blocks.10.mlp.fc2.weight": "model.safetensors",
480
+ "vision.vision_tower.blocks.10.norm1.bias": "model.safetensors",
481
+ "vision.vision_tower.blocks.10.norm1.weight": "model.safetensors",
482
+ "vision.vision_tower.blocks.10.norm2.bias": "model.safetensors",
483
+ "vision.vision_tower.blocks.10.norm2.weight": "model.safetensors",
484
+ "vision.vision_tower.blocks.11.attn.proj.bias": "model.safetensors",
485
+ "vision.vision_tower.blocks.11.attn.proj.biases": "model.safetensors",
486
+ "vision.vision_tower.blocks.11.attn.proj.scales": "model.safetensors",
487
+ "vision.vision_tower.blocks.11.attn.proj.weight": "model.safetensors",
488
+ "vision.vision_tower.blocks.11.attn.qkv.bias": "model.safetensors",
489
+ "vision.vision_tower.blocks.11.attn.qkv.biases": "model.safetensors",
490
+ "vision.vision_tower.blocks.11.attn.qkv.scales": "model.safetensors",
491
+ "vision.vision_tower.blocks.11.attn.qkv.weight": "model.safetensors",
492
+ "vision.vision_tower.blocks.11.mlp.fc1.bias": "model.safetensors",
493
+ "vision.vision_tower.blocks.11.mlp.fc1.biases": "model.safetensors",
494
+ "vision.vision_tower.blocks.11.mlp.fc1.scales": "model.safetensors",
495
+ "vision.vision_tower.blocks.11.mlp.fc1.weight": "model.safetensors",
496
+ "vision.vision_tower.blocks.11.mlp.fc2.bias": "model.safetensors",
497
+ "vision.vision_tower.blocks.11.mlp.fc2.weight": "model.safetensors",
498
+ "vision.vision_tower.blocks.11.norm1.bias": "model.safetensors",
499
+ "vision.vision_tower.blocks.11.norm1.weight": "model.safetensors",
500
+ "vision.vision_tower.blocks.11.norm2.bias": "model.safetensors",
501
+ "vision.vision_tower.blocks.11.norm2.weight": "model.safetensors",
502
+ "vision.vision_tower.blocks.12.attn.proj.bias": "model.safetensors",
503
+ "vision.vision_tower.blocks.12.attn.proj.biases": "model.safetensors",
504
+ "vision.vision_tower.blocks.12.attn.proj.scales": "model.safetensors",
505
+ "vision.vision_tower.blocks.12.attn.proj.weight": "model.safetensors",
506
+ "vision.vision_tower.blocks.12.attn.qkv.bias": "model.safetensors",
507
+ "vision.vision_tower.blocks.12.attn.qkv.biases": "model.safetensors",
508
+ "vision.vision_tower.blocks.12.attn.qkv.scales": "model.safetensors",
509
+ "vision.vision_tower.blocks.12.attn.qkv.weight": "model.safetensors",
510
+ "vision.vision_tower.blocks.12.mlp.fc1.bias": "model.safetensors",
511
+ "vision.vision_tower.blocks.12.mlp.fc1.biases": "model.safetensors",
512
+ "vision.vision_tower.blocks.12.mlp.fc1.scales": "model.safetensors",
513
+ "vision.vision_tower.blocks.12.mlp.fc1.weight": "model.safetensors",
514
+ "vision.vision_tower.blocks.12.mlp.fc2.bias": "model.safetensors",
515
+ "vision.vision_tower.blocks.12.mlp.fc2.weight": "model.safetensors",
516
+ "vision.vision_tower.blocks.12.norm1.bias": "model.safetensors",
517
+ "vision.vision_tower.blocks.12.norm1.weight": "model.safetensors",
518
+ "vision.vision_tower.blocks.12.norm2.bias": "model.safetensors",
519
+ "vision.vision_tower.blocks.12.norm2.weight": "model.safetensors",
520
+ "vision.vision_tower.blocks.13.attn.proj.bias": "model.safetensors",
521
+ "vision.vision_tower.blocks.13.attn.proj.biases": "model.safetensors",
522
+ "vision.vision_tower.blocks.13.attn.proj.scales": "model.safetensors",
523
+ "vision.vision_tower.blocks.13.attn.proj.weight": "model.safetensors",
524
+ "vision.vision_tower.blocks.13.attn.qkv.bias": "model.safetensors",
525
+ "vision.vision_tower.blocks.13.attn.qkv.biases": "model.safetensors",
526
+ "vision.vision_tower.blocks.13.attn.qkv.scales": "model.safetensors",
527
+ "vision.vision_tower.blocks.13.attn.qkv.weight": "model.safetensors",
528
+ "vision.vision_tower.blocks.13.mlp.fc1.bias": "model.safetensors",
529
+ "vision.vision_tower.blocks.13.mlp.fc1.biases": "model.safetensors",
530
+ "vision.vision_tower.blocks.13.mlp.fc1.scales": "model.safetensors",
531
+ "vision.vision_tower.blocks.13.mlp.fc1.weight": "model.safetensors",
532
+ "vision.vision_tower.blocks.13.mlp.fc2.bias": "model.safetensors",
533
+ "vision.vision_tower.blocks.13.mlp.fc2.weight": "model.safetensors",
534
+ "vision.vision_tower.blocks.13.norm1.bias": "model.safetensors",
535
+ "vision.vision_tower.blocks.13.norm1.weight": "model.safetensors",
536
+ "vision.vision_tower.blocks.13.norm2.bias": "model.safetensors",
537
+ "vision.vision_tower.blocks.13.norm2.weight": "model.safetensors",
538
+ "vision.vision_tower.blocks.14.attn.proj.bias": "model.safetensors",
539
+ "vision.vision_tower.blocks.14.attn.proj.biases": "model.safetensors",
540
+ "vision.vision_tower.blocks.14.attn.proj.scales": "model.safetensors",
541
+ "vision.vision_tower.blocks.14.attn.proj.weight": "model.safetensors",
542
+ "vision.vision_tower.blocks.14.attn.qkv.bias": "model.safetensors",
543
+ "vision.vision_tower.blocks.14.attn.qkv.biases": "model.safetensors",
544
+ "vision.vision_tower.blocks.14.attn.qkv.scales": "model.safetensors",
545
+ "vision.vision_tower.blocks.14.attn.qkv.weight": "model.safetensors",
546
+ "vision.vision_tower.blocks.14.mlp.fc1.bias": "model.safetensors",
547
+ "vision.vision_tower.blocks.14.mlp.fc1.biases": "model.safetensors",
548
+ "vision.vision_tower.blocks.14.mlp.fc1.scales": "model.safetensors",
549
+ "vision.vision_tower.blocks.14.mlp.fc1.weight": "model.safetensors",
550
+ "vision.vision_tower.blocks.14.mlp.fc2.bias": "model.safetensors",
551
+ "vision.vision_tower.blocks.14.mlp.fc2.weight": "model.safetensors",
552
+ "vision.vision_tower.blocks.14.norm1.bias": "model.safetensors",
553
+ "vision.vision_tower.blocks.14.norm1.weight": "model.safetensors",
554
+ "vision.vision_tower.blocks.14.norm2.bias": "model.safetensors",
555
+ "vision.vision_tower.blocks.14.norm2.weight": "model.safetensors",
556
+ "vision.vision_tower.blocks.15.attn.proj.bias": "model.safetensors",
557
+ "vision.vision_tower.blocks.15.attn.proj.biases": "model.safetensors",
558
+ "vision.vision_tower.blocks.15.attn.proj.scales": "model.safetensors",
559
+ "vision.vision_tower.blocks.15.attn.proj.weight": "model.safetensors",
560
+ "vision.vision_tower.blocks.15.attn.qkv.bias": "model.safetensors",
561
+ "vision.vision_tower.blocks.15.attn.qkv.biases": "model.safetensors",
562
+ "vision.vision_tower.blocks.15.attn.qkv.scales": "model.safetensors",
563
+ "vision.vision_tower.blocks.15.attn.qkv.weight": "model.safetensors",
564
+ "vision.vision_tower.blocks.15.mlp.fc1.bias": "model.safetensors",
565
+ "vision.vision_tower.blocks.15.mlp.fc1.biases": "model.safetensors",
566
+ "vision.vision_tower.blocks.15.mlp.fc1.scales": "model.safetensors",
567
+ "vision.vision_tower.blocks.15.mlp.fc1.weight": "model.safetensors",
568
+ "vision.vision_tower.blocks.15.mlp.fc2.bias": "model.safetensors",
569
+ "vision.vision_tower.blocks.15.mlp.fc2.weight": "model.safetensors",
570
+ "vision.vision_tower.blocks.15.norm1.bias": "model.safetensors",
571
+ "vision.vision_tower.blocks.15.norm1.weight": "model.safetensors",
572
+ "vision.vision_tower.blocks.15.norm2.bias": "model.safetensors",
573
+ "vision.vision_tower.blocks.15.norm2.weight": "model.safetensors",
574
+ "vision.vision_tower.blocks.16.attn.proj.bias": "model.safetensors",
575
+ "vision.vision_tower.blocks.16.attn.proj.biases": "model.safetensors",
576
+ "vision.vision_tower.blocks.16.attn.proj.scales": "model.safetensors",
577
+ "vision.vision_tower.blocks.16.attn.proj.weight": "model.safetensors",
578
+ "vision.vision_tower.blocks.16.attn.qkv.bias": "model.safetensors",
579
+ "vision.vision_tower.blocks.16.attn.qkv.biases": "model.safetensors",
580
+ "vision.vision_tower.blocks.16.attn.qkv.scales": "model.safetensors",
581
+ "vision.vision_tower.blocks.16.attn.qkv.weight": "model.safetensors",
582
+ "vision.vision_tower.blocks.16.mlp.fc1.bias": "model.safetensors",
583
+ "vision.vision_tower.blocks.16.mlp.fc1.biases": "model.safetensors",
584
+ "vision.vision_tower.blocks.16.mlp.fc1.scales": "model.safetensors",
585
+ "vision.vision_tower.blocks.16.mlp.fc1.weight": "model.safetensors",
586
+ "vision.vision_tower.blocks.16.mlp.fc2.bias": "model.safetensors",
587
+ "vision.vision_tower.blocks.16.mlp.fc2.weight": "model.safetensors",
588
+ "vision.vision_tower.blocks.16.norm1.bias": "model.safetensors",
589
+ "vision.vision_tower.blocks.16.norm1.weight": "model.safetensors",
590
+ "vision.vision_tower.blocks.16.norm2.bias": "model.safetensors",
591
+ "vision.vision_tower.blocks.16.norm2.weight": "model.safetensors",
592
+ "vision.vision_tower.blocks.17.attn.proj.bias": "model.safetensors",
593
+ "vision.vision_tower.blocks.17.attn.proj.biases": "model.safetensors",
594
+ "vision.vision_tower.blocks.17.attn.proj.scales": "model.safetensors",
595
+ "vision.vision_tower.blocks.17.attn.proj.weight": "model.safetensors",
596
+ "vision.vision_tower.blocks.17.attn.qkv.bias": "model.safetensors",
597
+ "vision.vision_tower.blocks.17.attn.qkv.biases": "model.safetensors",
598
+ "vision.vision_tower.blocks.17.attn.qkv.scales": "model.safetensors",
599
+ "vision.vision_tower.blocks.17.attn.qkv.weight": "model.safetensors",
600
+ "vision.vision_tower.blocks.17.mlp.fc1.bias": "model.safetensors",
601
+ "vision.vision_tower.blocks.17.mlp.fc1.biases": "model.safetensors",
602
+ "vision.vision_tower.blocks.17.mlp.fc1.scales": "model.safetensors",
603
+ "vision.vision_tower.blocks.17.mlp.fc1.weight": "model.safetensors",
604
+ "vision.vision_tower.blocks.17.mlp.fc2.bias": "model.safetensors",
605
+ "vision.vision_tower.blocks.17.mlp.fc2.weight": "model.safetensors",
606
+ "vision.vision_tower.blocks.17.norm1.bias": "model.safetensors",
607
+ "vision.vision_tower.blocks.17.norm1.weight": "model.safetensors",
608
+ "vision.vision_tower.blocks.17.norm2.bias": "model.safetensors",
609
+ "vision.vision_tower.blocks.17.norm2.weight": "model.safetensors",
610
+ "vision.vision_tower.blocks.18.attn.proj.bias": "model.safetensors",
611
+ "vision.vision_tower.blocks.18.attn.proj.biases": "model.safetensors",
612
+ "vision.vision_tower.blocks.18.attn.proj.scales": "model.safetensors",
613
+ "vision.vision_tower.blocks.18.attn.proj.weight": "model.safetensors",
614
+ "vision.vision_tower.blocks.18.attn.qkv.bias": "model.safetensors",
615
+ "vision.vision_tower.blocks.18.attn.qkv.biases": "model.safetensors",
616
+ "vision.vision_tower.blocks.18.attn.qkv.scales": "model.safetensors",
617
+ "vision.vision_tower.blocks.18.attn.qkv.weight": "model.safetensors",
618
+ "vision.vision_tower.blocks.18.mlp.fc1.bias": "model.safetensors",
619
+ "vision.vision_tower.blocks.18.mlp.fc1.biases": "model.safetensors",
620
+ "vision.vision_tower.blocks.18.mlp.fc1.scales": "model.safetensors",
621
+ "vision.vision_tower.blocks.18.mlp.fc1.weight": "model.safetensors",
622
+ "vision.vision_tower.blocks.18.mlp.fc2.bias": "model.safetensors",
623
+ "vision.vision_tower.blocks.18.mlp.fc2.weight": "model.safetensors",
624
+ "vision.vision_tower.blocks.18.norm1.bias": "model.safetensors",
625
+ "vision.vision_tower.blocks.18.norm1.weight": "model.safetensors",
626
+ "vision.vision_tower.blocks.18.norm2.bias": "model.safetensors",
627
+ "vision.vision_tower.blocks.18.norm2.weight": "model.safetensors",
628
+ "vision.vision_tower.blocks.19.attn.proj.bias": "model.safetensors",
629
+ "vision.vision_tower.blocks.19.attn.proj.biases": "model.safetensors",
630
+ "vision.vision_tower.blocks.19.attn.proj.scales": "model.safetensors",
631
+ "vision.vision_tower.blocks.19.attn.proj.weight": "model.safetensors",
632
+ "vision.vision_tower.blocks.19.attn.qkv.bias": "model.safetensors",
633
+ "vision.vision_tower.blocks.19.attn.qkv.biases": "model.safetensors",
634
+ "vision.vision_tower.blocks.19.attn.qkv.scales": "model.safetensors",
635
+ "vision.vision_tower.blocks.19.attn.qkv.weight": "model.safetensors",
636
+ "vision.vision_tower.blocks.19.mlp.fc1.bias": "model.safetensors",
637
+ "vision.vision_tower.blocks.19.mlp.fc1.biases": "model.safetensors",
638
+ "vision.vision_tower.blocks.19.mlp.fc1.scales": "model.safetensors",
639
+ "vision.vision_tower.blocks.19.mlp.fc1.weight": "model.safetensors",
640
+ "vision.vision_tower.blocks.19.mlp.fc2.bias": "model.safetensors",
641
+ "vision.vision_tower.blocks.19.mlp.fc2.weight": "model.safetensors",
642
+ "vision.vision_tower.blocks.19.norm1.bias": "model.safetensors",
643
+ "vision.vision_tower.blocks.19.norm1.weight": "model.safetensors",
644
+ "vision.vision_tower.blocks.19.norm2.bias": "model.safetensors",
645
+ "vision.vision_tower.blocks.19.norm2.weight": "model.safetensors",
646
+ "vision.vision_tower.blocks.2.attn.proj.bias": "model.safetensors",
647
+ "vision.vision_tower.blocks.2.attn.proj.biases": "model.safetensors",
648
+ "vision.vision_tower.blocks.2.attn.proj.scales": "model.safetensors",
649
+ "vision.vision_tower.blocks.2.attn.proj.weight": "model.safetensors",
650
+ "vision.vision_tower.blocks.2.attn.qkv.bias": "model.safetensors",
651
+ "vision.vision_tower.blocks.2.attn.qkv.biases": "model.safetensors",
652
+ "vision.vision_tower.blocks.2.attn.qkv.scales": "model.safetensors",
653
+ "vision.vision_tower.blocks.2.attn.qkv.weight": "model.safetensors",
654
+ "vision.vision_tower.blocks.2.mlp.fc1.bias": "model.safetensors",
655
+ "vision.vision_tower.blocks.2.mlp.fc1.biases": "model.safetensors",
656
+ "vision.vision_tower.blocks.2.mlp.fc1.scales": "model.safetensors",
657
+ "vision.vision_tower.blocks.2.mlp.fc1.weight": "model.safetensors",
658
+ "vision.vision_tower.blocks.2.mlp.fc2.bias": "model.safetensors",
659
+ "vision.vision_tower.blocks.2.mlp.fc2.weight": "model.safetensors",
660
+ "vision.vision_tower.blocks.2.norm1.bias": "model.safetensors",
661
+ "vision.vision_tower.blocks.2.norm1.weight": "model.safetensors",
662
+ "vision.vision_tower.blocks.2.norm2.bias": "model.safetensors",
663
+ "vision.vision_tower.blocks.2.norm2.weight": "model.safetensors",
664
+ "vision.vision_tower.blocks.20.attn.proj.bias": "model.safetensors",
665
+ "vision.vision_tower.blocks.20.attn.proj.biases": "model.safetensors",
666
+ "vision.vision_tower.blocks.20.attn.proj.scales": "model.safetensors",
667
+ "vision.vision_tower.blocks.20.attn.proj.weight": "model.safetensors",
668
+ "vision.vision_tower.blocks.20.attn.qkv.bias": "model.safetensors",
669
+ "vision.vision_tower.blocks.20.attn.qkv.biases": "model.safetensors",
670
+ "vision.vision_tower.blocks.20.attn.qkv.scales": "model.safetensors",
671
+ "vision.vision_tower.blocks.20.attn.qkv.weight": "model.safetensors",
672
+ "vision.vision_tower.blocks.20.mlp.fc1.bias": "model.safetensors",
673
+ "vision.vision_tower.blocks.20.mlp.fc1.biases": "model.safetensors",
674
+ "vision.vision_tower.blocks.20.mlp.fc1.scales": "model.safetensors",
675
+ "vision.vision_tower.blocks.20.mlp.fc1.weight": "model.safetensors",
676
+ "vision.vision_tower.blocks.20.mlp.fc2.bias": "model.safetensors",
677
+ "vision.vision_tower.blocks.20.mlp.fc2.weight": "model.safetensors",
678
+ "vision.vision_tower.blocks.20.norm1.bias": "model.safetensors",
679
+ "vision.vision_tower.blocks.20.norm1.weight": "model.safetensors",
680
+ "vision.vision_tower.blocks.20.norm2.bias": "model.safetensors",
681
+ "vision.vision_tower.blocks.20.norm2.weight": "model.safetensors",
682
+ "vision.vision_tower.blocks.21.attn.proj.bias": "model.safetensors",
683
+ "vision.vision_tower.blocks.21.attn.proj.biases": "model.safetensors",
684
+ "vision.vision_tower.blocks.21.attn.proj.scales": "model.safetensors",
685
+ "vision.vision_tower.blocks.21.attn.proj.weight": "model.safetensors",
686
+ "vision.vision_tower.blocks.21.attn.qkv.bias": "model.safetensors",
687
+ "vision.vision_tower.blocks.21.attn.qkv.biases": "model.safetensors",
688
+ "vision.vision_tower.blocks.21.attn.qkv.scales": "model.safetensors",
689
+ "vision.vision_tower.blocks.21.attn.qkv.weight": "model.safetensors",
690
+ "vision.vision_tower.blocks.21.mlp.fc1.bias": "model.safetensors",
691
+ "vision.vision_tower.blocks.21.mlp.fc1.biases": "model.safetensors",
692
+ "vision.vision_tower.blocks.21.mlp.fc1.scales": "model.safetensors",
693
+ "vision.vision_tower.blocks.21.mlp.fc1.weight": "model.safetensors",
694
+ "vision.vision_tower.blocks.21.mlp.fc2.bias": "model.safetensors",
695
+ "vision.vision_tower.blocks.21.mlp.fc2.weight": "model.safetensors",
696
+ "vision.vision_tower.blocks.21.norm1.bias": "model.safetensors",
697
+ "vision.vision_tower.blocks.21.norm1.weight": "model.safetensors",
698
+ "vision.vision_tower.blocks.21.norm2.bias": "model.safetensors",
699
+ "vision.vision_tower.blocks.21.norm2.weight": "model.safetensors",
700
+ "vision.vision_tower.blocks.22.attn.proj.bias": "model.safetensors",
701
+ "vision.vision_tower.blocks.22.attn.proj.biases": "model.safetensors",
702
+ "vision.vision_tower.blocks.22.attn.proj.scales": "model.safetensors",
703
+ "vision.vision_tower.blocks.22.attn.proj.weight": "model.safetensors",
704
+ "vision.vision_tower.blocks.22.attn.qkv.bias": "model.safetensors",
705
+ "vision.vision_tower.blocks.22.attn.qkv.biases": "model.safetensors",
706
+ "vision.vision_tower.blocks.22.attn.qkv.scales": "model.safetensors",
707
+ "vision.vision_tower.blocks.22.attn.qkv.weight": "model.safetensors",
708
+ "vision.vision_tower.blocks.22.mlp.fc1.bias": "model.safetensors",
709
+ "vision.vision_tower.blocks.22.mlp.fc1.biases": "model.safetensors",
710
+ "vision.vision_tower.blocks.22.mlp.fc1.scales": "model.safetensors",
711
+ "vision.vision_tower.blocks.22.mlp.fc1.weight": "model.safetensors",
712
+ "vision.vision_tower.blocks.22.mlp.fc2.bias": "model.safetensors",
713
+ "vision.vision_tower.blocks.22.mlp.fc2.weight": "model.safetensors",
714
+ "vision.vision_tower.blocks.22.norm1.bias": "model.safetensors",
715
+ "vision.vision_tower.blocks.22.norm1.weight": "model.safetensors",
716
+ "vision.vision_tower.blocks.22.norm2.bias": "model.safetensors",
717
+ "vision.vision_tower.blocks.22.norm2.weight": "model.safetensors",
718
+ "vision.vision_tower.blocks.23.attn.proj.bias": "model.safetensors",
719
+ "vision.vision_tower.blocks.23.attn.proj.biases": "model.safetensors",
720
+ "vision.vision_tower.blocks.23.attn.proj.scales": "model.safetensors",
721
+ "vision.vision_tower.blocks.23.attn.proj.weight": "model.safetensors",
722
+ "vision.vision_tower.blocks.23.attn.qkv.bias": "model.safetensors",
723
+ "vision.vision_tower.blocks.23.attn.qkv.biases": "model.safetensors",
724
+ "vision.vision_tower.blocks.23.attn.qkv.scales": "model.safetensors",
725
+ "vision.vision_tower.blocks.23.attn.qkv.weight": "model.safetensors",
726
+ "vision.vision_tower.blocks.23.mlp.fc1.bias": "model.safetensors",
727
+ "vision.vision_tower.blocks.23.mlp.fc1.biases": "model.safetensors",
728
+ "vision.vision_tower.blocks.23.mlp.fc1.scales": "model.safetensors",
729
+ "vision.vision_tower.blocks.23.mlp.fc1.weight": "model.safetensors",
730
+ "vision.vision_tower.blocks.23.mlp.fc2.bias": "model.safetensors",
731
+ "vision.vision_tower.blocks.23.mlp.fc2.weight": "model.safetensors",
732
+ "vision.vision_tower.blocks.23.norm1.bias": "model.safetensors",
733
+ "vision.vision_tower.blocks.23.norm1.weight": "model.safetensors",
734
+ "vision.vision_tower.blocks.23.norm2.bias": "model.safetensors",
735
+ "vision.vision_tower.blocks.23.norm2.weight": "model.safetensors",
736
+ "vision.vision_tower.blocks.24.attn.proj.bias": "model.safetensors",
737
+ "vision.vision_tower.blocks.24.attn.proj.biases": "model.safetensors",
738
+ "vision.vision_tower.blocks.24.attn.proj.scales": "model.safetensors",
739
+ "vision.vision_tower.blocks.24.attn.proj.weight": "model.safetensors",
740
+ "vision.vision_tower.blocks.24.attn.qkv.bias": "model.safetensors",
741
+ "vision.vision_tower.blocks.24.attn.qkv.biases": "model.safetensors",
742
+ "vision.vision_tower.blocks.24.attn.qkv.scales": "model.safetensors",
743
+ "vision.vision_tower.blocks.24.attn.qkv.weight": "model.safetensors",
744
+ "vision.vision_tower.blocks.24.mlp.fc1.bias": "model.safetensors",
745
+ "vision.vision_tower.blocks.24.mlp.fc1.biases": "model.safetensors",
746
+ "vision.vision_tower.blocks.24.mlp.fc1.scales": "model.safetensors",
747
+ "vision.vision_tower.blocks.24.mlp.fc1.weight": "model.safetensors",
748
+ "vision.vision_tower.blocks.24.mlp.fc2.bias": "model.safetensors",
749
+ "vision.vision_tower.blocks.24.mlp.fc2.weight": "model.safetensors",
750
+ "vision.vision_tower.blocks.24.norm1.bias": "model.safetensors",
751
+ "vision.vision_tower.blocks.24.norm1.weight": "model.safetensors",
752
+ "vision.vision_tower.blocks.24.norm2.bias": "model.safetensors",
753
+ "vision.vision_tower.blocks.24.norm2.weight": "model.safetensors",
754
+ "vision.vision_tower.blocks.25.attn.proj.bias": "model.safetensors",
755
+ "vision.vision_tower.blocks.25.attn.proj.biases": "model.safetensors",
756
+ "vision.vision_tower.blocks.25.attn.proj.scales": "model.safetensors",
757
+ "vision.vision_tower.blocks.25.attn.proj.weight": "model.safetensors",
758
+ "vision.vision_tower.blocks.25.attn.qkv.bias": "model.safetensors",
759
+ "vision.vision_tower.blocks.25.attn.qkv.biases": "model.safetensors",
760
+ "vision.vision_tower.blocks.25.attn.qkv.scales": "model.safetensors",
761
+ "vision.vision_tower.blocks.25.attn.qkv.weight": "model.safetensors",
762
+ "vision.vision_tower.blocks.25.mlp.fc1.bias": "model.safetensors",
763
+ "vision.vision_tower.blocks.25.mlp.fc1.biases": "model.safetensors",
764
+ "vision.vision_tower.blocks.25.mlp.fc1.scales": "model.safetensors",
765
+ "vision.vision_tower.blocks.25.mlp.fc1.weight": "model.safetensors",
766
+ "vision.vision_tower.blocks.25.mlp.fc2.bias": "model.safetensors",
767
+ "vision.vision_tower.blocks.25.mlp.fc2.weight": "model.safetensors",
768
+ "vision.vision_tower.blocks.25.norm1.bias": "model.safetensors",
769
+ "vision.vision_tower.blocks.25.norm1.weight": "model.safetensors",
770
+ "vision.vision_tower.blocks.25.norm2.bias": "model.safetensors",
771
+ "vision.vision_tower.blocks.25.norm2.weight": "model.safetensors",
772
+ "vision.vision_tower.blocks.26.attn.proj.bias": "model.safetensors",
773
+ "vision.vision_tower.blocks.26.attn.proj.biases": "model.safetensors",
774
+ "vision.vision_tower.blocks.26.attn.proj.scales": "model.safetensors",
775
+ "vision.vision_tower.blocks.26.attn.proj.weight": "model.safetensors",
776
+ "vision.vision_tower.blocks.26.attn.qkv.bias": "model.safetensors",
777
+ "vision.vision_tower.blocks.26.attn.qkv.biases": "model.safetensors",
778
+ "vision.vision_tower.blocks.26.attn.qkv.scales": "model.safetensors",
779
+ "vision.vision_tower.blocks.26.attn.qkv.weight": "model.safetensors",
780
+ "vision.vision_tower.blocks.26.mlp.fc1.bias": "model.safetensors",
781
+ "vision.vision_tower.blocks.26.mlp.fc1.biases": "model.safetensors",
782
+ "vision.vision_tower.blocks.26.mlp.fc1.scales": "model.safetensors",
783
+ "vision.vision_tower.blocks.26.mlp.fc1.weight": "model.safetensors",
784
+ "vision.vision_tower.blocks.26.mlp.fc2.bias": "model.safetensors",
785
+ "vision.vision_tower.blocks.26.mlp.fc2.weight": "model.safetensors",
786
+ "vision.vision_tower.blocks.26.norm1.bias": "model.safetensors",
787
+ "vision.vision_tower.blocks.26.norm1.weight": "model.safetensors",
788
+ "vision.vision_tower.blocks.26.norm2.bias": "model.safetensors",
789
+ "vision.vision_tower.blocks.26.norm2.weight": "model.safetensors",
790
+ "vision.vision_tower.blocks.3.attn.proj.bias": "model.safetensors",
791
+ "vision.vision_tower.blocks.3.attn.proj.biases": "model.safetensors",
792
+ "vision.vision_tower.blocks.3.attn.proj.scales": "model.safetensors",
793
+ "vision.vision_tower.blocks.3.attn.proj.weight": "model.safetensors",
794
+ "vision.vision_tower.blocks.3.attn.qkv.bias": "model.safetensors",
795
+ "vision.vision_tower.blocks.3.attn.qkv.biases": "model.safetensors",
796
+ "vision.vision_tower.blocks.3.attn.qkv.scales": "model.safetensors",
797
+ "vision.vision_tower.blocks.3.attn.qkv.weight": "model.safetensors",
798
+ "vision.vision_tower.blocks.3.mlp.fc1.bias": "model.safetensors",
799
+ "vision.vision_tower.blocks.3.mlp.fc1.biases": "model.safetensors",
800
+ "vision.vision_tower.blocks.3.mlp.fc1.scales": "model.safetensors",
801
+ "vision.vision_tower.blocks.3.mlp.fc1.weight": "model.safetensors",
802
+ "vision.vision_tower.blocks.3.mlp.fc2.bias": "model.safetensors",
803
+ "vision.vision_tower.blocks.3.mlp.fc2.weight": "model.safetensors",
804
+ "vision.vision_tower.blocks.3.norm1.bias": "model.safetensors",
805
+ "vision.vision_tower.blocks.3.norm1.weight": "model.safetensors",
806
+ "vision.vision_tower.blocks.3.norm2.bias": "model.safetensors",
807
+ "vision.vision_tower.blocks.3.norm2.weight": "model.safetensors",
808
+ "vision.vision_tower.blocks.4.attn.proj.bias": "model.safetensors",
809
+ "vision.vision_tower.blocks.4.attn.proj.biases": "model.safetensors",
810
+ "vision.vision_tower.blocks.4.attn.proj.scales": "model.safetensors",
811
+ "vision.vision_tower.blocks.4.attn.proj.weight": "model.safetensors",
812
+ "vision.vision_tower.blocks.4.attn.qkv.bias": "model.safetensors",
813
+ "vision.vision_tower.blocks.4.attn.qkv.biases": "model.safetensors",
814
+ "vision.vision_tower.blocks.4.attn.qkv.scales": "model.safetensors",
815
+ "vision.vision_tower.blocks.4.attn.qkv.weight": "model.safetensors",
816
+ "vision.vision_tower.blocks.4.mlp.fc1.bias": "model.safetensors",
817
+ "vision.vision_tower.blocks.4.mlp.fc1.biases": "model.safetensors",
818
+ "vision.vision_tower.blocks.4.mlp.fc1.scales": "model.safetensors",
819
+ "vision.vision_tower.blocks.4.mlp.fc1.weight": "model.safetensors",
820
+ "vision.vision_tower.blocks.4.mlp.fc2.bias": "model.safetensors",
821
+ "vision.vision_tower.blocks.4.mlp.fc2.weight": "model.safetensors",
822
+ "vision.vision_tower.blocks.4.norm1.bias": "model.safetensors",
823
+ "vision.vision_tower.blocks.4.norm1.weight": "model.safetensors",
824
+ "vision.vision_tower.blocks.4.norm2.bias": "model.safetensors",
825
+ "vision.vision_tower.blocks.4.norm2.weight": "model.safetensors",
826
+ "vision.vision_tower.blocks.5.attn.proj.bias": "model.safetensors",
827
+ "vision.vision_tower.blocks.5.attn.proj.biases": "model.safetensors",
828
+ "vision.vision_tower.blocks.5.attn.proj.scales": "model.safetensors",
829
+ "vision.vision_tower.blocks.5.attn.proj.weight": "model.safetensors",
830
+ "vision.vision_tower.blocks.5.attn.qkv.bias": "model.safetensors",
831
+ "vision.vision_tower.blocks.5.attn.qkv.biases": "model.safetensors",
832
+ "vision.vision_tower.blocks.5.attn.qkv.scales": "model.safetensors",
833
+ "vision.vision_tower.blocks.5.attn.qkv.weight": "model.safetensors",
834
+ "vision.vision_tower.blocks.5.mlp.fc1.bias": "model.safetensors",
835
+ "vision.vision_tower.blocks.5.mlp.fc1.biases": "model.safetensors",
836
+ "vision.vision_tower.blocks.5.mlp.fc1.scales": "model.safetensors",
837
+ "vision.vision_tower.blocks.5.mlp.fc1.weight": "model.safetensors",
838
+ "vision.vision_tower.blocks.5.mlp.fc2.bias": "model.safetensors",
839
+ "vision.vision_tower.blocks.5.mlp.fc2.weight": "model.safetensors",
840
+ "vision.vision_tower.blocks.5.norm1.bias": "model.safetensors",
841
+ "vision.vision_tower.blocks.5.norm1.weight": "model.safetensors",
842
+ "vision.vision_tower.blocks.5.norm2.bias": "model.safetensors",
843
+ "vision.vision_tower.blocks.5.norm2.weight": "model.safetensors",
844
+ "vision.vision_tower.blocks.6.attn.proj.bias": "model.safetensors",
845
+ "vision.vision_tower.blocks.6.attn.proj.biases": "model.safetensors",
846
+ "vision.vision_tower.blocks.6.attn.proj.scales": "model.safetensors",
847
+ "vision.vision_tower.blocks.6.attn.proj.weight": "model.safetensors",
848
+ "vision.vision_tower.blocks.6.attn.qkv.bias": "model.safetensors",
849
+ "vision.vision_tower.blocks.6.attn.qkv.biases": "model.safetensors",
850
+ "vision.vision_tower.blocks.6.attn.qkv.scales": "model.safetensors",
851
+ "vision.vision_tower.blocks.6.attn.qkv.weight": "model.safetensors",
852
+ "vision.vision_tower.blocks.6.mlp.fc1.bias": "model.safetensors",
853
+ "vision.vision_tower.blocks.6.mlp.fc1.biases": "model.safetensors",
854
+ "vision.vision_tower.blocks.6.mlp.fc1.scales": "model.safetensors",
855
+ "vision.vision_tower.blocks.6.mlp.fc1.weight": "model.safetensors",
856
+ "vision.vision_tower.blocks.6.mlp.fc2.bias": "model.safetensors",
857
+ "vision.vision_tower.blocks.6.mlp.fc2.weight": "model.safetensors",
858
+ "vision.vision_tower.blocks.6.norm1.bias": "model.safetensors",
859
+ "vision.vision_tower.blocks.6.norm1.weight": "model.safetensors",
860
+ "vision.vision_tower.blocks.6.norm2.bias": "model.safetensors",
861
+ "vision.vision_tower.blocks.6.norm2.weight": "model.safetensors",
862
+ "vision.vision_tower.blocks.7.attn.proj.bias": "model.safetensors",
863
+ "vision.vision_tower.blocks.7.attn.proj.biases": "model.safetensors",
864
+ "vision.vision_tower.blocks.7.attn.proj.scales": "model.safetensors",
865
+ "vision.vision_tower.blocks.7.attn.proj.weight": "model.safetensors",
866
+ "vision.vision_tower.blocks.7.attn.qkv.bias": "model.safetensors",
867
+ "vision.vision_tower.blocks.7.attn.qkv.biases": "model.safetensors",
868
+ "vision.vision_tower.blocks.7.attn.qkv.scales": "model.safetensors",
869
+ "vision.vision_tower.blocks.7.attn.qkv.weight": "model.safetensors",
870
+ "vision.vision_tower.blocks.7.mlp.fc1.bias": "model.safetensors",
871
+ "vision.vision_tower.blocks.7.mlp.fc1.biases": "model.safetensors",
872
+ "vision.vision_tower.blocks.7.mlp.fc1.scales": "model.safetensors",
873
+ "vision.vision_tower.blocks.7.mlp.fc1.weight": "model.safetensors",
874
+ "vision.vision_tower.blocks.7.mlp.fc2.bias": "model.safetensors",
875
+ "vision.vision_tower.blocks.7.mlp.fc2.weight": "model.safetensors",
876
+ "vision.vision_tower.blocks.7.norm1.bias": "model.safetensors",
877
+ "vision.vision_tower.blocks.7.norm1.weight": "model.safetensors",
878
+ "vision.vision_tower.blocks.7.norm2.bias": "model.safetensors",
879
+ "vision.vision_tower.blocks.7.norm2.weight": "model.safetensors",
880
+ "vision.vision_tower.blocks.8.attn.proj.bias": "model.safetensors",
881
+ "vision.vision_tower.blocks.8.attn.proj.biases": "model.safetensors",
882
+ "vision.vision_tower.blocks.8.attn.proj.scales": "model.safetensors",
883
+ "vision.vision_tower.blocks.8.attn.proj.weight": "model.safetensors",
884
+ "vision.vision_tower.blocks.8.attn.qkv.bias": "model.safetensors",
885
+ "vision.vision_tower.blocks.8.attn.qkv.biases": "model.safetensors",
886
+ "vision.vision_tower.blocks.8.attn.qkv.scales": "model.safetensors",
887
+ "vision.vision_tower.blocks.8.attn.qkv.weight": "model.safetensors",
888
+ "vision.vision_tower.blocks.8.mlp.fc1.bias": "model.safetensors",
889
+ "vision.vision_tower.blocks.8.mlp.fc1.biases": "model.safetensors",
890
+ "vision.vision_tower.blocks.8.mlp.fc1.scales": "model.safetensors",
891
+ "vision.vision_tower.blocks.8.mlp.fc1.weight": "model.safetensors",
892
+ "vision.vision_tower.blocks.8.mlp.fc2.bias": "model.safetensors",
893
+ "vision.vision_tower.blocks.8.mlp.fc2.weight": "model.safetensors",
894
+ "vision.vision_tower.blocks.8.norm1.bias": "model.safetensors",
895
+ "vision.vision_tower.blocks.8.norm1.weight": "model.safetensors",
896
+ "vision.vision_tower.blocks.8.norm2.bias": "model.safetensors",
897
+ "vision.vision_tower.blocks.8.norm2.weight": "model.safetensors",
898
+ "vision.vision_tower.blocks.9.attn.proj.bias": "model.safetensors",
899
+ "vision.vision_tower.blocks.9.attn.proj.biases": "model.safetensors",
900
+ "vision.vision_tower.blocks.9.attn.proj.scales": "model.safetensors",
901
+ "vision.vision_tower.blocks.9.attn.proj.weight": "model.safetensors",
902
+ "vision.vision_tower.blocks.9.attn.qkv.bias": "model.safetensors",
903
+ "vision.vision_tower.blocks.9.attn.qkv.biases": "model.safetensors",
904
+ "vision.vision_tower.blocks.9.attn.qkv.scales": "model.safetensors",
905
+ "vision.vision_tower.blocks.9.attn.qkv.weight": "model.safetensors",
906
+ "vision.vision_tower.blocks.9.mlp.fc1.bias": "model.safetensors",
907
+ "vision.vision_tower.blocks.9.mlp.fc1.biases": "model.safetensors",
908
+ "vision.vision_tower.blocks.9.mlp.fc1.scales": "model.safetensors",
909
+ "vision.vision_tower.blocks.9.mlp.fc1.weight": "model.safetensors",
910
+ "vision.vision_tower.blocks.9.mlp.fc2.bias": "model.safetensors",
911
+ "vision.vision_tower.blocks.9.mlp.fc2.weight": "model.safetensors",
912
+ "vision.vision_tower.blocks.9.norm1.bias": "model.safetensors",
913
+ "vision.vision_tower.blocks.9.norm1.weight": "model.safetensors",
914
+ "vision.vision_tower.blocks.9.norm2.bias": "model.safetensors",
915
+ "vision.vision_tower.blocks.9.norm2.weight": "model.safetensors",
916
+ "vision.vision_tower.norm.bias": "model.safetensors",
917
+ "vision.vision_tower.norm.weight": "model.safetensors",
918
+ "vision.vision_tower.patch_embed.proj.bias": "model.safetensors",
919
+ "vision.vision_tower.patch_embed.proj.weight": "model.safetensors",
920
+ "vision.vision_tower.pos_embed": "model.safetensors"
921
+ }
922
+ }
processor_config.json ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_special_token": false,
3
+ "candidate_resolutions": [
4
+ [
5
+ 384,
6
+ 384
7
+ ],
8
+ [
9
+ 384,
10
+ 768
11
+ ],
12
+ [
13
+ 768,
14
+ 384
15
+ ],
16
+ [
17
+ 384,
18
+ 1152
19
+ ],
20
+ [
21
+ 1152,
22
+ 384
23
+ ],
24
+ [
25
+ 384,
26
+ 1536
27
+ ],
28
+ [
29
+ 1536,
30
+ 384
31
+ ],
32
+ [
33
+ 768,
34
+ 768
35
+ ],
36
+ [
37
+ 384,
38
+ 1920
39
+ ],
40
+ [
41
+ 1920,
42
+ 384
43
+ ],
44
+ [
45
+ 384,
46
+ 2304
47
+ ],
48
+ [
49
+ 2304,
50
+ 384
51
+ ],
52
+ [
53
+ 768,
54
+ 1152
55
+ ],
56
+ [
57
+ 1152,
58
+ 768
59
+ ],
60
+ [
61
+ 384,
62
+ 2688
63
+ ],
64
+ [
65
+ 2688,
66
+ 384
67
+ ],
68
+ [
69
+ 384,
70
+ 3072
71
+ ],
72
+ [
73
+ 3072,
74
+ 384
75
+ ],
76
+ [
77
+ 768,
78
+ 1536
79
+ ],
80
+ [
81
+ 1536,
82
+ 768
83
+ ],
84
+ [
85
+ 384,
86
+ 3456
87
+ ],
88
+ [
89
+ 3456,
90
+ 384
91
+ ],
92
+ [
93
+ 1152,
94
+ 1152
95
+ ]
96
+ ],
97
+ "downsample_ratio": 2,
98
+ "ignore_id": -100,
99
+ "image_mean": [
100
+ 0.5,
101
+ 0.5,
102
+ 0.5
103
+ ],
104
+ "image_std": [
105
+ 0.5,
106
+ 0.5,
107
+ 0.5
108
+ ],
109
+ "image_token": "<image>",
110
+ "mask_prompt": false,
111
+ "normalize": true,
112
+ "pad_token": "<\uff5c\u2581pad\u2581\uff5c>",
113
+ "patch_size": 14,
114
+ "processor_class": "DeepseekVLV2Processor",
115
+ "sft_format": "deepseek"
116
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|User|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|Assistant|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": {
19
+ "content": "<｜begin▁of▁sentence｜>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "eos_token": {
26
+ "content": "<｜end▁of▁sentence｜>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "pad_token": {
33
+ "content": "<｜▁pad▁｜>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ }
39
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff