Hugging Face's logo

AXERA-TECH
/
MiniCPM-V-4

Image-Text-to-Text
Transformers
Safetensors
Chinese
English
MiniCPM
MiniCPM-V-4
Model card Files
xet
Community
jordan0811 commited on
Commit
5990989
·
verified ·
1 Parent(s): 964a1c2

Delete files *.json with huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +0 -203
  2. generation_config.json +0 -10
  3. model.safetensors.index.json +0 -748
  4. preprocessor_config.json +0 -24
  5. special_tokens_map.json +0 -81
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +0 -120
config.json DELETED
@@ -1,203 +0,0 @@
1
- {
2
- "architectures": [
3
- "MiniCPMV"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "auto_map": {
8
- "AutoConfig": "configuration_minicpm.MiniCPMVConfig",
9
- "AutoModel": "modeling_minicpmv.MiniCPMV",
10
- "AutoModelForCausalLM": "modeling_minicpmv.MiniCPMV"
11
- },
12
- "batch_vision_input": true,
13
- "bos_token_id": 1,
14
- "drop_vision_last_layer": false,
15
- "eos_token_id": [
16
- 2,
17
- 73440
18
- ],
19
- "head_dim": 128,
20
- "hidden_act": "silu",
21
- "hidden_size": 2560,
22
- "image_size": 448,
23
- "initializer_range": 0.1,
24
- "intermediate_size": 10240,
25
- "max_position_embeddings": 32768,
26
- "mlp_bias": false,
27
- "model_type": "minicpmv",
28
- "num_attention_heads": 32,
29
- "num_hidden_layers": 32,
30
- "num_key_value_heads": 2,
31
- "pad_token_id": 2,
32
- "patch_size": 14,
33
- "pretraining_tp": 1,
34
- "query_num": 64,
35
- "rms_norm_eps": 1e-06,
36
- "rope_scaling": {
37
- "factor": 1.0,
38
- "long_factor": [
39
- 0.9977997200264581,
40
- 1.014658295992452,
41
- 1.0349680404997148,
42
- 1.059429246056193,
43
- 1.0888815016813513,
44
- 1.1243301355211495,
45
- 1.166977103606075,
46
- 1.2182568066927284,
47
- 1.2798772354275727,
48
- 1.3538666751582975,
49
- 1.4426259039919596,
50
- 1.5489853358570191,
51
- 1.6762658237220625,
52
- 1.8283407612492941,
53
- 2.0096956085876183,
54
- 2.225478927469756,
55
- 2.481536379650452,
56
- 2.784415934557119,
57
- 3.1413289096347365,
58
- 3.560047844772632,
59
- 4.048719380066383,
60
- 4.615569542115128,
61
- 5.2684819496549835,
62
- 6.014438591970396,
63
- 6.858830049237097,
64
- 7.804668263503327,
65
- 8.851768731513417,
66
- 9.99600492938444,
67
- 11.228766118181639,
68
- 12.536757560834843,
69
- 13.902257701387796,
70
- 15.303885189125953,
71
- 16.717837610115794,
72
- 18.119465097853947,
73
- 19.484965238406907,
74
- 20.792956681060105,
75
- 22.02571786985731,
76
- 23.16995406772833,
77
- 24.217054535738416,
78
- 25.16289275000465,
79
- 26.007284207271347,
80
- 26.753240849586767,
81
- 27.40615325712662,
82
- 27.973003419175363,
83
- 28.461674954469114,
84
- 28.880393889607006,
85
- 29.237306864684626,
86
- 29.540186419591297,
87
- 29.79624387177199,
88
- 30.01202719065413,
89
- 30.193382037992453,
90
- 30.34545697551969,
91
- 30.47273746338473,
92
- 30.579096895249787,
93
- 30.66785612408345,
94
- 30.741845563814174,
95
- 30.80346599254902,
96
- 30.85474569563567,
97
- 30.897392663720595,
98
- 30.932841297560394,
99
- 30.962293553185553,
100
- 30.986754758742034,
101
- 31.007064503249293,
102
- 31.02392307921529
103
- ],
104
- "original_max_position_embeddings": 32786,
105
- "rope_type": "longrope",
106
- "short_factor": [
107
- 0.9977997200264581,
108
- 1.014658295992452,
109
- 1.0349680404997148,
110
- 1.059429246056193,
111
- 1.0888815016813513,
112
- 1.1243301355211495,
113
- 1.166977103606075,
114
- 1.2182568066927284,
115
- 1.2798772354275727,
116
- 1.3538666751582975,
117
- 1.4426259039919596,
118
- 1.5489853358570191,
119
- 1.6762658237220625,
120
- 1.8283407612492941,
121
- 2.0096956085876183,
122
- 2.225478927469756,
123
- 2.481536379650452,
124
- 2.784415934557119,
125
- 3.1413289096347365,
126
- 3.560047844772632,
127
- 4.048719380066383,
128
- 4.615569542115128,
129
- 5.2684819496549835,
130
- 6.014438591970396,
131
- 6.858830049237097,
132
- 7.804668263503327,
133
- 8.851768731513417,
134
- 9.99600492938444,
135
- 11.228766118181639,
136
- 12.536757560834843,
137
- 13.902257701387796,
138
- 15.303885189125953,
139
- 16.717837610115794,
140
- 18.119465097853947,
141
- 19.484965238406907,
142
- 20.792956681060105,
143
- 22.02571786985731,
144
- 23.16995406772833,
145
- 24.217054535738416,
146
- 25.16289275000465,
147
- 26.007284207271347,
148
- 26.753240849586767,
149
- 27.40615325712662,
150
- 27.973003419175363,
151
- 28.461674954469114,
152
- 28.880393889607006,
153
- 29.237306864684626,
154
- 29.540186419591297,
155
- 29.79624387177199,
156
- 30.01202719065413,
157
- 30.193382037992453,
158
- 30.34545697551969,
159
- 30.47273746338473,
160
- 30.579096895249787,
161
- 30.66785612408345,
162
- 30.741845563814174,
163
- 30.80346599254902,
164
- 30.85474569563567,
165
- 30.897392663720595,
166
- 30.932841297560394,
167
- 30.962293553185553,
168
- 30.986754758742034,
169
- 31.007064503249293,
170
- 31.02392307921529
171
- ]
172
- },
173
- "rope_theta": 10000.0,
174
- "slice_config": {
175
- "max_slice_nums": 9,
176
- "model_type": "minicpmv",
177
- "patch_size": 14,
178
- "scale_resolution": 448
179
- },
180
- "slice_mode": true,
181
- "tie_word_embeddings": false,
182
- "torch_dtype": "bfloat16",
183
- "transformers_version": "4.51.0",
184
- "use_cache": true,
185
- "use_image_id": true,
186
- "version": 4.0,
187
- "vision_batch_size": 16,
188
- "vision_config": {
189
- "_attn_implementation_autoset": true,
190
- "attention_dropout": 0.0,
191
- "hidden_act": "gelu_pytorch_tanh",
192
- "hidden_size": 1152,
193
- "image_size": 980,
194
- "intermediate_size": 4304,
195
- "layer_norm_eps": 1e-06,
196
- "model_type": "siglip_vision_model",
197
- "num_attention_heads": 16,
198
- "num_channels": 3,
199
- "num_hidden_layers": 27,
200
- "patch_size": 14
201
- },
202
- "vocab_size": 73448
203
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
generation_config.json DELETED
@@ -1,10 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "eos_token_id": [
5
- 2,
6
- 73440
7
- ],
8
- "pad_token_id": 2,
9
- "transformers_version": "4.51.0"
10
- }
 
 
 
 
 
 
 
 
 
 
 
model.safetensors.index.json DELETED
@@ -1,748 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 8119066080
4
- },
5
- "weight_map": {
6
- "llm.lm_head.weight": "model-00002-of-00002.safetensors",
7
- "llm.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
- "llm.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
- "llm.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
- "llm.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
- "llm.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
- "llm.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
- "llm.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
14
- "llm.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
15
- "llm.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
16
- "llm.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
17
- "llm.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
18
- "llm.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
19
- "llm.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
20
- "llm.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
21
- "llm.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
22
- "llm.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
23
- "llm.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
24
- "llm.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
25
- "llm.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
26
- "llm.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
27
- "llm.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
28
- "llm.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
29
- "llm.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
30
- "llm.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
31
- "llm.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
32
- "llm.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
33
- "llm.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
34
- "llm.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
35
- "llm.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
36
- "llm.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
37
- "llm.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
38
- "llm.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
39
- "llm.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
40
- "llm.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
41
- "llm.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
42
- "llm.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
43
- "llm.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
44
- "llm.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
45
- "llm.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
- "llm.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
47
- "llm.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
48
- "llm.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
49
- "llm.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
- "llm.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
51
- "llm.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
52
- "llm.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
53
- "llm.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
54
- "llm.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
55
- "llm.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
56
- "llm.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
57
- "llm.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
58
- "llm.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
- "llm.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
- "llm.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
61
- "llm.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
62
- "llm.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
63
- "llm.model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
64
- "llm.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
65
- "llm.model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
66
- "llm.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
67
- "llm.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
68
- "llm.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
69
- "llm.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
70
- "llm.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
71
- "llm.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
72
- "llm.model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
73
- "llm.model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
74
- "llm.model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
75
- "llm.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
76
- "llm.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
77
- "llm.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
78
- "llm.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
79
- "llm.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
80
- "llm.model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
- "llm.model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
- "llm.model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
83
- "llm.model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
84
- "llm.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
85
- "llm.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
86
- "llm.model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
87
- "llm.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
88
- "llm.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
89
- "llm.model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
90
- "llm.model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
91
- "llm.model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
92
- "llm.model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
93
- "llm.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
94
- "llm.model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
95
- "llm.model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
96
- "llm.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
97
- "llm.model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
98
- "llm.model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
99
- "llm.model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
100
- "llm.model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
101
- "llm.model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
102
- "llm.model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
103
- "llm.model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
104
- "llm.model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
105
- "llm.model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
106
- "llm.model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
107
- "llm.model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
108
- "llm.model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
109
- "llm.model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
110
- "llm.model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
111
- "llm.model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
112
- "llm.model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
113
- "llm.model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
114
- "llm.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
115
- "llm.model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
116
- "llm.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
117
- "llm.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
118
- "llm.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
119
- "llm.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
120
- "llm.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
121
- "llm.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
122
- "llm.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
123
- "llm.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
124
- "llm.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
125
- "llm.model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
126
- "llm.model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
127
- "llm.model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
128
- "llm.model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
129
- "llm.model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
130
- "llm.model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
131
- "llm.model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
132
- "llm.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
133
- "llm.model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
134
- "llm.model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
135
- "llm.model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
136
- "llm.model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
137
- "llm.model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
138
- "llm.model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
139
- "llm.model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
140
- "llm.model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
141
- "llm.model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
142
- "llm.model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
143
- "llm.model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
144
- "llm.model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
145
- "llm.model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
146
- "llm.model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
147
- "llm.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
148
- "llm.model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
149
- "llm.model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
150
- "llm.model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
151
- "llm.model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
152
- "llm.model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
153
- "llm.model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
154
- "llm.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
155
- "llm.model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
156
- "llm.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
157
- "llm.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
158
- "llm.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
159
- "llm.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
160
- "llm.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
161
- "llm.model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
162
- "llm.model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
163
- "llm.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
164
- "llm.model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
165
- "llm.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
166
- "llm.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
167
- "llm.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
168
- "llm.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
169
- "llm.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
170
- "llm.model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
171
- "llm.model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
172
- "llm.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
173
- "llm.model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
174
- "llm.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
175
- "llm.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
176
- "llm.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
177
- "llm.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
178
- "llm.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
179
- "llm.model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
180
- "llm.model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
181
- "llm.model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
182
- "llm.model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
183
- "llm.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
184
- "llm.model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
185
- "llm.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
186
- "llm.model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
187
- "llm.model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
188
- "llm.model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
189
- "llm.model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
190
- "llm.model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
191
- "llm.model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
192
- "llm.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
193
- "llm.model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
194
- "llm.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
195
- "llm.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
196
- "llm.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
197
- "llm.model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
198
- "llm.model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
199
- "llm.model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
200
- "llm.model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
201
- "llm.model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
202
- "llm.model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
203
- "llm.model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
204
- "llm.model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
205
- "llm.model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
206
- "llm.model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
207
- "llm.model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
208
- "llm.model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
209
- "llm.model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
210
- "llm.model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
211
- "llm.model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
212
- "llm.model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
213
- "llm.model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
214
- "llm.model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
215
- "llm.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
216
- "llm.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
217
- "llm.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
218
- "llm.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
219
- "llm.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
220
- "llm.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
221
- "llm.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
222
- "llm.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
223
- "llm.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
224
- "llm.model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
225
- "llm.model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
226
- "llm.model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
227
- "llm.model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
228
- "llm.model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
229
- "llm.model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
230
- "llm.model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
231
- "llm.model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
232
- "llm.model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
233
- "llm.model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
234
- "llm.model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
235
- "llm.model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
236
- "llm.model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
237
- "llm.model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
238
- "llm.model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
239
- "llm.model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
240
- "llm.model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
241
- "llm.model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
242
- "llm.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
243
- "llm.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
244
- "llm.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
245
- "llm.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
246
- "llm.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
247
- "llm.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
248
- "llm.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
249
- "llm.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
250
- "llm.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
251
- "llm.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
252
- "llm.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
253
- "llm.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
254
- "llm.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
255
- "llm.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
256
- "llm.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
257
- "llm.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
258
- "llm.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
259
- "llm.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
260
- "llm.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
261
- "llm.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
262
- "llm.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
263
- "llm.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
264
- "llm.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
265
- "llm.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
266
- "llm.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
267
- "llm.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
268
- "llm.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
269
- "llm.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
270
- "llm.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
271
- "llm.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
272
- "llm.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
273
- "llm.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
274
- "llm.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
275
- "llm.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
276
- "llm.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
277
- "llm.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
278
- "llm.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
279
- "llm.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
280
- "llm.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
281
- "llm.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
282
- "llm.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
283
- "llm.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
284
- "llm.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
285
- "llm.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
286
- "llm.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
287
- "llm.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
288
- "llm.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
289
- "llm.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
290
- "llm.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
291
- "llm.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
292
- "llm.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
293
- "llm.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
294
- "llm.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
295
- "llm.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
296
- "llm.model.norm.weight": "model-00002-of-00002.safetensors",
297
- "resampler.attn.in_proj_bias": "model-00002-of-00002.safetensors",
298
- "resampler.attn.in_proj_weight": "model-00002-of-00002.safetensors",
299
- "resampler.attn.out_proj.bias": "model-00002-of-00002.safetensors",
300
- "resampler.attn.out_proj.weight": "model-00002-of-00002.safetensors",
301
- "resampler.kv_proj.weight": "model-00002-of-00002.safetensors",
302
- "resampler.ln_kv.bias": "model-00002-of-00002.safetensors",
303
- "resampler.ln_kv.weight": "model-00002-of-00002.safetensors",
304
- "resampler.ln_post.bias": "model-00002-of-00002.safetensors",
305
- "resampler.ln_post.weight": "model-00002-of-00002.safetensors",
306
- "resampler.ln_q.bias": "model-00002-of-00002.safetensors",
307
- "resampler.ln_q.weight": "model-00002-of-00002.safetensors",
308
- "resampler.proj": "model-00002-of-00002.safetensors",
309
- "resampler.query": "model-00002-of-00002.safetensors",
310
- "vpm.embeddings.patch_embedding.bias": "model-00002-of-00002.safetensors",
311
- "vpm.embeddings.patch_embedding.weight": "model-00002-of-00002.safetensors",
312
- "vpm.embeddings.position_embedding.weight": "model-00002-of-00002.safetensors",
313
- "vpm.encoder.layers.0.layer_norm1.bias": "model-00002-of-00002.safetensors",
314
- "vpm.encoder.layers.0.layer_norm1.weight": "model-00002-of-00002.safetensors",
315
- "vpm.encoder.layers.0.layer_norm2.bias": "model-00002-of-00002.safetensors",
316
- "vpm.encoder.layers.0.layer_norm2.weight": "model-00002-of-00002.safetensors",
317
- "vpm.encoder.layers.0.mlp.fc1.bias": "model-00002-of-00002.safetensors",
318
- "vpm.encoder.layers.0.mlp.fc1.weight": "model-00002-of-00002.safetensors",
319
- "vpm.encoder.layers.0.mlp.fc2.bias": "model-00002-of-00002.safetensors",
320
- "vpm.encoder.layers.0.mlp.fc2.weight": "model-00002-of-00002.safetensors",
321
- "vpm.encoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
322
- "vpm.encoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
323
- "vpm.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
324
- "vpm.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
325
- "vpm.encoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
326
- "vpm.encoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
327
- "vpm.encoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
328
- "vpm.encoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
329
- "vpm.encoder.layers.1.layer_norm1.bias": "model-00002-of-00002.safetensors",
330
- "vpm.encoder.layers.1.layer_norm1.weight": "model-00002-of-00002.safetensors",
331
- "vpm.encoder.layers.1.layer_norm2.bias": "model-00002-of-00002.safetensors",
332
- "vpm.encoder.layers.1.layer_norm2.weight": "model-00002-of-00002.safetensors",
333
- "vpm.encoder.layers.1.mlp.fc1.bias": "model-00002-of-00002.safetensors",
334
- "vpm.encoder.layers.1.mlp.fc1.weight": "model-00002-of-00002.safetensors",
335
- "vpm.encoder.layers.1.mlp.fc2.bias": "model-00002-of-00002.safetensors",
336
- "vpm.encoder.layers.1.mlp.fc2.weight": "model-00002-of-00002.safetensors",
337
- "vpm.encoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
338
- "vpm.encoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
339
- "vpm.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
340
- "vpm.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
341
- "vpm.encoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
342
- "vpm.encoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
343
- "vpm.encoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
344
- "vpm.encoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
345
- "vpm.encoder.layers.10.layer_norm1.bias": "model-00002-of-00002.safetensors",
346
- "vpm.encoder.layers.10.layer_norm1.weight": "model-00002-of-00002.safetensors",
347
- "vpm.encoder.layers.10.layer_norm2.bias": "model-00002-of-00002.safetensors",
348
- "vpm.encoder.layers.10.layer_norm2.weight": "model-00002-of-00002.safetensors",
349
- "vpm.encoder.layers.10.mlp.fc1.bias": "model-00002-of-00002.safetensors",
350
- "vpm.encoder.layers.10.mlp.fc1.weight": "model-00002-of-00002.safetensors",
351
- "vpm.encoder.layers.10.mlp.fc2.bias": "model-00002-of-00002.safetensors",
352
- "vpm.encoder.layers.10.mlp.fc2.weight": "model-00002-of-00002.safetensors",
353
- "vpm.encoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
354
- "vpm.encoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
355
- "vpm.encoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
356
- "vpm.encoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
357
- "vpm.encoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
358
- "vpm.encoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
359
- "vpm.encoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
360
- "vpm.encoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
361
- "vpm.encoder.layers.11.layer_norm1.bias": "model-00002-of-00002.safetensors",
362
- "vpm.encoder.layers.11.layer_norm1.weight": "model-00002-of-00002.safetensors",
363
- "vpm.encoder.layers.11.layer_norm2.bias": "model-00002-of-00002.safetensors",
364
- "vpm.encoder.layers.11.layer_norm2.weight": "model-00002-of-00002.safetensors",
365
- "vpm.encoder.layers.11.mlp.fc1.bias": "model-00002-of-00002.safetensors",
366
- "vpm.encoder.layers.11.mlp.fc1.weight": "model-00002-of-00002.safetensors",
367
- "vpm.encoder.layers.11.mlp.fc2.bias": "model-00002-of-00002.safetensors",
368
- "vpm.encoder.layers.11.mlp.fc2.weight": "model-00002-of-00002.safetensors",
369
- "vpm.encoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
370
- "vpm.encoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
371
- "vpm.encoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
372
- "vpm.encoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
373
- "vpm.encoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
374
- "vpm.encoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
375
- "vpm.encoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
376
- "vpm.encoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
377
- "vpm.encoder.layers.12.layer_norm1.bias": "model-00002-of-00002.safetensors",
378
- "vpm.encoder.layers.12.layer_norm1.weight": "model-00002-of-00002.safetensors",
379
- "vpm.encoder.layers.12.layer_norm2.bias": "model-00002-of-00002.safetensors",
380
- "vpm.encoder.layers.12.layer_norm2.weight": "model-00002-of-00002.safetensors",
381
- "vpm.encoder.layers.12.mlp.fc1.bias": "model-00002-of-00002.safetensors",
382
- "vpm.encoder.layers.12.mlp.fc1.weight": "model-00002-of-00002.safetensors",
383
- "vpm.encoder.layers.12.mlp.fc2.bias": "model-00002-of-00002.safetensors",
384
- "vpm.encoder.layers.12.mlp.fc2.weight": "model-00002-of-00002.safetensors",
385
- "vpm.encoder.layers.12.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
386
- "vpm.encoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
387
- "vpm.encoder.layers.12.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
388
- "vpm.encoder.layers.12.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
389
- "vpm.encoder.layers.12.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
390
- "vpm.encoder.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
391
- "vpm.encoder.layers.12.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
392
- "vpm.encoder.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
393
- "vpm.encoder.layers.13.layer_norm1.bias": "model-00002-of-00002.safetensors",
394
- "vpm.encoder.layers.13.layer_norm1.weight": "model-00002-of-00002.safetensors",
395
- "vpm.encoder.layers.13.layer_norm2.bias": "model-00002-of-00002.safetensors",
396
- "vpm.encoder.layers.13.layer_norm2.weight": "model-00002-of-00002.safetensors",
397
- "vpm.encoder.layers.13.mlp.fc1.bias": "model-00002-of-00002.safetensors",
398
- "vpm.encoder.layers.13.mlp.fc1.weight": "model-00002-of-00002.safetensors",
399
- "vpm.encoder.layers.13.mlp.fc2.bias": "model-00002-of-00002.safetensors",
400
- "vpm.encoder.layers.13.mlp.fc2.weight": "model-00002-of-00002.safetensors",
401
- "vpm.encoder.layers.13.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
402
- "vpm.encoder.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
403
- "vpm.encoder.layers.13.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
404
- "vpm.encoder.layers.13.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
405
- "vpm.encoder.layers.13.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
406
- "vpm.encoder.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
407
- "vpm.encoder.layers.13.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
408
- "vpm.encoder.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
409
- "vpm.encoder.layers.14.layer_norm1.bias": "model-00002-of-00002.safetensors",
410
- "vpm.encoder.layers.14.layer_norm1.weight": "model-00002-of-00002.safetensors",
411
- "vpm.encoder.layers.14.layer_norm2.bias": "model-00002-of-00002.safetensors",
412
- "vpm.encoder.layers.14.layer_norm2.weight": "model-00002-of-00002.safetensors",
413
- "vpm.encoder.layers.14.mlp.fc1.bias": "model-00002-of-00002.safetensors",
414
- "vpm.encoder.layers.14.mlp.fc1.weight": "model-00002-of-00002.safetensors",
415
- "vpm.encoder.layers.14.mlp.fc2.bias": "model-00002-of-00002.safetensors",
416
- "vpm.encoder.layers.14.mlp.fc2.weight": "model-00002-of-00002.safetensors",
417
- "vpm.encoder.layers.14.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
418
- "vpm.encoder.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
419
- "vpm.encoder.layers.14.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
420
- "vpm.encoder.layers.14.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
421
- "vpm.encoder.layers.14.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
422
- "vpm.encoder.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
423
- "vpm.encoder.layers.14.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
424
- "vpm.encoder.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
425
- "vpm.encoder.layers.15.layer_norm1.bias": "model-00002-of-00002.safetensors",
426
- "vpm.encoder.layers.15.layer_norm1.weight": "model-00002-of-00002.safetensors",
427
- "vpm.encoder.layers.15.layer_norm2.bias": "model-00002-of-00002.safetensors",
428
- "vpm.encoder.layers.15.layer_norm2.weight": "model-00002-of-00002.safetensors",
429
- "vpm.encoder.layers.15.mlp.fc1.bias": "model-00002-of-00002.safetensors",
430
- "vpm.encoder.layers.15.mlp.fc1.weight": "model-00002-of-00002.safetensors",
431
- "vpm.encoder.layers.15.mlp.fc2.bias": "model-00002-of-00002.safetensors",
432
- "vpm.encoder.layers.15.mlp.fc2.weight": "model-00002-of-00002.safetensors",
433
- "vpm.encoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
434
- "vpm.encoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
435
- "vpm.encoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
436
- "vpm.encoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
437
- "vpm.encoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
438
- "vpm.encoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
439
- "vpm.encoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
440
- "vpm.encoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
441
- "vpm.encoder.layers.16.layer_norm1.bias": "model-00002-of-00002.safetensors",
442
- "vpm.encoder.layers.16.layer_norm1.weight": "model-00002-of-00002.safetensors",
443
- "vpm.encoder.layers.16.layer_norm2.bias": "model-00002-of-00002.safetensors",
444
- "vpm.encoder.layers.16.layer_norm2.weight": "model-00002-of-00002.safetensors",
445
- "vpm.encoder.layers.16.mlp.fc1.bias": "model-00002-of-00002.safetensors",
446
- "vpm.encoder.layers.16.mlp.fc1.weight": "model-00002-of-00002.safetensors",
447
- "vpm.encoder.layers.16.mlp.fc2.bias": "model-00002-of-00002.safetensors",
448
- "vpm.encoder.layers.16.mlp.fc2.weight": "model-00002-of-00002.safetensors",
449
- "vpm.encoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
450
- "vpm.encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
451
- "vpm.encoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
452
- "vpm.encoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
453
- "vpm.encoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
454
- "vpm.encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
455
- "vpm.encoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
456
- "vpm.encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
457
- "vpm.encoder.layers.17.layer_norm1.bias": "model-00002-of-00002.safetensors",
458
- "vpm.encoder.layers.17.layer_norm1.weight": "model-00002-of-00002.safetensors",
459
- "vpm.encoder.layers.17.layer_norm2.bias": "model-00002-of-00002.safetensors",
460
- "vpm.encoder.layers.17.layer_norm2.weight": "model-00002-of-00002.safetensors",
461
- "vpm.encoder.layers.17.mlp.fc1.bias": "model-00002-of-00002.safetensors",
462
- "vpm.encoder.layers.17.mlp.fc1.weight": "model-00002-of-00002.safetensors",
463
- "vpm.encoder.layers.17.mlp.fc2.bias": "model-00002-of-00002.safetensors",
464
- "vpm.encoder.layers.17.mlp.fc2.weight": "model-00002-of-00002.safetensors",
465
- "vpm.encoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
466
- "vpm.encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
467
- "vpm.encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
468
- "vpm.encoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
469
- "vpm.encoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
470
- "vpm.encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
471
- "vpm.encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
472
- "vpm.encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
473
- "vpm.encoder.layers.18.layer_norm1.bias": "model-00002-of-00002.safetensors",
474
- "vpm.encoder.layers.18.layer_norm1.weight": "model-00002-of-00002.safetensors",
475
- "vpm.encoder.layers.18.layer_norm2.bias": "model-00002-of-00002.safetensors",
476
- "vpm.encoder.layers.18.layer_norm2.weight": "model-00002-of-00002.safetensors",
477
- "vpm.encoder.layers.18.mlp.fc1.bias": "model-00002-of-00002.safetensors",
478
- "vpm.encoder.layers.18.mlp.fc1.weight": "model-00002-of-00002.safetensors",
479
- "vpm.encoder.layers.18.mlp.fc2.bias": "model-00002-of-00002.safetensors",
480
- "vpm.encoder.layers.18.mlp.fc2.weight": "model-00002-of-00002.safetensors",
481
- "vpm.encoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
482
- "vpm.encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
483
- "vpm.encoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
484
- "vpm.encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
485
- "vpm.encoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
486
- "vpm.encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
487
- "vpm.encoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
488
- "vpm.encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
489
- "vpm.encoder.layers.19.layer_norm1.bias": "model-00002-of-00002.safetensors",
490
- "vpm.encoder.layers.19.layer_norm1.weight": "model-00002-of-00002.safetensors",
491
- "vpm.encoder.layers.19.layer_norm2.bias": "model-00002-of-00002.safetensors",
492
- "vpm.encoder.layers.19.layer_norm2.weight": "model-00002-of-00002.safetensors",
493
- "vpm.encoder.layers.19.mlp.fc1.bias": "model-00002-of-00002.safetensors",
494
- "vpm.encoder.layers.19.mlp.fc1.weight": "model-00002-of-00002.safetensors",
495
- "vpm.encoder.layers.19.mlp.fc2.bias": "model-00002-of-00002.safetensors",
496
- "vpm.encoder.layers.19.mlp.fc2.weight": "model-00002-of-00002.safetensors",
497
- "vpm.encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
498
- "vpm.encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
499
- "vpm.encoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
500
- "vpm.encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
501
- "vpm.encoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
502
- "vpm.encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
503
- "vpm.encoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
504
- "vpm.encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
505
- "vpm.encoder.layers.2.layer_norm1.bias": "model-00002-of-00002.safetensors",
506
- "vpm.encoder.layers.2.layer_norm1.weight": "model-00002-of-00002.safetensors",
507
- "vpm.encoder.layers.2.layer_norm2.bias": "model-00002-of-00002.safetensors",
508
- "vpm.encoder.layers.2.layer_norm2.weight": "model-00002-of-00002.safetensors",
509
- "vpm.encoder.layers.2.mlp.fc1.bias": "model-00002-of-00002.safetensors",
510
- "vpm.encoder.layers.2.mlp.fc1.weight": "model-00002-of-00002.safetensors",
511
- "vpm.encoder.layers.2.mlp.fc2.bias": "model-00002-of-00002.safetensors",
512
- "vpm.encoder.layers.2.mlp.fc2.weight": "model-00002-of-00002.safetensors",
513
- "vpm.encoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
514
- "vpm.encoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
515
- "vpm.encoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
516
- "vpm.encoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
517
- "vpm.encoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
518
- "vpm.encoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
519
- "vpm.encoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
520
- "vpm.encoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
521
- "vpm.encoder.layers.20.layer_norm1.bias": "model-00002-of-00002.safetensors",
522
- "vpm.encoder.layers.20.layer_norm1.weight": "model-00002-of-00002.safetensors",
523
- "vpm.encoder.layers.20.layer_norm2.bias": "model-00002-of-00002.safetensors",
524
- "vpm.encoder.layers.20.layer_norm2.weight": "model-00002-of-00002.safetensors",
525
- "vpm.encoder.layers.20.mlp.fc1.bias": "model-00002-of-00002.safetensors",
526
- "vpm.encoder.layers.20.mlp.fc1.weight": "model-00002-of-00002.safetensors",
527
- "vpm.encoder.layers.20.mlp.fc2.bias": "model-00002-of-00002.safetensors",
528
- "vpm.encoder.layers.20.mlp.fc2.weight": "model-00002-of-00002.safetensors",
529
- "vpm.encoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
530
- "vpm.encoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
531
- "vpm.encoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
532
- "vpm.encoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
533
- "vpm.encoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
534
- "vpm.encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
535
- "vpm.encoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
536
- "vpm.encoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
537
- "vpm.encoder.layers.21.layer_norm1.bias": "model-00002-of-00002.safetensors",
538
- "vpm.encoder.layers.21.layer_norm1.weight": "model-00002-of-00002.safetensors",
539
- "vpm.encoder.layers.21.layer_norm2.bias": "model-00002-of-00002.safetensors",
540
- "vpm.encoder.layers.21.layer_norm2.weight": "model-00002-of-00002.safetensors",
541
- "vpm.encoder.layers.21.mlp.fc1.bias": "model-00002-of-00002.safetensors",
542
- "vpm.encoder.layers.21.mlp.fc1.weight": "model-00002-of-00002.safetensors",
543
- "vpm.encoder.layers.21.mlp.fc2.bias": "model-00002-of-00002.safetensors",
544
- "vpm.encoder.layers.21.mlp.fc2.weight": "model-00002-of-00002.safetensors",
545
- "vpm.encoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
546
- "vpm.encoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
547
- "vpm.encoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
548
- "vpm.encoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
549
- "vpm.encoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
550
- "vpm.encoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
551
- "vpm.encoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
552
- "vpm.encoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
553
- "vpm.encoder.layers.22.layer_norm1.bias": "model-00002-of-00002.safetensors",
554
- "vpm.encoder.layers.22.layer_norm1.weight": "model-00002-of-00002.safetensors",
555
- "vpm.encoder.layers.22.layer_norm2.bias": "model-00002-of-00002.safetensors",
556
- "vpm.encoder.layers.22.layer_norm2.weight": "model-00002-of-00002.safetensors",
557
- "vpm.encoder.layers.22.mlp.fc1.bias": "model-00002-of-00002.safetensors",
558
- "vpm.encoder.layers.22.mlp.fc1.weight": "model-00002-of-00002.safetensors",
559
- "vpm.encoder.layers.22.mlp.fc2.bias": "model-00002-of-00002.safetensors",
560
- "vpm.encoder.layers.22.mlp.fc2.weight": "model-00002-of-00002.safetensors",
561
- "vpm.encoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
562
- "vpm.encoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
563
- "vpm.encoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
564
- "vpm.encoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
565
- "vpm.encoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
566
- "vpm.encoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
567
- "vpm.encoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
568
- "vpm.encoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
569
- "vpm.encoder.layers.23.layer_norm1.bias": "model-00002-of-00002.safetensors",
570
- "vpm.encoder.layers.23.layer_norm1.weight": "model-00002-of-00002.safetensors",
571
- "vpm.encoder.layers.23.layer_norm2.bias": "model-00002-of-00002.safetensors",
572
- "vpm.encoder.layers.23.layer_norm2.weight": "model-00002-of-00002.safetensors",
573
- "vpm.encoder.layers.23.mlp.fc1.bias": "model-00002-of-00002.safetensors",
574
- "vpm.encoder.layers.23.mlp.fc1.weight": "model-00002-of-00002.safetensors",
575
- "vpm.encoder.layers.23.mlp.fc2.bias": "model-00002-of-00002.safetensors",
576
- "vpm.encoder.layers.23.mlp.fc2.weight": "model-00002-of-00002.safetensors",
577
- "vpm.encoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
578
- "vpm.encoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
579
- "vpm.encoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
580
- "vpm.encoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
581
- "vpm.encoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
582
- "vpm.encoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
583
- "vpm.encoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
584
- "vpm.encoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
585
- "vpm.encoder.layers.24.layer_norm1.bias": "model-00002-of-00002.safetensors",
586
- "vpm.encoder.layers.24.layer_norm1.weight": "model-00002-of-00002.safetensors",
587
- "vpm.encoder.layers.24.layer_norm2.bias": "model-00002-of-00002.safetensors",
588
- "vpm.encoder.layers.24.layer_norm2.weight": "model-00002-of-00002.safetensors",
589
- "vpm.encoder.layers.24.mlp.fc1.bias": "model-00002-of-00002.safetensors",
590
- "vpm.encoder.layers.24.mlp.fc1.weight": "model-00002-of-00002.safetensors",
591
- "vpm.encoder.layers.24.mlp.fc2.bias": "model-00002-of-00002.safetensors",
592
- "vpm.encoder.layers.24.mlp.fc2.weight": "model-00002-of-00002.safetensors",
593
- "vpm.encoder.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
594
- "vpm.encoder.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
595
- "vpm.encoder.layers.24.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
596
- "vpm.encoder.layers.24.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
597
- "vpm.encoder.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
598
- "vpm.encoder.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
599
- "vpm.encoder.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
600
- "vpm.encoder.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
601
- "vpm.encoder.layers.25.layer_norm1.bias": "model-00002-of-00002.safetensors",
602
- "vpm.encoder.layers.25.layer_norm1.weight": "model-00002-of-00002.safetensors",
603
- "vpm.encoder.layers.25.layer_norm2.bias": "model-00002-of-00002.safetensors",
604
- "vpm.encoder.layers.25.layer_norm2.weight": "model-00002-of-00002.safetensors",
605
- "vpm.encoder.layers.25.mlp.fc1.bias": "model-00002-of-00002.safetensors",
606
- "vpm.encoder.layers.25.mlp.fc1.weight": "model-00002-of-00002.safetensors",
607
- "vpm.encoder.layers.25.mlp.fc2.bias": "model-00002-of-00002.safetensors",
608
- "vpm.encoder.layers.25.mlp.fc2.weight": "model-00002-of-00002.safetensors",
609
- "vpm.encoder.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
610
- "vpm.encoder.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
611
- "vpm.encoder.layers.25.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
612
- "vpm.encoder.layers.25.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
613
- "vpm.encoder.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
614
- "vpm.encoder.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
615
- "vpm.encoder.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
616
- "vpm.encoder.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
617
- "vpm.encoder.layers.26.layer_norm1.bias": "model-00002-of-00002.safetensors",
618
- "vpm.encoder.layers.26.layer_norm1.weight": "model-00002-of-00002.safetensors",
619
- "vpm.encoder.layers.26.layer_norm2.bias": "model-00002-of-00002.safetensors",
620
- "vpm.encoder.layers.26.layer_norm2.weight": "model-00002-of-00002.safetensors",
621
- "vpm.encoder.layers.26.mlp.fc1.bias": "model-00002-of-00002.safetensors",
622
- "vpm.encoder.layers.26.mlp.fc1.weight": "model-00002-of-00002.safetensors",
623
- "vpm.encoder.layers.26.mlp.fc2.bias": "model-00002-of-00002.safetensors",
624
- "vpm.encoder.layers.26.mlp.fc2.weight": "model-00002-of-00002.safetensors",
625
- "vpm.encoder.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
626
- "vpm.encoder.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
627
- "vpm.encoder.layers.26.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
628
- "vpm.encoder.layers.26.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
629
- "vpm.encoder.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
630
- "vpm.encoder.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
631
- "vpm.encoder.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
632
- "vpm.encoder.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
633
- "vpm.encoder.layers.3.layer_norm1.bias": "model-00002-of-00002.safetensors",
634
- "vpm.encoder.layers.3.layer_norm1.weight": "model-00002-of-00002.safetensors",
635
- "vpm.encoder.layers.3.layer_norm2.bias": "model-00002-of-00002.safetensors",
636
- "vpm.encoder.layers.3.layer_norm2.weight": "model-00002-of-00002.safetensors",
637
- "vpm.encoder.layers.3.mlp.fc1.bias": "model-00002-of-00002.safetensors",
638
- "vpm.encoder.layers.3.mlp.fc1.weight": "model-00002-of-00002.safetensors",
639
- "vpm.encoder.layers.3.mlp.fc2.bias": "model-00002-of-00002.safetensors",
640
- "vpm.encoder.layers.3.mlp.fc2.weight": "model-00002-of-00002.safetensors",
641
- "vpm.encoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
642
- "vpm.encoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
643
- "vpm.encoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
644
- "vpm.encoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
645
- "vpm.encoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
646
- "vpm.encoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
647
- "vpm.encoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
648
- "vpm.encoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
649
- "vpm.encoder.layers.4.layer_norm1.bias": "model-00002-of-00002.safetensors",
650
- "vpm.encoder.layers.4.layer_norm1.weight": "model-00002-of-00002.safetensors",
651
- "vpm.encoder.layers.4.layer_norm2.bias": "model-00002-of-00002.safetensors",
652
- "vpm.encoder.layers.4.layer_norm2.weight": "model-00002-of-00002.safetensors",
653
- "vpm.encoder.layers.4.mlp.fc1.bias": "model-00002-of-00002.safetensors",
654
- "vpm.encoder.layers.4.mlp.fc1.weight": "model-00002-of-00002.safetensors",
655
- "vpm.encoder.layers.4.mlp.fc2.bias": "model-00002-of-00002.safetensors",
656
- "vpm.encoder.layers.4.mlp.fc2.weight": "model-00002-of-00002.safetensors",
657
- "vpm.encoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
658
- "vpm.encoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
659
- "vpm.encoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
660
- "vpm.encoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
661
- "vpm.encoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
662
- "vpm.encoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
663
- "vpm.encoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
664
- "vpm.encoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
665
- "vpm.encoder.layers.5.layer_norm1.bias": "model-00002-of-00002.safetensors",
666
- "vpm.encoder.layers.5.layer_norm1.weight": "model-00002-of-00002.safetensors",
667
- "vpm.encoder.layers.5.layer_norm2.bias": "model-00002-of-00002.safetensors",
668
- "vpm.encoder.layers.5.layer_norm2.weight": "model-00002-of-00002.safetensors",
669
- "vpm.encoder.layers.5.mlp.fc1.bias": "model-00002-of-00002.safetensors",
670
- "vpm.encoder.layers.5.mlp.fc1.weight": "model-00002-of-00002.safetensors",
671
- "vpm.encoder.layers.5.mlp.fc2.bias": "model-00002-of-00002.safetensors",
672
- "vpm.encoder.layers.5.mlp.fc2.weight": "model-00002-of-00002.safetensors",
673
- "vpm.encoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
674
- "vpm.encoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
675
- "vpm.encoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
676
- "vpm.encoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
677
- "vpm.encoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
678
- "vpm.encoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
679
- "vpm.encoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
680
- "vpm.encoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
681
- "vpm.encoder.layers.6.layer_norm1.bias": "model-00002-of-00002.safetensors",
682
- "vpm.encoder.layers.6.layer_norm1.weight": "model-00002-of-00002.safetensors",
683
- "vpm.encoder.layers.6.layer_norm2.bias": "model-00002-of-00002.safetensors",
684
- "vpm.encoder.layers.6.layer_norm2.weight": "model-00002-of-00002.safetensors",
685
- "vpm.encoder.layers.6.mlp.fc1.bias": "model-00002-of-00002.safetensors",
686
- "vpm.encoder.layers.6.mlp.fc1.weight": "model-00002-of-00002.safetensors",
687
- "vpm.encoder.layers.6.mlp.fc2.bias": "model-00002-of-00002.safetensors",
688
- "vpm.encoder.layers.6.mlp.fc2.weight": "model-00002-of-00002.safetensors",
689
- "vpm.encoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
690
- "vpm.encoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
691
- "vpm.encoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
692
- "vpm.encoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
693
- "vpm.encoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
694
- "vpm.encoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
695
- "vpm.encoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
696
- "vpm.encoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
697
- "vpm.encoder.layers.7.layer_norm1.bias": "model-00002-of-00002.safetensors",
698
- "vpm.encoder.layers.7.layer_norm1.weight": "model-00002-of-00002.safetensors",
699
- "vpm.encoder.layers.7.layer_norm2.bias": "model-00002-of-00002.safetensors",
700
- "vpm.encoder.layers.7.layer_norm2.weight": "model-00002-of-00002.safetensors",
701
- "vpm.encoder.layers.7.mlp.fc1.bias": "model-00002-of-00002.safetensors",
702
- "vpm.encoder.layers.7.mlp.fc1.weight": "model-00002-of-00002.safetensors",
703
- "vpm.encoder.layers.7.mlp.fc2.bias": "model-00002-of-00002.safetensors",
704
- "vpm.encoder.layers.7.mlp.fc2.weight": "model-00002-of-00002.safetensors",
705
- "vpm.encoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
706
- "vpm.encoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
707
- "vpm.encoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
708
- "vpm.encoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
709
- "vpm.encoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
710
- "vpm.encoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
711
- "vpm.encoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
712
- "vpm.encoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
713
- "vpm.encoder.layers.8.layer_norm1.bias": "model-00002-of-00002.safetensors",
714
- "vpm.encoder.layers.8.layer_norm1.weight": "model-00002-of-00002.safetensors",
715
- "vpm.encoder.layers.8.layer_norm2.bias": "model-00002-of-00002.safetensors",
716
- "vpm.encoder.layers.8.layer_norm2.weight": "model-00002-of-00002.safetensors",
717
- "vpm.encoder.layers.8.mlp.fc1.bias": "model-00002-of-00002.safetensors",
718
- "vpm.encoder.layers.8.mlp.fc1.weight": "model-00002-of-00002.safetensors",
719
- "vpm.encoder.layers.8.mlp.fc2.bias": "model-00002-of-00002.safetensors",
720
- "vpm.encoder.layers.8.mlp.fc2.weight": "model-00002-of-00002.safetensors",
721
- "vpm.encoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
722
- "vpm.encoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
723
- "vpm.encoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
724
- "vpm.encoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
725
- "vpm.encoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
726
- "vpm.encoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
727
- "vpm.encoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
728
- "vpm.encoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
729
- "vpm.encoder.layers.9.layer_norm1.bias": "model-00002-of-00002.safetensors",
730
- "vpm.encoder.layers.9.layer_norm1.weight": "model-00002-of-00002.safetensors",
731
- "vpm.encoder.layers.9.layer_norm2.bias": "model-00002-of-00002.safetensors",
732
- "vpm.encoder.layers.9.layer_norm2.weight": "model-00002-of-00002.safetensors",
733
- "vpm.encoder.layers.9.mlp.fc1.bias": "model-00002-of-00002.safetensors",
734
- "vpm.encoder.layers.9.mlp.fc1.weight": "model-00002-of-00002.safetensors",
735
- "vpm.encoder.layers.9.mlp.fc2.bias": "model-00002-of-00002.safetensors",
736
- "vpm.encoder.layers.9.mlp.fc2.weight": "model-00002-of-00002.safetensors",
737
- "vpm.encoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
738
- "vpm.encoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
739
- "vpm.encoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
740
- "vpm.encoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
741
- "vpm.encoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
742
- "vpm.encoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
743
- "vpm.encoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
744
- "vpm.encoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
745
- "vpm.post_layernorm.bias": "model-00002-of-00002.safetensors",
746
- "vpm.post_layernorm.weight": "model-00002-of-00002.safetensors"
747
- }
748
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
preprocessor_config.json DELETED
@@ -1,24 +0,0 @@
1
- {
2
- "image_processor_type": "MiniCPMVImageProcessor",
3
- "auto_map": {
4
- "AutoProcessor": "processing_minicpmv.MiniCPMVProcessor",
5
- "AutoImageProcessor": "image_processing_minicpmv.MiniCPMVImageProcessor"
6
- },
7
- "processor_class": "MiniCPMVProcessor",
8
- "max_slice_nums": 9,
9
- "scale_resolution": 448,
10
- "patch_size": 14,
11
- "use_image_id": true,
12
- "image_feature_size": 64,
13
- "im_start": "<image>",
14
- "im_end": "</image>",
15
- "slice_start": "<slice>",
16
- "slice_end": "</slice>",
17
- "unk": "<unk>",
18
- "im_id_start": "<image_id>",
19
- "im_id_end": "</image_id>",
20
- "slice_mode": true,
21
- "norm_mean": [0.5, 0.5, 0.5],
22
- "norm_std": [0.5, 0.5, 0.5],
23
- "version": 3.0
24
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
special_tokens_map.json DELETED
@@ -1,81 +0,0 @@
1
- {
2
- "additional_special_tokens": [
3
- {
4
- "content": "<|im_end|>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false
9
- },
10
- {
11
- "content": "<|im_start|>",
12
- "lstrip": false,
13
- "normalized": false,
14
- "rstrip": false,
15
- "single_word": false
16
- },
17
- {
18
- "content": "<|tool_call|>",
19
- "lstrip": false,
20
- "normalized": false,
21
- "rstrip": false,
22
- "single_word": false
23
- },
24
- {
25
- "content": "<|execute_start|>",
26
- "lstrip": false,
27
- "normalized": false,
28
- "rstrip": false,
29
- "single_word": false
30
- },
31
- {
32
- "content": "<|execute_end|>",
33
- "lstrip": false,
34
- "normalized": false,
35
- "rstrip": false,
36
- "single_word": false
37
- },
38
- {
39
- "content": "<|fim_prefix|>",
40
- "lstrip": false,
41
- "normalized": false,
42
- "rstrip": false,
43
- "single_word": false
44
- },
45
- {
46
- "content": "<|fim_middle|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false
51
- },
52
- {
53
- "content": "<|fim_suffix|>",
54
- "lstrip": false,
55
- "normalized": false,
56
- "rstrip": false,
57
- "single_word": false
58
- }
59
- ],
60
- "bos_token": {
61
- "content": "<s>",
62
- "lstrip": false,
63
- "normalized": false,
64
- "rstrip": false,
65
- "single_word": false
66
- },
67
- "eos_token": {
68
- "content": "</s>",
69
- "lstrip": false,
70
- "normalized": false,
71
- "rstrip": false,
72
- "single_word": false
73
- },
74
- "unk_token": {
75
- "content": "<unk>",
76
- "lstrip": false,
77
- "normalized": false,
78
- "rstrip": false,
79
- "single_word": false
80
- }
81
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json DELETED
@@ -1,120 +0,0 @@
1
- {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
- "added_tokens_decoder": {
5
- "0": {
6
- "content": "<unk>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "1": {
14
- "content": "<s>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "2": {
22
- "content": "</s>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- },
29
- "73440": {
30
- "content": "<|im_end|>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "73441": {
38
- "content": "<|im_start|>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": true
44
- },
45
- "73442": {
46
- "content": "<|tool_call|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "73443": {
54
- "content": "<|execute_start|>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "73444": {
62
- "content": "<|execute_end|>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": false,
66
- "single_word": false,
67
- "special": true
68
- },
69
- "73445": {
70
- "content": "<|fim_prefix|>",
71
- "lstrip": false,
72
- "normalized": false,
73
- "rstrip": false,
74
- "single_word": false,
75
- "special": true
76
- },
77
- "73446": {
78
- "content": "<|fim_middle|>",
79
- "lstrip": false,
80
- "normalized": false,
81
- "rstrip": false
82
- },
83
- "73447": {
84
- "content": "<|fim_suffix|>",
85
- "lstrip": false,
86
- "normalized": false,
87
- "rstrip": false,
88
- "single_word": false,
89
- "special": true
90
- }
91
- },
92
- "additional_special_tokens": [
93
- "<|im_end|>",
94
- "<|im_start|>",
95
- "<|tool_call|>",
96
- "<|execute_start|>",
97
- "<|execute_end|>",
98
- "<|fim_prefix|>",
99
- "<|fim_middle|>",
100
- "<|fim_suffix|>"
101
- ],
102
- "bos_token": "<s>",
103
- "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
104
- "clean_up_tokenization_spaces": false,
105
- "eos_token": "<|im_end|>",
106
- "legacy": true,
107
- "model_max_length": 1000000000000000019884624838656,
108
- "pad_token": null,
109
- "sp_model_kwargs": {},
110
- "spaces_between_special_tokens": false,
111
- "auto_map": {
112
- "AutoTokenizer": [
113
- "tokenization_minicpmv_fast.MiniCPMVTokenizerFast",
114
- null
115
- ]
116
- },
117
- "tokenizer_class": "MiniCPMVTokenizerFast",
118
- "unk_token": "<unk>",
119
- "use_default_system_prompt": false
120
- }