LeroyDyer commited on
Commit
79703b2
1 Parent(s): e4d7a86

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<image>": 32002,
3
+ "<pad>": 32003,
4
+ "<|endthought|>": 32001,
5
+ "<|startthought|>": 32000
6
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "LeroyDyer/Mixtral_AI_MiniTron_SFT",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 16,
17
+ "num_key_value_heads": 8,
18
+ "pad_token_id": 2,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_theta": 10000.0,
21
+ "sliding_window": 4096,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "float16",
24
+ "transformers_version": "4.38.2",
25
+ "unsloth_version": "2024.4",
26
+ "use_cache": true,
27
+ "vocab_size": 32004
28
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 2,
6
+ "transformers_version": "4.38.2"
7
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b312bc90fb41027279441a6afd34b620688bad8fbe8a1153ce8d2c9b15c8f44e
3
+ size 4943195008
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62d7b7702dbb69677a38b8172044d12d61ca64e96282a88b687cd1a7e7f110b6
3
+ size 3231211496
model.safetensors.index.json ADDED
@@ -0,0 +1,467 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 8174347264
4
+ },
5
+ "weight_map": {
6
+ "ImageProcessor.decoder.lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "ImageProcessor.decoder.model.embed_tokens.weight": "model-00002-of-00002.safetensors",
8
+ "ImageProcessor.decoder.model.layers.0.input_layernorm.weight": "model-00002-of-00002.safetensors",
9
+ "ImageProcessor.decoder.model.layers.0.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
10
+ "ImageProcessor.decoder.model.layers.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
11
+ "ImageProcessor.decoder.model.layers.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
12
+ "ImageProcessor.decoder.model.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
13
+ "ImageProcessor.decoder.model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
14
+ "ImageProcessor.decoder.model.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
15
+ "ImageProcessor.decoder.model.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
16
+ "ImageProcessor.decoder.model.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
17
+ "ImageProcessor.decoder.model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors",
18
+ "ImageProcessor.decoder.model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
19
+ "ImageProcessor.decoder.model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
20
+ "ImageProcessor.decoder.model.layers.1.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
21
+ "ImageProcessor.decoder.model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
22
+ "ImageProcessor.decoder.model.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
23
+ "ImageProcessor.decoder.model.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
24
+ "ImageProcessor.decoder.model.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
25
+ "ImageProcessor.decoder.model.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
26
+ "ImageProcessor.decoder.model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
27
+ "ImageProcessor.decoder.model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
28
+ "ImageProcessor.decoder.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
29
+ "ImageProcessor.decoder.model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
30
+ "ImageProcessor.decoder.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
31
+ "ImageProcessor.decoder.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
32
+ "ImageProcessor.decoder.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
33
+ "ImageProcessor.decoder.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
34
+ "ImageProcessor.decoder.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
35
+ "ImageProcessor.decoder.model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
36
+ "ImageProcessor.decoder.model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
37
+ "ImageProcessor.decoder.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
38
+ "ImageProcessor.decoder.model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
39
+ "ImageProcessor.decoder.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
40
+ "ImageProcessor.decoder.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
41
+ "ImageProcessor.decoder.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
42
+ "ImageProcessor.decoder.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
43
+ "ImageProcessor.decoder.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
44
+ "ImageProcessor.decoder.model.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors",
45
+ "ImageProcessor.decoder.model.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
46
+ "ImageProcessor.decoder.model.layers.2.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
47
+ "ImageProcessor.decoder.model.layers.2.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
48
+ "ImageProcessor.decoder.model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
49
+ "ImageProcessor.decoder.model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
50
+ "ImageProcessor.decoder.model.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
51
+ "ImageProcessor.decoder.model.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
52
+ "ImageProcessor.decoder.model.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
53
+ "ImageProcessor.decoder.model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
54
+ "ImageProcessor.decoder.model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
55
+ "ImageProcessor.decoder.model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
56
+ "ImageProcessor.decoder.model.layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
57
+ "ImageProcessor.decoder.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
58
+ "ImageProcessor.decoder.model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
59
+ "ImageProcessor.decoder.model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
60
+ "ImageProcessor.decoder.model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
61
+ "ImageProcessor.decoder.model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
62
+ "ImageProcessor.decoder.model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors",
63
+ "ImageProcessor.decoder.model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
64
+ "ImageProcessor.decoder.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
65
+ "ImageProcessor.decoder.model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
66
+ "ImageProcessor.decoder.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
67
+ "ImageProcessor.decoder.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
68
+ "ImageProcessor.decoder.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
69
+ "ImageProcessor.decoder.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
70
+ "ImageProcessor.decoder.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
71
+ "ImageProcessor.decoder.model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
72
+ "ImageProcessor.decoder.model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
73
+ "ImageProcessor.decoder.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
74
+ "ImageProcessor.decoder.model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
75
+ "ImageProcessor.decoder.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
76
+ "ImageProcessor.decoder.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
77
+ "ImageProcessor.decoder.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
78
+ "ImageProcessor.decoder.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
79
+ "ImageProcessor.decoder.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
80
+ "ImageProcessor.decoder.model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors",
81
+ "ImageProcessor.decoder.model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
82
+ "ImageProcessor.decoder.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
83
+ "ImageProcessor.decoder.model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
84
+ "ImageProcessor.decoder.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
85
+ "ImageProcessor.decoder.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
86
+ "ImageProcessor.decoder.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
87
+ "ImageProcessor.decoder.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
88
+ "ImageProcessor.decoder.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
89
+ "ImageProcessor.decoder.model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
90
+ "ImageProcessor.decoder.model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
91
+ "ImageProcessor.decoder.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
92
+ "ImageProcessor.decoder.model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
93
+ "ImageProcessor.decoder.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
94
+ "ImageProcessor.decoder.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
95
+ "ImageProcessor.decoder.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
96
+ "ImageProcessor.decoder.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
97
+ "ImageProcessor.decoder.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
98
+ "ImageProcessor.decoder.model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
99
+ "ImageProcessor.decoder.model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
100
+ "ImageProcessor.decoder.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
101
+ "ImageProcessor.decoder.model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
102
+ "ImageProcessor.decoder.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
103
+ "ImageProcessor.decoder.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
104
+ "ImageProcessor.decoder.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
105
+ "ImageProcessor.decoder.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
106
+ "ImageProcessor.decoder.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
107
+ "ImageProcessor.decoder.model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
108
+ "ImageProcessor.decoder.model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
109
+ "ImageProcessor.decoder.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
110
+ "ImageProcessor.decoder.model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
111
+ "ImageProcessor.decoder.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
112
+ "ImageProcessor.decoder.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
113
+ "ImageProcessor.decoder.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
114
+ "ImageProcessor.decoder.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
115
+ "ImageProcessor.decoder.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
116
+ "ImageProcessor.decoder.model.norm.weight": "model-00002-of-00002.safetensors",
117
+ "ImageProcessor.enc_to_dec_proj.bias": "model-00002-of-00002.safetensors",
118
+ "ImageProcessor.enc_to_dec_proj.weight": "model-00002-of-00002.safetensors",
119
+ "ImageProcessor.encoder.embeddings.cls_token": "model-00002-of-00002.safetensors",
120
+ "ImageProcessor.encoder.embeddings.patch_embeddings.projection.bias": "model-00002-of-00002.safetensors",
121
+ "ImageProcessor.encoder.embeddings.patch_embeddings.projection.weight": "model-00002-of-00002.safetensors",
122
+ "ImageProcessor.encoder.embeddings.position_embeddings": "model-00002-of-00002.safetensors",
123
+ "ImageProcessor.encoder.encoder.layer.0.attention.attention.key.bias": "model-00002-of-00002.safetensors",
124
+ "ImageProcessor.encoder.encoder.layer.0.attention.attention.key.weight": "model-00002-of-00002.safetensors",
125
+ "ImageProcessor.encoder.encoder.layer.0.attention.attention.query.bias": "model-00002-of-00002.safetensors",
126
+ "ImageProcessor.encoder.encoder.layer.0.attention.attention.query.weight": "model-00002-of-00002.safetensors",
127
+ "ImageProcessor.encoder.encoder.layer.0.attention.attention.value.bias": "model-00002-of-00002.safetensors",
128
+ "ImageProcessor.encoder.encoder.layer.0.attention.attention.value.weight": "model-00002-of-00002.safetensors",
129
+ "ImageProcessor.encoder.encoder.layer.0.attention.output.dense.bias": "model-00002-of-00002.safetensors",
130
+ "ImageProcessor.encoder.encoder.layer.0.attention.output.dense.weight": "model-00002-of-00002.safetensors",
131
+ "ImageProcessor.encoder.encoder.layer.0.intermediate.dense.bias": "model-00002-of-00002.safetensors",
132
+ "ImageProcessor.encoder.encoder.layer.0.intermediate.dense.weight": "model-00002-of-00002.safetensors",
133
+ "ImageProcessor.encoder.encoder.layer.0.layernorm_after.bias": "model-00002-of-00002.safetensors",
134
+ "ImageProcessor.encoder.encoder.layer.0.layernorm_after.weight": "model-00002-of-00002.safetensors",
135
+ "ImageProcessor.encoder.encoder.layer.0.layernorm_before.bias": "model-00002-of-00002.safetensors",
136
+ "ImageProcessor.encoder.encoder.layer.0.layernorm_before.weight": "model-00002-of-00002.safetensors",
137
+ "ImageProcessor.encoder.encoder.layer.0.output.dense.bias": "model-00002-of-00002.safetensors",
138
+ "ImageProcessor.encoder.encoder.layer.0.output.dense.weight": "model-00002-of-00002.safetensors",
139
+ "ImageProcessor.encoder.encoder.layer.1.attention.attention.key.bias": "model-00002-of-00002.safetensors",
140
+ "ImageProcessor.encoder.encoder.layer.1.attention.attention.key.weight": "model-00002-of-00002.safetensors",
141
+ "ImageProcessor.encoder.encoder.layer.1.attention.attention.query.bias": "model-00002-of-00002.safetensors",
142
+ "ImageProcessor.encoder.encoder.layer.1.attention.attention.query.weight": "model-00002-of-00002.safetensors",
143
+ "ImageProcessor.encoder.encoder.layer.1.attention.attention.value.bias": "model-00002-of-00002.safetensors",
144
+ "ImageProcessor.encoder.encoder.layer.1.attention.attention.value.weight": "model-00002-of-00002.safetensors",
145
+ "ImageProcessor.encoder.encoder.layer.1.attention.output.dense.bias": "model-00002-of-00002.safetensors",
146
+ "ImageProcessor.encoder.encoder.layer.1.attention.output.dense.weight": "model-00002-of-00002.safetensors",
147
+ "ImageProcessor.encoder.encoder.layer.1.intermediate.dense.bias": "model-00002-of-00002.safetensors",
148
+ "ImageProcessor.encoder.encoder.layer.1.intermediate.dense.weight": "model-00002-of-00002.safetensors",
149
+ "ImageProcessor.encoder.encoder.layer.1.layernorm_after.bias": "model-00002-of-00002.safetensors",
150
+ "ImageProcessor.encoder.encoder.layer.1.layernorm_after.weight": "model-00002-of-00002.safetensors",
151
+ "ImageProcessor.encoder.encoder.layer.1.layernorm_before.bias": "model-00002-of-00002.safetensors",
152
+ "ImageProcessor.encoder.encoder.layer.1.layernorm_before.weight": "model-00002-of-00002.safetensors",
153
+ "ImageProcessor.encoder.encoder.layer.1.output.dense.bias": "model-00002-of-00002.safetensors",
154
+ "ImageProcessor.encoder.encoder.layer.1.output.dense.weight": "model-00002-of-00002.safetensors",
155
+ "ImageProcessor.encoder.encoder.layer.10.attention.attention.key.bias": "model-00002-of-00002.safetensors",
156
+ "ImageProcessor.encoder.encoder.layer.10.attention.attention.key.weight": "model-00002-of-00002.safetensors",
157
+ "ImageProcessor.encoder.encoder.layer.10.attention.attention.query.bias": "model-00002-of-00002.safetensors",
158
+ "ImageProcessor.encoder.encoder.layer.10.attention.attention.query.weight": "model-00002-of-00002.safetensors",
159
+ "ImageProcessor.encoder.encoder.layer.10.attention.attention.value.bias": "model-00002-of-00002.safetensors",
160
+ "ImageProcessor.encoder.encoder.layer.10.attention.attention.value.weight": "model-00002-of-00002.safetensors",
161
+ "ImageProcessor.encoder.encoder.layer.10.attention.output.dense.bias": "model-00002-of-00002.safetensors",
162
+ "ImageProcessor.encoder.encoder.layer.10.attention.output.dense.weight": "model-00002-of-00002.safetensors",
163
+ "ImageProcessor.encoder.encoder.layer.10.intermediate.dense.bias": "model-00002-of-00002.safetensors",
164
+ "ImageProcessor.encoder.encoder.layer.10.intermediate.dense.weight": "model-00002-of-00002.safetensors",
165
+ "ImageProcessor.encoder.encoder.layer.10.layernorm_after.bias": "model-00002-of-00002.safetensors",
166
+ "ImageProcessor.encoder.encoder.layer.10.layernorm_after.weight": "model-00002-of-00002.safetensors",
167
+ "ImageProcessor.encoder.encoder.layer.10.layernorm_before.bias": "model-00002-of-00002.safetensors",
168
+ "ImageProcessor.encoder.encoder.layer.10.layernorm_before.weight": "model-00002-of-00002.safetensors",
169
+ "ImageProcessor.encoder.encoder.layer.10.output.dense.bias": "model-00002-of-00002.safetensors",
170
+ "ImageProcessor.encoder.encoder.layer.10.output.dense.weight": "model-00002-of-00002.safetensors",
171
+ "ImageProcessor.encoder.encoder.layer.11.attention.attention.key.bias": "model-00002-of-00002.safetensors",
172
+ "ImageProcessor.encoder.encoder.layer.11.attention.attention.key.weight": "model-00002-of-00002.safetensors",
173
+ "ImageProcessor.encoder.encoder.layer.11.attention.attention.query.bias": "model-00002-of-00002.safetensors",
174
+ "ImageProcessor.encoder.encoder.layer.11.attention.attention.query.weight": "model-00002-of-00002.safetensors",
175
+ "ImageProcessor.encoder.encoder.layer.11.attention.attention.value.bias": "model-00002-of-00002.safetensors",
176
+ "ImageProcessor.encoder.encoder.layer.11.attention.attention.value.weight": "model-00002-of-00002.safetensors",
177
+ "ImageProcessor.encoder.encoder.layer.11.attention.output.dense.bias": "model-00002-of-00002.safetensors",
178
+ "ImageProcessor.encoder.encoder.layer.11.attention.output.dense.weight": "model-00002-of-00002.safetensors",
179
+ "ImageProcessor.encoder.encoder.layer.11.intermediate.dense.bias": "model-00002-of-00002.safetensors",
180
+ "ImageProcessor.encoder.encoder.layer.11.intermediate.dense.weight": "model-00002-of-00002.safetensors",
181
+ "ImageProcessor.encoder.encoder.layer.11.layernorm_after.bias": "model-00002-of-00002.safetensors",
182
+ "ImageProcessor.encoder.encoder.layer.11.layernorm_after.weight": "model-00002-of-00002.safetensors",
183
+ "ImageProcessor.encoder.encoder.layer.11.layernorm_before.bias": "model-00002-of-00002.safetensors",
184
+ "ImageProcessor.encoder.encoder.layer.11.layernorm_before.weight": "model-00002-of-00002.safetensors",
185
+ "ImageProcessor.encoder.encoder.layer.11.output.dense.bias": "model-00002-of-00002.safetensors",
186
+ "ImageProcessor.encoder.encoder.layer.11.output.dense.weight": "model-00002-of-00002.safetensors",
187
+ "ImageProcessor.encoder.encoder.layer.2.attention.attention.key.bias": "model-00002-of-00002.safetensors",
188
+ "ImageProcessor.encoder.encoder.layer.2.attention.attention.key.weight": "model-00002-of-00002.safetensors",
189
+ "ImageProcessor.encoder.encoder.layer.2.attention.attention.query.bias": "model-00002-of-00002.safetensors",
190
+ "ImageProcessor.encoder.encoder.layer.2.attention.attention.query.weight": "model-00002-of-00002.safetensors",
191
+ "ImageProcessor.encoder.encoder.layer.2.attention.attention.value.bias": "model-00002-of-00002.safetensors",
192
+ "ImageProcessor.encoder.encoder.layer.2.attention.attention.value.weight": "model-00002-of-00002.safetensors",
193
+ "ImageProcessor.encoder.encoder.layer.2.attention.output.dense.bias": "model-00002-of-00002.safetensors",
194
+ "ImageProcessor.encoder.encoder.layer.2.attention.output.dense.weight": "model-00002-of-00002.safetensors",
195
+ "ImageProcessor.encoder.encoder.layer.2.intermediate.dense.bias": "model-00002-of-00002.safetensors",
196
+ "ImageProcessor.encoder.encoder.layer.2.intermediate.dense.weight": "model-00002-of-00002.safetensors",
197
+ "ImageProcessor.encoder.encoder.layer.2.layernorm_after.bias": "model-00002-of-00002.safetensors",
198
+ "ImageProcessor.encoder.encoder.layer.2.layernorm_after.weight": "model-00002-of-00002.safetensors",
199
+ "ImageProcessor.encoder.encoder.layer.2.layernorm_before.bias": "model-00002-of-00002.safetensors",
200
+ "ImageProcessor.encoder.encoder.layer.2.layernorm_before.weight": "model-00002-of-00002.safetensors",
201
+ "ImageProcessor.encoder.encoder.layer.2.output.dense.bias": "model-00002-of-00002.safetensors",
202
+ "ImageProcessor.encoder.encoder.layer.2.output.dense.weight": "model-00002-of-00002.safetensors",
203
+ "ImageProcessor.encoder.encoder.layer.3.attention.attention.key.bias": "model-00002-of-00002.safetensors",
204
+ "ImageProcessor.encoder.encoder.layer.3.attention.attention.key.weight": "model-00002-of-00002.safetensors",
205
+ "ImageProcessor.encoder.encoder.layer.3.attention.attention.query.bias": "model-00002-of-00002.safetensors",
206
+ "ImageProcessor.encoder.encoder.layer.3.attention.attention.query.weight": "model-00002-of-00002.safetensors",
207
+ "ImageProcessor.encoder.encoder.layer.3.attention.attention.value.bias": "model-00002-of-00002.safetensors",
208
+ "ImageProcessor.encoder.encoder.layer.3.attention.attention.value.weight": "model-00002-of-00002.safetensors",
209
+ "ImageProcessor.encoder.encoder.layer.3.attention.output.dense.bias": "model-00002-of-00002.safetensors",
210
+ "ImageProcessor.encoder.encoder.layer.3.attention.output.dense.weight": "model-00002-of-00002.safetensors",
211
+ "ImageProcessor.encoder.encoder.layer.3.intermediate.dense.bias": "model-00002-of-00002.safetensors",
212
+ "ImageProcessor.encoder.encoder.layer.3.intermediate.dense.weight": "model-00002-of-00002.safetensors",
213
+ "ImageProcessor.encoder.encoder.layer.3.layernorm_after.bias": "model-00002-of-00002.safetensors",
214
+ "ImageProcessor.encoder.encoder.layer.3.layernorm_after.weight": "model-00002-of-00002.safetensors",
215
+ "ImageProcessor.encoder.encoder.layer.3.layernorm_before.bias": "model-00002-of-00002.safetensors",
216
+ "ImageProcessor.encoder.encoder.layer.3.layernorm_before.weight": "model-00002-of-00002.safetensors",
217
+ "ImageProcessor.encoder.encoder.layer.3.output.dense.bias": "model-00002-of-00002.safetensors",
218
+ "ImageProcessor.encoder.encoder.layer.3.output.dense.weight": "model-00002-of-00002.safetensors",
219
+ "ImageProcessor.encoder.encoder.layer.4.attention.attention.key.bias": "model-00002-of-00002.safetensors",
220
+ "ImageProcessor.encoder.encoder.layer.4.attention.attention.key.weight": "model-00002-of-00002.safetensors",
221
+ "ImageProcessor.encoder.encoder.layer.4.attention.attention.query.bias": "model-00002-of-00002.safetensors",
222
+ "ImageProcessor.encoder.encoder.layer.4.attention.attention.query.weight": "model-00002-of-00002.safetensors",
223
+ "ImageProcessor.encoder.encoder.layer.4.attention.attention.value.bias": "model-00002-of-00002.safetensors",
224
+ "ImageProcessor.encoder.encoder.layer.4.attention.attention.value.weight": "model-00002-of-00002.safetensors",
225
+ "ImageProcessor.encoder.encoder.layer.4.attention.output.dense.bias": "model-00002-of-00002.safetensors",
226
+ "ImageProcessor.encoder.encoder.layer.4.attention.output.dense.weight": "model-00002-of-00002.safetensors",
227
+ "ImageProcessor.encoder.encoder.layer.4.intermediate.dense.bias": "model-00002-of-00002.safetensors",
228
+ "ImageProcessor.encoder.encoder.layer.4.intermediate.dense.weight": "model-00002-of-00002.safetensors",
229
+ "ImageProcessor.encoder.encoder.layer.4.layernorm_after.bias": "model-00002-of-00002.safetensors",
230
+ "ImageProcessor.encoder.encoder.layer.4.layernorm_after.weight": "model-00002-of-00002.safetensors",
231
+ "ImageProcessor.encoder.encoder.layer.4.layernorm_before.bias": "model-00002-of-00002.safetensors",
232
+ "ImageProcessor.encoder.encoder.layer.4.layernorm_before.weight": "model-00002-of-00002.safetensors",
233
+ "ImageProcessor.encoder.encoder.layer.4.output.dense.bias": "model-00002-of-00002.safetensors",
234
+ "ImageProcessor.encoder.encoder.layer.4.output.dense.weight": "model-00002-of-00002.safetensors",
235
+ "ImageProcessor.encoder.encoder.layer.5.attention.attention.key.bias": "model-00002-of-00002.safetensors",
236
+ "ImageProcessor.encoder.encoder.layer.5.attention.attention.key.weight": "model-00002-of-00002.safetensors",
237
+ "ImageProcessor.encoder.encoder.layer.5.attention.attention.query.bias": "model-00002-of-00002.safetensors",
238
+ "ImageProcessor.encoder.encoder.layer.5.attention.attention.query.weight": "model-00002-of-00002.safetensors",
239
+ "ImageProcessor.encoder.encoder.layer.5.attention.attention.value.bias": "model-00002-of-00002.safetensors",
240
+ "ImageProcessor.encoder.encoder.layer.5.attention.attention.value.weight": "model-00002-of-00002.safetensors",
241
+ "ImageProcessor.encoder.encoder.layer.5.attention.output.dense.bias": "model-00002-of-00002.safetensors",
242
+ "ImageProcessor.encoder.encoder.layer.5.attention.output.dense.weight": "model-00002-of-00002.safetensors",
243
+ "ImageProcessor.encoder.encoder.layer.5.intermediate.dense.bias": "model-00002-of-00002.safetensors",
244
+ "ImageProcessor.encoder.encoder.layer.5.intermediate.dense.weight": "model-00002-of-00002.safetensors",
245
+ "ImageProcessor.encoder.encoder.layer.5.layernorm_after.bias": "model-00002-of-00002.safetensors",
246
+ "ImageProcessor.encoder.encoder.layer.5.layernorm_after.weight": "model-00002-of-00002.safetensors",
247
+ "ImageProcessor.encoder.encoder.layer.5.layernorm_before.bias": "model-00002-of-00002.safetensors",
248
+ "ImageProcessor.encoder.encoder.layer.5.layernorm_before.weight": "model-00002-of-00002.safetensors",
249
+ "ImageProcessor.encoder.encoder.layer.5.output.dense.bias": "model-00002-of-00002.safetensors",
250
+ "ImageProcessor.encoder.encoder.layer.5.output.dense.weight": "model-00002-of-00002.safetensors",
251
+ "ImageProcessor.encoder.encoder.layer.6.attention.attention.key.bias": "model-00002-of-00002.safetensors",
252
+ "ImageProcessor.encoder.encoder.layer.6.attention.attention.key.weight": "model-00002-of-00002.safetensors",
253
+ "ImageProcessor.encoder.encoder.layer.6.attention.attention.query.bias": "model-00002-of-00002.safetensors",
254
+ "ImageProcessor.encoder.encoder.layer.6.attention.attention.query.weight": "model-00002-of-00002.safetensors",
255
+ "ImageProcessor.encoder.encoder.layer.6.attention.attention.value.bias": "model-00002-of-00002.safetensors",
256
+ "ImageProcessor.encoder.encoder.layer.6.attention.attention.value.weight": "model-00002-of-00002.safetensors",
257
+ "ImageProcessor.encoder.encoder.layer.6.attention.output.dense.bias": "model-00002-of-00002.safetensors",
258
+ "ImageProcessor.encoder.encoder.layer.6.attention.output.dense.weight": "model-00002-of-00002.safetensors",
259
+ "ImageProcessor.encoder.encoder.layer.6.intermediate.dense.bias": "model-00002-of-00002.safetensors",
260
+ "ImageProcessor.encoder.encoder.layer.6.intermediate.dense.weight": "model-00002-of-00002.safetensors",
261
+ "ImageProcessor.encoder.encoder.layer.6.layernorm_after.bias": "model-00002-of-00002.safetensors",
262
+ "ImageProcessor.encoder.encoder.layer.6.layernorm_after.weight": "model-00002-of-00002.safetensors",
263
+ "ImageProcessor.encoder.encoder.layer.6.layernorm_before.bias": "model-00002-of-00002.safetensors",
264
+ "ImageProcessor.encoder.encoder.layer.6.layernorm_before.weight": "model-00002-of-00002.safetensors",
265
+ "ImageProcessor.encoder.encoder.layer.6.output.dense.bias": "model-00002-of-00002.safetensors",
266
+ "ImageProcessor.encoder.encoder.layer.6.output.dense.weight": "model-00002-of-00002.safetensors",
267
+ "ImageProcessor.encoder.encoder.layer.7.attention.attention.key.bias": "model-00002-of-00002.safetensors",
268
+ "ImageProcessor.encoder.encoder.layer.7.attention.attention.key.weight": "model-00002-of-00002.safetensors",
269
+ "ImageProcessor.encoder.encoder.layer.7.attention.attention.query.bias": "model-00002-of-00002.safetensors",
270
+ "ImageProcessor.encoder.encoder.layer.7.attention.attention.query.weight": "model-00002-of-00002.safetensors",
271
+ "ImageProcessor.encoder.encoder.layer.7.attention.attention.value.bias": "model-00002-of-00002.safetensors",
272
+ "ImageProcessor.encoder.encoder.layer.7.attention.attention.value.weight": "model-00002-of-00002.safetensors",
273
+ "ImageProcessor.encoder.encoder.layer.7.attention.output.dense.bias": "model-00002-of-00002.safetensors",
274
+ "ImageProcessor.encoder.encoder.layer.7.attention.output.dense.weight": "model-00002-of-00002.safetensors",
275
+ "ImageProcessor.encoder.encoder.layer.7.intermediate.dense.bias": "model-00002-of-00002.safetensors",
276
+ "ImageProcessor.encoder.encoder.layer.7.intermediate.dense.weight": "model-00002-of-00002.safetensors",
277
+ "ImageProcessor.encoder.encoder.layer.7.layernorm_after.bias": "model-00002-of-00002.safetensors",
278
+ "ImageProcessor.encoder.encoder.layer.7.layernorm_after.weight": "model-00002-of-00002.safetensors",
279
+ "ImageProcessor.encoder.encoder.layer.7.layernorm_before.bias": "model-00002-of-00002.safetensors",
280
+ "ImageProcessor.encoder.encoder.layer.7.layernorm_before.weight": "model-00002-of-00002.safetensors",
281
+ "ImageProcessor.encoder.encoder.layer.7.output.dense.bias": "model-00002-of-00002.safetensors",
282
+ "ImageProcessor.encoder.encoder.layer.7.output.dense.weight": "model-00002-of-00002.safetensors",
283
+ "ImageProcessor.encoder.encoder.layer.8.attention.attention.key.bias": "model-00002-of-00002.safetensors",
284
+ "ImageProcessor.encoder.encoder.layer.8.attention.attention.key.weight": "model-00002-of-00002.safetensors",
285
+ "ImageProcessor.encoder.encoder.layer.8.attention.attention.query.bias": "model-00002-of-00002.safetensors",
286
+ "ImageProcessor.encoder.encoder.layer.8.attention.attention.query.weight": "model-00002-of-00002.safetensors",
287
+ "ImageProcessor.encoder.encoder.layer.8.attention.attention.value.bias": "model-00002-of-00002.safetensors",
288
+ "ImageProcessor.encoder.encoder.layer.8.attention.attention.value.weight": "model-00002-of-00002.safetensors",
289
+ "ImageProcessor.encoder.encoder.layer.8.attention.output.dense.bias": "model-00002-of-00002.safetensors",
290
+ "ImageProcessor.encoder.encoder.layer.8.attention.output.dense.weight": "model-00002-of-00002.safetensors",
291
+ "ImageProcessor.encoder.encoder.layer.8.intermediate.dense.bias": "model-00002-of-00002.safetensors",
292
+ "ImageProcessor.encoder.encoder.layer.8.intermediate.dense.weight": "model-00002-of-00002.safetensors",
293
+ "ImageProcessor.encoder.encoder.layer.8.layernorm_after.bias": "model-00002-of-00002.safetensors",
294
+ "ImageProcessor.encoder.encoder.layer.8.layernorm_after.weight": "model-00002-of-00002.safetensors",
295
+ "ImageProcessor.encoder.encoder.layer.8.layernorm_before.bias": "model-00002-of-00002.safetensors",
296
+ "ImageProcessor.encoder.encoder.layer.8.layernorm_before.weight": "model-00002-of-00002.safetensors",
297
+ "ImageProcessor.encoder.encoder.layer.8.output.dense.bias": "model-00002-of-00002.safetensors",
298
+ "ImageProcessor.encoder.encoder.layer.8.output.dense.weight": "model-00002-of-00002.safetensors",
299
+ "ImageProcessor.encoder.encoder.layer.9.attention.attention.key.bias": "model-00002-of-00002.safetensors",
300
+ "ImageProcessor.encoder.encoder.layer.9.attention.attention.key.weight": "model-00002-of-00002.safetensors",
301
+ "ImageProcessor.encoder.encoder.layer.9.attention.attention.query.bias": "model-00002-of-00002.safetensors",
302
+ "ImageProcessor.encoder.encoder.layer.9.attention.attention.query.weight": "model-00002-of-00002.safetensors",
303
+ "ImageProcessor.encoder.encoder.layer.9.attention.attention.value.bias": "model-00002-of-00002.safetensors",
304
+ "ImageProcessor.encoder.encoder.layer.9.attention.attention.value.weight": "model-00002-of-00002.safetensors",
305
+ "ImageProcessor.encoder.encoder.layer.9.attention.output.dense.bias": "model-00002-of-00002.safetensors",
306
+ "ImageProcessor.encoder.encoder.layer.9.attention.output.dense.weight": "model-00002-of-00002.safetensors",
307
+ "ImageProcessor.encoder.encoder.layer.9.intermediate.dense.bias": "model-00002-of-00002.safetensors",
308
+ "ImageProcessor.encoder.encoder.layer.9.intermediate.dense.weight": "model-00002-of-00002.safetensors",
309
+ "ImageProcessor.encoder.encoder.layer.9.layernorm_after.bias": "model-00002-of-00002.safetensors",
310
+ "ImageProcessor.encoder.encoder.layer.9.layernorm_after.weight": "model-00002-of-00002.safetensors",
311
+ "ImageProcessor.encoder.encoder.layer.9.layernorm_before.bias": "model-00002-of-00002.safetensors",
312
+ "ImageProcessor.encoder.encoder.layer.9.layernorm_before.weight": "model-00002-of-00002.safetensors",
313
+ "ImageProcessor.encoder.encoder.layer.9.output.dense.bias": "model-00002-of-00002.safetensors",
314
+ "ImageProcessor.encoder.encoder.layer.9.output.dense.weight": "model-00002-of-00002.safetensors",
315
+ "ImageProcessor.encoder.layernorm.bias": "model-00002-of-00002.safetensors",
316
+ "ImageProcessor.encoder.layernorm.weight": "model-00002-of-00002.safetensors",
317
+ "ImageProcessor.encoder.pooler.dense.bias": "model-00002-of-00002.safetensors",
318
+ "ImageProcessor.encoder.pooler.dense.weight": "model-00002-of-00002.safetensors",
319
+ "lm_head.weight": "model-00002-of-00002.safetensors",
320
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
321
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
322
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
323
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
324
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
325
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
326
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
327
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
328
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
329
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
330
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
331
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
332
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
333
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
334
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
335
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
336
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
337
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
338
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
339
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
340
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
341
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
342
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
343
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
344
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
345
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
346
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
347
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
348
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
349
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
350
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
351
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
352
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
353
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
354
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
355
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
356
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
357
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
358
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
359
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
360
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
361
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
362
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
363
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
364
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
365
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
366
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
367
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
368
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
369
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
370
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
371
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
372
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
373
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
374
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
375
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
376
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
377
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
378
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
379
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
380
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
381
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
382
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
383
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
384
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
385
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
386
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
387
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
388
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
389
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
390
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
391
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
392
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
393
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
394
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
395
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
396
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
397
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
398
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
399
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
400
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
401
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
402
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
403
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
404
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
405
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
406
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
407
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
408
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
409
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
410
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
411
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
412
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
413
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
414
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
415
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
416
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
417
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
418
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
419
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
420
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
421
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
422
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
423
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
424
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
425
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
426
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
427
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
428
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
429
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
430
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
431
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
432
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
433
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
434
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
435
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
436
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
437
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
438
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
439
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
440
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
441
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
442
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
443
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
444
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
445
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
446
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
447
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
448
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
449
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
450
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
451
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
452
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
453
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
454
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
455
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
456
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
457
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
458
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
459
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
460
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
461
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
462
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
463
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
464
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
465
+ "model.norm.weight": "model-00002-of-00002.safetensors"
466
+ }
467
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|startthought|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|endthought|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<|startthought|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "<image>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<pad>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ }
38
+ ],
39
+ "bos_token": {
40
+ "content": "<s>",
41
+ "lstrip": false,
42
+ "normalized": false,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "eos_token": {
47
+ "content": "<|im_end|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
+ "pad_token": "<|im_end|>",
54
+ "unk_token": {
55
+ "content": "<unk>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false
60
+ }
61
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc460a0129515b7579ec9f63218012601729de4fbd1b5de8d56dc47e8a204a29
3
+ size 493449
tokenizer_config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<|startthought|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|endthought|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "<image>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32003": {
54
+ "content": "<pad>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ }
61
+ },
62
+ "additional_special_tokens": [
63
+ "<|startthought|>",
64
+ "<|endthought|>",
65
+ "<|startthought|>",
66
+ "<image>",
67
+ "<pad>"
68
+ ],
69
+ "bos_token": "<s>",
70
+ "chat_template": "{% for message in messages %}{% if message['from'] == 'human' %}{{'<|im_start|>user\n' + message['value'] + '<|im_end|>\n'}}{% elif message['from'] == 'gpt' %}{{'<|im_start|>assistant\n' + message['value'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['value'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
71
+ "clean_up_tokenization_spaces": false,
72
+ "eos_token": "<|im_end|>",
73
+ "model_max_length": 32768,
74
+ "pad_token": "<|im_end|>",
75
+ "padding_side": "right",
76
+ "tokenizer_class": "LlamaTokenizer",
77
+ "truncation": true,
78
+ "unk_token": "<unk>",
79
+ "use_default_system_prompt": false
80
+ }