Hugging Face's logo

AINovice2005
/
quantized-GLM-4.1V-9B-Thinking

Image-Text-to-Text
Transformers
PyTorch
glm4v
conversational
torchao
Model card Files
xet
Community
AINovice2005 commited on
Commit
da2244d
·
verified ·
1 Parent(s): a991593

Add TorchAO quantized-THUDM/GLM-4.1V-9B-Thinking

Browse files
Files changed (13) hide show
  1. .gitattributes +1 -0
  2. chat_template.jinja +33 -0
  3. config.json +131 -0
  4. generation_config.json +11 -0
  5. preprocessor_config.json +27 -0
  6. pytorch_model-00001-of-00003.bin +3 -0
  7. pytorch_model-00002-of-00003.bin +3 -0
  8. pytorch_model-00003-of-00003.bin +3 -0
  9. pytorch_model.bin.index.json +712 -0
  10. special_tokens_map.json +34 -0
  11. tokenizer.json +3 -0
  12. tokenizer_config.json +220 -0
  13. video_preprocessor_config.json +42 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [gMASK]<sop>
2
+ {%- for msg in messages %}
3
+ {%- if msg.role == 'system' %}
4
+ <|system|>
5
+ {{ msg.content }}
6
+ {%- elif msg.role == 'user' %}
7
+ <|user|>{{ '\n' }}
8
+
9
+ {%- if msg.content is string %}
10
+ {{ msg.content }}
11
+ {%- else %}
12
+ {%- for item in msg.content %}
13
+ {%- if item.type == 'video' or 'video' in item %}
14
+ <|begin_of_video|><|video|><|end_of_video|>
15
+ {%- elif item.type == 'image' or 'image' in item %}
16
+ <|begin_of_image|><|image|><|end_of_image|>
17
+ {%- elif item.type == 'text' %}
18
+ {{ item.text }}
19
+ {%- endif %}
20
+ {%- endfor %}
21
+ {%- endif %}
22
+ {%- elif msg.role == 'assistant' %}
23
+ {%- if msg.metadata %}
24
+ <|assistant|>{{ msg.metadata }}
25
+ {{ msg.content }}
26
+ {%- else %}
27
+ <|assistant|>
28
+ {{ msg.content }}
29
+ {%- endif %}
30
+ {%- endif %}
31
+ {%- endfor %}
32
+ {% if add_generation_prompt %}<|assistant|>
33
+ {% endif %}
config.json ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Glm4vForConditionalGeneration"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "eos_token_id": [
8
+ 151329,
9
+ 151336,
10
+ 151338,
11
+ 151348
12
+ ],
13
+ "hidden_act": "silu",
14
+ "hidden_size": 4096,
15
+ "image_end_token_id": 151340,
16
+ "image_start_token_id": 151339,
17
+ "image_token_id": 151343,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 13696,
20
+ "max_position_embeddings": 65536,
21
+ "model_type": "glm4v",
22
+ "num_attention_heads": 32,
23
+ "num_hidden_layers": 40,
24
+ "num_key_value_heads": 2,
25
+ "pad_token_id": 151329,
26
+ "partial_rotary_factor": 0.5,
27
+ "quantization_config": {
28
+ "include_input_output_embeddings": false,
29
+ "modules_to_not_convert": null,
30
+ "quant_method": "torchao",
31
+ "quant_type": {
32
+ "default": {
33
+ "_data": {
34
+ "act_mapping_type": {
35
+ "_data": "SYMMETRIC",
36
+ "_type": "MappingType"
37
+ },
38
+ "layout": {
39
+ "_data": {},
40
+ "_type": "PlainLayout",
41
+ "_version": 1
42
+ },
43
+ "set_inductor_config": true,
44
+ "weight_only_decode": false
45
+ },
46
+ "_type": "Int8DynamicActivationInt8WeightConfig",
47
+ "_version": 1
48
+ }
49
+ },
50
+ "quant_type_kwargs": {},
51
+ "untie_embedding_weights": false
52
+ },
53
+ "rms_norm_eps": 1e-05,
54
+ "rope_scaling": {
55
+ "mrope_section": [
56
+ 8,
57
+ 12,
58
+ 12
59
+ ],
60
+ "rope_type": "default",
61
+ "type": "default"
62
+ },
63
+ "rope_theta": 10000.0,
64
+ "text_config": {
65
+ "architectures": [
66
+ "Glm4vForConditionalGeneration"
67
+ ],
68
+ "attention_bias": true,
69
+ "attention_dropout": 0.0,
70
+ "eos_token_id": [
71
+ 151329,
72
+ 151336,
73
+ 151338,
74
+ 151348
75
+ ],
76
+ "hidden_act": "silu",
77
+ "hidden_size": 4096,
78
+ "image_token_id": null,
79
+ "initializer_range": 0.02,
80
+ "intermediate_size": 13696,
81
+ "max_position_embeddings": 65536,
82
+ "model_type": "glm4v_text",
83
+ "num_attention_heads": 32,
84
+ "num_hidden_layers": 40,
85
+ "num_key_value_heads": 2,
86
+ "pad_token_id": 151329,
87
+ "partial_rotary_factor": 0.5,
88
+ "rms_norm_eps": 1e-05,
89
+ "rope_scaling": {
90
+ "mrope_section": [
91
+ 8,
92
+ 12,
93
+ 12
94
+ ],
95
+ "rope_type": "default",
96
+ "type": "default"
97
+ },
98
+ "rope_theta": 10000.0,
99
+ "torch_dtype": "bfloat16",
100
+ "use_cache": true,
101
+ "video_token_id": null,
102
+ "vocab_size": 151552
103
+ },
104
+ "tie_word_embeddings": false,
105
+ "torch_dtype": "bfloat16",
106
+ "transformers_version": "4.53.2",
107
+ "use_cache": true,
108
+ "video_end_token_id": 151342,
109
+ "video_start_token_id": 151341,
110
+ "video_token_id": 151344,
111
+ "vision_config": {
112
+ "attention_bias": false,
113
+ "attention_dropout": 0.0,
114
+ "depth": 24,
115
+ "hidden_act": "silu",
116
+ "hidden_dropout_prob": 0.0,
117
+ "hidden_size": 1536,
118
+ "image_size": 336,
119
+ "in_channels": 3,
120
+ "initializer_range": 0.02,
121
+ "intermediate_size": 13696,
122
+ "model_type": "glm4v",
123
+ "num_heads": 12,
124
+ "out_hidden_size": 4096,
125
+ "patch_size": 14,
126
+ "rms_norm_eps": 1e-05,
127
+ "spatial_merge_size": 2,
128
+ "temporal_patch_size": 2
129
+ },
130
+ "vocab_size": 151552
131
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 151329,
5
+ 151336,
6
+ 151338,
7
+ 151348
8
+ ],
9
+ "pad_token_id": 151329,
10
+ "transformers_version": "4.53.2"
11
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Glm4vImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "merge_size": 2,
18
+ "patch_size": 14,
19
+ "processor_class": "Glm4vProcessor",
20
+ "resample": 3,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "longest_edge": 11760000,
24
+ "shortest_edge": 12544
25
+ },
26
+ "temporal_patch_size": 2
27
+ }
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff63c7864af85fc2d1875e55f944e3802dde11cc45374bf186a9451d670959b7
3
+ size 4963902039
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cff16025b57f6a32d97f8a20e52e1fe69e70289af52eced78d1d205084417a8
3
+ size 4989723876
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ccb5b4d76896aa318aedfeeaead80d04032adb9bd30f976568d69c25857f20d
3
+ size 1613999083
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,712 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 10292777472,
4
+ "total_size": 11567131136
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "pytorch_model-00003-of-00003.bin",
8
+ "model.language_model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
9
+ "model.language_model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
10
+ "model.language_model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
11
+ "model.language_model.layers.0.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00003.bin",
12
+ "model.language_model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
13
+ "model.language_model.layers.0.post_mlp_layernorm.weight": "pytorch_model-00001-of-00003.bin",
14
+ "model.language_model.layers.0.post_self_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
15
+ "model.language_model.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
16
+ "model.language_model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
17
+ "model.language_model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
18
+ "model.language_model.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
19
+ "model.language_model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
20
+ "model.language_model.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
21
+ "model.language_model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
22
+ "model.language_model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
23
+ "model.language_model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
24
+ "model.language_model.layers.1.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00003.bin",
25
+ "model.language_model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
26
+ "model.language_model.layers.1.post_mlp_layernorm.weight": "pytorch_model-00001-of-00003.bin",
27
+ "model.language_model.layers.1.post_self_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
28
+ "model.language_model.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
29
+ "model.language_model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
30
+ "model.language_model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
31
+ "model.language_model.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
32
+ "model.language_model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
33
+ "model.language_model.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
34
+ "model.language_model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
35
+ "model.language_model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
36
+ "model.language_model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
37
+ "model.language_model.layers.10.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00003.bin",
38
+ "model.language_model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
39
+ "model.language_model.layers.10.post_mlp_layernorm.weight": "pytorch_model-00001-of-00003.bin",
40
+ "model.language_model.layers.10.post_self_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
41
+ "model.language_model.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
42
+ "model.language_model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
43
+ "model.language_model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
44
+ "model.language_model.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
45
+ "model.language_model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
46
+ "model.language_model.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
47
+ "model.language_model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
48
+ "model.language_model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
49
+ "model.language_model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
50
+ "model.language_model.layers.11.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00003.bin",
51
+ "model.language_model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
52
+ "model.language_model.layers.11.post_mlp_layernorm.weight": "pytorch_model-00001-of-00003.bin",
53
+ "model.language_model.layers.11.post_self_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
54
+ "model.language_model.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
55
+ "model.language_model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
56
+ "model.language_model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
57
+ "model.language_model.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
58
+ "model.language_model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
59
+ "model.language_model.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
60
+ "model.language_model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
61
+ "model.language_model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
62
+ "model.language_model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
63
+ "model.language_model.layers.12.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00003.bin",
64
+ "model.language_model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
65
+ "model.language_model.layers.12.post_mlp_layernorm.weight": "pytorch_model-00001-of-00003.bin",
66
+ "model.language_model.layers.12.post_self_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
67
+ "model.language_model.layers.12.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
68
+ "model.language_model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
69
+ "model.language_model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
70
+ "model.language_model.layers.12.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
71
+ "model.language_model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
72
+ "model.language_model.layers.12.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
73
+ "model.language_model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
74
+ "model.language_model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
75
+ "model.language_model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
76
+ "model.language_model.layers.13.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00003.bin",
77
+ "model.language_model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
78
+ "model.language_model.layers.13.post_mlp_layernorm.weight": "pytorch_model-00002-of-00003.bin",
79
+ "model.language_model.layers.13.post_self_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
80
+ "model.language_model.layers.13.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
81
+ "model.language_model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
82
+ "model.language_model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
83
+ "model.language_model.layers.13.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
84
+ "model.language_model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
85
+ "model.language_model.layers.13.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
86
+ "model.language_model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
87
+ "model.language_model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
88
+ "model.language_model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
89
+ "model.language_model.layers.14.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00003.bin",
90
+ "model.language_model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
91
+ "model.language_model.layers.14.post_mlp_layernorm.weight": "pytorch_model-00002-of-00003.bin",
92
+ "model.language_model.layers.14.post_self_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
93
+ "model.language_model.layers.14.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
94
+ "model.language_model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
95
+ "model.language_model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
96
+ "model.language_model.layers.14.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
97
+ "model.language_model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
98
+ "model.language_model.layers.14.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
99
+ "model.language_model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
100
+ "model.language_model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
101
+ "model.language_model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
102
+ "model.language_model.layers.15.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00003.bin",
103
+ "model.language_model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
104
+ "model.language_model.layers.15.post_mlp_layernorm.weight": "pytorch_model-00002-of-00003.bin",
105
+ "model.language_model.layers.15.post_self_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
106
+ "model.language_model.layers.15.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
107
+ "model.language_model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
108
+ "model.language_model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
109
+ "model.language_model.layers.15.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
110
+ "model.language_model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
111
+ "model.language_model.layers.15.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
112
+ "model.language_model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
113
+ "model.language_model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
114
+ "model.language_model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
115
+ "model.language_model.layers.16.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00003.bin",
116
+ "model.language_model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
117
+ "model.language_model.layers.16.post_mlp_layernorm.weight": "pytorch_model-00002-of-00003.bin",
118
+ "model.language_model.layers.16.post_self_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
119
+ "model.language_model.layers.16.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
120
+ "model.language_model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
121
+ "model.language_model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
122
+ "model.language_model.layers.16.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
123
+ "model.language_model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
124
+ "model.language_model.layers.16.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
125
+ "model.language_model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
126
+ "model.language_model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
127
+ "model.language_model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
128
+ "model.language_model.layers.17.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00003.bin",
129
+ "model.language_model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
130
+ "model.language_model.layers.17.post_mlp_layernorm.weight": "pytorch_model-00002-of-00003.bin",
131
+ "model.language_model.layers.17.post_self_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
132
+ "model.language_model.layers.17.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
133
+ "model.language_model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
134
+ "model.language_model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
135
+ "model.language_model.layers.17.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
136
+ "model.language_model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
137
+ "model.language_model.layers.17.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
138
+ "model.language_model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
139
+ "model.language_model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
140
+ "model.language_model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
141
+ "model.language_model.layers.18.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00003.bin",
142
+ "model.language_model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
143
+ "model.language_model.layers.18.post_mlp_layernorm.weight": "pytorch_model-00002-of-00003.bin",
144
+ "model.language_model.layers.18.post_self_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
145
+ "model.language_model.layers.18.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
146
+ "model.language_model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
147
+ "model.language_model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
148
+ "model.language_model.layers.18.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
149
+ "model.language_model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
150
+ "model.language_model.layers.18.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
151
+ "model.language_model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
152
+ "model.language_model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
153
+ "model.language_model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
154
+ "model.language_model.layers.19.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00003.bin",
155
+ "model.language_model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
156
+ "model.language_model.layers.19.post_mlp_layernorm.weight": "pytorch_model-00002-of-00003.bin",
157
+ "model.language_model.layers.19.post_self_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
158
+ "model.language_model.layers.19.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
159
+ "model.language_model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
160
+ "model.language_model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
161
+ "model.language_model.layers.19.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
162
+ "model.language_model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
163
+ "model.language_model.layers.19.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
164
+ "model.language_model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
165
+ "model.language_model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
166
+ "model.language_model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
167
+ "model.language_model.layers.2.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00003.bin",
168
+ "model.language_model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
169
+ "model.language_model.layers.2.post_mlp_layernorm.weight": "pytorch_model-00001-of-00003.bin",
170
+ "model.language_model.layers.2.post_self_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
171
+ "model.language_model.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
172
+ "model.language_model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
173
+ "model.language_model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
174
+ "model.language_model.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
175
+ "model.language_model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
176
+ "model.language_model.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
177
+ "model.language_model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
178
+ "model.language_model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
179
+ "model.language_model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
180
+ "model.language_model.layers.20.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00003.bin",
181
+ "model.language_model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
182
+ "model.language_model.layers.20.post_mlp_layernorm.weight": "pytorch_model-00002-of-00003.bin",
183
+ "model.language_model.layers.20.post_self_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
184
+ "model.language_model.layers.20.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
185
+ "model.language_model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
186
+ "model.language_model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
187
+ "model.language_model.layers.20.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
188
+ "model.language_model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
189
+ "model.language_model.layers.20.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
190
+ "model.language_model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
191
+ "model.language_model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
192
+ "model.language_model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
193
+ "model.language_model.layers.21.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00003.bin",
194
+ "model.language_model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
195
+ "model.language_model.layers.21.post_mlp_layernorm.weight": "pytorch_model-00002-of-00003.bin",
196
+ "model.language_model.layers.21.post_self_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
197
+ "model.language_model.layers.21.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
198
+ "model.language_model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
199
+ "model.language_model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
200
+ "model.language_model.layers.21.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
201
+ "model.language_model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
202
+ "model.language_model.layers.21.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
203
+ "model.language_model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
204
+ "model.language_model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
205
+ "model.language_model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
206
+ "model.language_model.layers.22.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00003.bin",
207
+ "model.language_model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
208
+ "model.language_model.layers.22.post_mlp_layernorm.weight": "pytorch_model-00002-of-00003.bin",
209
+ "model.language_model.layers.22.post_self_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
210
+ "model.language_model.layers.22.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
211
+ "model.language_model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
212
+ "model.language_model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
213
+ "model.language_model.layers.22.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
214
+ "model.language_model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
215
+ "model.language_model.layers.22.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
216
+ "model.language_model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
217
+ "model.language_model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
218
+ "model.language_model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
219
+ "model.language_model.layers.23.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00003.bin",
220
+ "model.language_model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
221
+ "model.language_model.layers.23.post_mlp_layernorm.weight": "pytorch_model-00002-of-00003.bin",
222
+ "model.language_model.layers.23.post_self_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
223
+ "model.language_model.layers.23.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
224
+ "model.language_model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
225
+ "model.language_model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
226
+ "model.language_model.layers.23.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
227
+ "model.language_model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
228
+ "model.language_model.layers.23.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
229
+ "model.language_model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
230
+ "model.language_model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
231
+ "model.language_model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
232
+ "model.language_model.layers.24.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00003.bin",
233
+ "model.language_model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
234
+ "model.language_model.layers.24.post_mlp_layernorm.weight": "pytorch_model-00002-of-00003.bin",
235
+ "model.language_model.layers.24.post_self_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
236
+ "model.language_model.layers.24.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
237
+ "model.language_model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
238
+ "model.language_model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
239
+ "model.language_model.layers.24.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
240
+ "model.language_model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
241
+ "model.language_model.layers.24.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
242
+ "model.language_model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
243
+ "model.language_model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
244
+ "model.language_model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
245
+ "model.language_model.layers.25.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00003.bin",
246
+ "model.language_model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
247
+ "model.language_model.layers.25.post_mlp_layernorm.weight": "pytorch_model-00002-of-00003.bin",
248
+ "model.language_model.layers.25.post_self_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
249
+ "model.language_model.layers.25.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
250
+ "model.language_model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
251
+ "model.language_model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
252
+ "model.language_model.layers.25.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
253
+ "model.language_model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
254
+ "model.language_model.layers.25.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
255
+ "model.language_model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
256
+ "model.language_model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
257
+ "model.language_model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
258
+ "model.language_model.layers.26.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00003.bin",
259
+ "model.language_model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
260
+ "model.language_model.layers.26.post_mlp_layernorm.weight": "pytorch_model-00002-of-00003.bin",
261
+ "model.language_model.layers.26.post_self_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
262
+ "model.language_model.layers.26.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
263
+ "model.language_model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
264
+ "model.language_model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
265
+ "model.language_model.layers.26.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
266
+ "model.language_model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
267
+ "model.language_model.layers.26.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
268
+ "model.language_model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
269
+ "model.language_model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
270
+ "model.language_model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
271
+ "model.language_model.layers.27.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00003.bin",
272
+ "model.language_model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
273
+ "model.language_model.layers.27.post_mlp_layernorm.weight": "pytorch_model-00002-of-00003.bin",
274
+ "model.language_model.layers.27.post_self_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
275
+ "model.language_model.layers.27.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
276
+ "model.language_model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
277
+ "model.language_model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
278
+ "model.language_model.layers.27.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
279
+ "model.language_model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
280
+ "model.language_model.layers.27.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
281
+ "model.language_model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
282
+ "model.language_model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
283
+ "model.language_model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
284
+ "model.language_model.layers.28.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00003.bin",
285
+ "model.language_model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
286
+ "model.language_model.layers.28.post_mlp_layernorm.weight": "pytorch_model-00002-of-00003.bin",
287
+ "model.language_model.layers.28.post_self_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
288
+ "model.language_model.layers.28.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
289
+ "model.language_model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
290
+ "model.language_model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
291
+ "model.language_model.layers.28.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
292
+ "model.language_model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
293
+ "model.language_model.layers.28.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
294
+ "model.language_model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
295
+ "model.language_model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
296
+ "model.language_model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
297
+ "model.language_model.layers.29.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00003.bin",
298
+ "model.language_model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
299
+ "model.language_model.layers.29.post_mlp_layernorm.weight": "pytorch_model-00002-of-00003.bin",
300
+ "model.language_model.layers.29.post_self_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
301
+ "model.language_model.layers.29.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
302
+ "model.language_model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
303
+ "model.language_model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
304
+ "model.language_model.layers.29.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
305
+ "model.language_model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
306
+ "model.language_model.layers.29.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
307
+ "model.language_model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
308
+ "model.language_model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
309
+ "model.language_model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
310
+ "model.language_model.layers.3.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00003.bin",
311
+ "model.language_model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
312
+ "model.language_model.layers.3.post_mlp_layernorm.weight": "pytorch_model-00001-of-00003.bin",
313
+ "model.language_model.layers.3.post_self_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
314
+ "model.language_model.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
315
+ "model.language_model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
316
+ "model.language_model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
317
+ "model.language_model.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
318
+ "model.language_model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
319
+ "model.language_model.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
320
+ "model.language_model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
321
+ "model.language_model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
322
+ "model.language_model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
323
+ "model.language_model.layers.30.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00003.bin",
324
+ "model.language_model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
325
+ "model.language_model.layers.30.post_mlp_layernorm.weight": "pytorch_model-00002-of-00003.bin",
326
+ "model.language_model.layers.30.post_self_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
327
+ "model.language_model.layers.30.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
328
+ "model.language_model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
329
+ "model.language_model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
330
+ "model.language_model.layers.30.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
331
+ "model.language_model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
332
+ "model.language_model.layers.30.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
333
+ "model.language_model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
334
+ "model.language_model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
335
+ "model.language_model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
336
+ "model.language_model.layers.31.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00003.bin",
337
+ "model.language_model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
338
+ "model.language_model.layers.31.post_mlp_layernorm.weight": "pytorch_model-00002-of-00003.bin",
339
+ "model.language_model.layers.31.post_self_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
340
+ "model.language_model.layers.31.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
341
+ "model.language_model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
342
+ "model.language_model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
343
+ "model.language_model.layers.31.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
344
+ "model.language_model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
345
+ "model.language_model.layers.31.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
346
+ "model.language_model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
347
+ "model.language_model.layers.32.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
348
+ "model.language_model.layers.32.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
349
+ "model.language_model.layers.32.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00003.bin",
350
+ "model.language_model.layers.32.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
351
+ "model.language_model.layers.32.post_mlp_layernorm.weight": "pytorch_model-00002-of-00003.bin",
352
+ "model.language_model.layers.32.post_self_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
353
+ "model.language_model.layers.32.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
354
+ "model.language_model.layers.32.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
355
+ "model.language_model.layers.32.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
356
+ "model.language_model.layers.32.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
357
+ "model.language_model.layers.32.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
358
+ "model.language_model.layers.32.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
359
+ "model.language_model.layers.32.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
360
+ "model.language_model.layers.33.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
361
+ "model.language_model.layers.33.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
362
+ "model.language_model.layers.33.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00003.bin",
363
+ "model.language_model.layers.33.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
364
+ "model.language_model.layers.33.post_mlp_layernorm.weight": "pytorch_model-00002-of-00003.bin",
365
+ "model.language_model.layers.33.post_self_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
366
+ "model.language_model.layers.33.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
367
+ "model.language_model.layers.33.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
368
+ "model.language_model.layers.33.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
369
+ "model.language_model.layers.33.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
370
+ "model.language_model.layers.33.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
371
+ "model.language_model.layers.33.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
372
+ "model.language_model.layers.33.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
373
+ "model.language_model.layers.34.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
374
+ "model.language_model.layers.34.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
375
+ "model.language_model.layers.34.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00003.bin",
376
+ "model.language_model.layers.34.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
377
+ "model.language_model.layers.34.post_mlp_layernorm.weight": "pytorch_model-00002-of-00003.bin",
378
+ "model.language_model.layers.34.post_self_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
379
+ "model.language_model.layers.34.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
380
+ "model.language_model.layers.34.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
381
+ "model.language_model.layers.34.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
382
+ "model.language_model.layers.34.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
383
+ "model.language_model.layers.34.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
384
+ "model.language_model.layers.34.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
385
+ "model.language_model.layers.34.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
386
+ "model.language_model.layers.35.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
387
+ "model.language_model.layers.35.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
388
+ "model.language_model.layers.35.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00003.bin",
389
+ "model.language_model.layers.35.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
390
+ "model.language_model.layers.35.post_mlp_layernorm.weight": "pytorch_model-00002-of-00003.bin",
391
+ "model.language_model.layers.35.post_self_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
392
+ "model.language_model.layers.35.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
393
+ "model.language_model.layers.35.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
394
+ "model.language_model.layers.35.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
395
+ "model.language_model.layers.35.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
396
+ "model.language_model.layers.35.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
397
+ "model.language_model.layers.35.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
398
+ "model.language_model.layers.35.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
399
+ "model.language_model.layers.36.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
400
+ "model.language_model.layers.36.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
401
+ "model.language_model.layers.36.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00003.bin",
402
+ "model.language_model.layers.36.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
403
+ "model.language_model.layers.36.post_mlp_layernorm.weight": "pytorch_model-00002-of-00003.bin",
404
+ "model.language_model.layers.36.post_self_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
405
+ "model.language_model.layers.36.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
406
+ "model.language_model.layers.36.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
407
+ "model.language_model.layers.36.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
408
+ "model.language_model.layers.36.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
409
+ "model.language_model.layers.36.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
410
+ "model.language_model.layers.36.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
411
+ "model.language_model.layers.36.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
412
+ "model.language_model.layers.37.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
413
+ "model.language_model.layers.37.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
414
+ "model.language_model.layers.37.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00003.bin",
415
+ "model.language_model.layers.37.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
416
+ "model.language_model.layers.37.post_mlp_layernorm.weight": "pytorch_model-00002-of-00003.bin",
417
+ "model.language_model.layers.37.post_self_attn_layernorm.weight": "pytorch_model-00002-of-00003.bin",
418
+ "model.language_model.layers.37.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
419
+ "model.language_model.layers.37.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
420
+ "model.language_model.layers.37.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
421
+ "model.language_model.layers.37.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
422
+ "model.language_model.layers.37.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
423
+ "model.language_model.layers.37.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
424
+ "model.language_model.layers.37.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
425
+ "model.language_model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
426
+ "model.language_model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
427
+ "model.language_model.layers.38.mlp.gate_up_proj.weight": "pytorch_model-00003-of-00003.bin",
428
+ "model.language_model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
429
+ "model.language_model.layers.38.post_mlp_layernorm.weight": "pytorch_model-00003-of-00003.bin",
430
+ "model.language_model.layers.38.post_self_attn_layernorm.weight": "pytorch_model-00003-of-00003.bin",
431
+ "model.language_model.layers.38.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
432
+ "model.language_model.layers.38.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
433
+ "model.language_model.layers.38.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
434
+ "model.language_model.layers.38.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
435
+ "model.language_model.layers.38.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
436
+ "model.language_model.layers.38.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
437
+ "model.language_model.layers.38.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
438
+ "model.language_model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
439
+ "model.language_model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
440
+ "model.language_model.layers.39.mlp.gate_up_proj.weight": "pytorch_model-00003-of-00003.bin",
441
+ "model.language_model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
442
+ "model.language_model.layers.39.post_mlp_layernorm.weight": "pytorch_model-00003-of-00003.bin",
443
+ "model.language_model.layers.39.post_self_attn_layernorm.weight": "pytorch_model-00003-of-00003.bin",
444
+ "model.language_model.layers.39.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
445
+ "model.language_model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
446
+ "model.language_model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
447
+ "model.language_model.layers.39.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
448
+ "model.language_model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
449
+ "model.language_model.layers.39.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
450
+ "model.language_model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
451
+ "model.language_model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
452
+ "model.language_model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
453
+ "model.language_model.layers.4.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00003.bin",
454
+ "model.language_model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
455
+ "model.language_model.layers.4.post_mlp_layernorm.weight": "pytorch_model-00001-of-00003.bin",
456
+ "model.language_model.layers.4.post_self_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
457
+ "model.language_model.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
458
+ "model.language_model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
459
+ "model.language_model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
460
+ "model.language_model.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
461
+ "model.language_model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
462
+ "model.language_model.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
463
+ "model.language_model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
464
+ "model.language_model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
465
+ "model.language_model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
466
+ "model.language_model.layers.5.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00003.bin",
467
+ "model.language_model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
468
+ "model.language_model.layers.5.post_mlp_layernorm.weight": "pytorch_model-00001-of-00003.bin",
469
+ "model.language_model.layers.5.post_self_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
470
+ "model.language_model.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
471
+ "model.language_model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
472
+ "model.language_model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
473
+ "model.language_model.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
474
+ "model.language_model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
475
+ "model.language_model.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
476
+ "model.language_model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
477
+ "model.language_model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
478
+ "model.language_model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
479
+ "model.language_model.layers.6.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00003.bin",
480
+ "model.language_model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
481
+ "model.language_model.layers.6.post_mlp_layernorm.weight": "pytorch_model-00001-of-00003.bin",
482
+ "model.language_model.layers.6.post_self_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
483
+ "model.language_model.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
484
+ "model.language_model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
485
+ "model.language_model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
486
+ "model.language_model.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
487
+ "model.language_model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
488
+ "model.language_model.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
489
+ "model.language_model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
490
+ "model.language_model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
491
+ "model.language_model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
492
+ "model.language_model.layers.7.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00003.bin",
493
+ "model.language_model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
494
+ "model.language_model.layers.7.post_mlp_layernorm.weight": "pytorch_model-00001-of-00003.bin",
495
+ "model.language_model.layers.7.post_self_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
496
+ "model.language_model.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
497
+ "model.language_model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
498
+ "model.language_model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
499
+ "model.language_model.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
500
+ "model.language_model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
501
+ "model.language_model.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
502
+ "model.language_model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
503
+ "model.language_model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
504
+ "model.language_model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
505
+ "model.language_model.layers.8.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00003.bin",
506
+ "model.language_model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
507
+ "model.language_model.layers.8.post_mlp_layernorm.weight": "pytorch_model-00001-of-00003.bin",
508
+ "model.language_model.layers.8.post_self_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
509
+ "model.language_model.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
510
+ "model.language_model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
511
+ "model.language_model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
512
+ "model.language_model.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
513
+ "model.language_model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
514
+ "model.language_model.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
515
+ "model.language_model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
516
+ "model.language_model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
517
+ "model.language_model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
518
+ "model.language_model.layers.9.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00003.bin",
519
+ "model.language_model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
520
+ "model.language_model.layers.9.post_mlp_layernorm.weight": "pytorch_model-00001-of-00003.bin",
521
+ "model.language_model.layers.9.post_self_attn_layernorm.weight": "pytorch_model-00001-of-00003.bin",
522
+ "model.language_model.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
523
+ "model.language_model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
524
+ "model.language_model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
525
+ "model.language_model.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
526
+ "model.language_model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
527
+ "model.language_model.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
528
+ "model.language_model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
529
+ "model.language_model.norm.weight": "pytorch_model-00003-of-00003.bin",
530
+ "model.visual.blocks.0.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
531
+ "model.visual.blocks.0.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
532
+ "model.visual.blocks.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
533
+ "model.visual.blocks.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
534
+ "model.visual.blocks.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
535
+ "model.visual.blocks.0.norm1.weight": "pytorch_model-00001-of-00003.bin",
536
+ "model.visual.blocks.0.norm2.weight": "pytorch_model-00001-of-00003.bin",
537
+ "model.visual.blocks.1.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
538
+ "model.visual.blocks.1.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
539
+ "model.visual.blocks.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
540
+ "model.visual.blocks.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
541
+ "model.visual.blocks.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
542
+ "model.visual.blocks.1.norm1.weight": "pytorch_model-00001-of-00003.bin",
543
+ "model.visual.blocks.1.norm2.weight": "pytorch_model-00001-of-00003.bin",
544
+ "model.visual.blocks.10.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
545
+ "model.visual.blocks.10.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
546
+ "model.visual.blocks.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
547
+ "model.visual.blocks.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
548
+ "model.visual.blocks.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
549
+ "model.visual.blocks.10.norm1.weight": "pytorch_model-00001-of-00003.bin",
550
+ "model.visual.blocks.10.norm2.weight": "pytorch_model-00001-of-00003.bin",
551
+ "model.visual.blocks.11.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
552
+ "model.visual.blocks.11.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
553
+ "model.visual.blocks.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
554
+ "model.visual.blocks.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
555
+ "model.visual.blocks.11.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
556
+ "model.visual.blocks.11.norm1.weight": "pytorch_model-00001-of-00003.bin",
557
+ "model.visual.blocks.11.norm2.weight": "pytorch_model-00001-of-00003.bin",
558
+ "model.visual.blocks.12.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
559
+ "model.visual.blocks.12.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
560
+ "model.visual.blocks.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
561
+ "model.visual.blocks.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
562
+ "model.visual.blocks.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
563
+ "model.visual.blocks.12.norm1.weight": "pytorch_model-00001-of-00003.bin",
564
+ "model.visual.blocks.12.norm2.weight": "pytorch_model-00001-of-00003.bin",
565
+ "model.visual.blocks.13.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
566
+ "model.visual.blocks.13.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
567
+ "model.visual.blocks.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
568
+ "model.visual.blocks.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
569
+ "model.visual.blocks.13.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
570
+ "model.visual.blocks.13.norm1.weight": "pytorch_model-00001-of-00003.bin",
571
+ "model.visual.blocks.13.norm2.weight": "pytorch_model-00001-of-00003.bin",
572
+ "model.visual.blocks.14.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
573
+ "model.visual.blocks.14.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
574
+ "model.visual.blocks.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
575
+ "model.visual.blocks.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
576
+ "model.visual.blocks.14.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
577
+ "model.visual.blocks.14.norm1.weight": "pytorch_model-00001-of-00003.bin",
578
+ "model.visual.blocks.14.norm2.weight": "pytorch_model-00001-of-00003.bin",
579
+ "model.visual.blocks.15.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
580
+ "model.visual.blocks.15.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
581
+ "model.visual.blocks.15.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
582
+ "model.visual.blocks.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
583
+ "model.visual.blocks.15.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
584
+ "model.visual.blocks.15.norm1.weight": "pytorch_model-00001-of-00003.bin",
585
+ "model.visual.blocks.15.norm2.weight": "pytorch_model-00001-of-00003.bin",
586
+ "model.visual.blocks.16.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
587
+ "model.visual.blocks.16.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
588
+ "model.visual.blocks.16.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
589
+ "model.visual.blocks.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
590
+ "model.visual.blocks.16.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
591
+ "model.visual.blocks.16.norm1.weight": "pytorch_model-00001-of-00003.bin",
592
+ "model.visual.blocks.16.norm2.weight": "pytorch_model-00001-of-00003.bin",
593
+ "model.visual.blocks.17.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
594
+ "model.visual.blocks.17.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
595
+ "model.visual.blocks.17.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
596
+ "model.visual.blocks.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
597
+ "model.visual.blocks.17.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
598
+ "model.visual.blocks.17.norm1.weight": "pytorch_model-00001-of-00003.bin",
599
+ "model.visual.blocks.17.norm2.weight": "pytorch_model-00001-of-00003.bin",
600
+ "model.visual.blocks.18.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
601
+ "model.visual.blocks.18.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
602
+ "model.visual.blocks.18.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
603
+ "model.visual.blocks.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
604
+ "model.visual.blocks.18.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
605
+ "model.visual.blocks.18.norm1.weight": "pytorch_model-00001-of-00003.bin",
606
+ "model.visual.blocks.18.norm2.weight": "pytorch_model-00001-of-00003.bin",
607
+ "model.visual.blocks.19.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
608
+ "model.visual.blocks.19.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
609
+ "model.visual.blocks.19.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
610
+ "model.visual.blocks.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
611
+ "model.visual.blocks.19.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
612
+ "model.visual.blocks.19.norm1.weight": "pytorch_model-00001-of-00003.bin",
613
+ "model.visual.blocks.19.norm2.weight": "pytorch_model-00001-of-00003.bin",
614
+ "model.visual.blocks.2.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
615
+ "model.visual.blocks.2.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
616
+ "model.visual.blocks.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
617
+ "model.visual.blocks.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
618
+ "model.visual.blocks.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
619
+ "model.visual.blocks.2.norm1.weight": "pytorch_model-00001-of-00003.bin",
620
+ "model.visual.blocks.2.norm2.weight": "pytorch_model-00001-of-00003.bin",
621
+ "model.visual.blocks.20.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
622
+ "model.visual.blocks.20.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
623
+ "model.visual.blocks.20.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
624
+ "model.visual.blocks.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
625
+ "model.visual.blocks.20.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
626
+ "model.visual.blocks.20.norm1.weight": "pytorch_model-00001-of-00003.bin",
627
+ "model.visual.blocks.20.norm2.weight": "pytorch_model-00001-of-00003.bin",
628
+ "model.visual.blocks.21.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
629
+ "model.visual.blocks.21.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
630
+ "model.visual.blocks.21.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
631
+ "model.visual.blocks.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
632
+ "model.visual.blocks.21.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
633
+ "model.visual.blocks.21.norm1.weight": "pytorch_model-00001-of-00003.bin",
634
+ "model.visual.blocks.21.norm2.weight": "pytorch_model-00001-of-00003.bin",
635
+ "model.visual.blocks.22.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
636
+ "model.visual.blocks.22.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
637
+ "model.visual.blocks.22.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
638
+ "model.visual.blocks.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
639
+ "model.visual.blocks.22.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
640
+ "model.visual.blocks.22.norm1.weight": "pytorch_model-00001-of-00003.bin",
641
+ "model.visual.blocks.22.norm2.weight": "pytorch_model-00001-of-00003.bin",
642
+ "model.visual.blocks.23.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
643
+ "model.visual.blocks.23.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
644
+ "model.visual.blocks.23.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
645
+ "model.visual.blocks.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
646
+ "model.visual.blocks.23.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
647
+ "model.visual.blocks.23.norm1.weight": "pytorch_model-00001-of-00003.bin",
648
+ "model.visual.blocks.23.norm2.weight": "pytorch_model-00001-of-00003.bin",
649
+ "model.visual.blocks.3.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
650
+ "model.visual.blocks.3.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
651
+ "model.visual.blocks.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
652
+ "model.visual.blocks.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
653
+ "model.visual.blocks.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
654
+ "model.visual.blocks.3.norm1.weight": "pytorch_model-00001-of-00003.bin",
655
+ "model.visual.blocks.3.norm2.weight": "pytorch_model-00001-of-00003.bin",
656
+ "model.visual.blocks.4.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
657
+ "model.visual.blocks.4.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
658
+ "model.visual.blocks.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
659
+ "model.visual.blocks.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
660
+ "model.visual.blocks.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
661
+ "model.visual.blocks.4.norm1.weight": "pytorch_model-00001-of-00003.bin",
662
+ "model.visual.blocks.4.norm2.weight": "pytorch_model-00001-of-00003.bin",
663
+ "model.visual.blocks.5.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
664
+ "model.visual.blocks.5.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
665
+ "model.visual.blocks.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
666
+ "model.visual.blocks.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
667
+ "model.visual.blocks.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
668
+ "model.visual.blocks.5.norm1.weight": "pytorch_model-00001-of-00003.bin",
669
+ "model.visual.blocks.5.norm2.weight": "pytorch_model-00001-of-00003.bin",
670
+ "model.visual.blocks.6.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
671
+ "model.visual.blocks.6.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
672
+ "model.visual.blocks.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
673
+ "model.visual.blocks.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
674
+ "model.visual.blocks.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
675
+ "model.visual.blocks.6.norm1.weight": "pytorch_model-00001-of-00003.bin",
676
+ "model.visual.blocks.6.norm2.weight": "pytorch_model-00001-of-00003.bin",
677
+ "model.visual.blocks.7.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
678
+ "model.visual.blocks.7.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
679
+ "model.visual.blocks.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
680
+ "model.visual.blocks.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
681
+ "model.visual.blocks.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
682
+ "model.visual.blocks.7.norm1.weight": "pytorch_model-00001-of-00003.bin",
683
+ "model.visual.blocks.7.norm2.weight": "pytorch_model-00001-of-00003.bin",
684
+ "model.visual.blocks.8.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
685
+ "model.visual.blocks.8.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
686
+ "model.visual.blocks.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
687
+ "model.visual.blocks.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
688
+ "model.visual.blocks.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
689
+ "model.visual.blocks.8.norm1.weight": "pytorch_model-00001-of-00003.bin",
690
+ "model.visual.blocks.8.norm2.weight": "pytorch_model-00001-of-00003.bin",
691
+ "model.visual.blocks.9.attn.proj.weight": "pytorch_model-00001-of-00003.bin",
692
+ "model.visual.blocks.9.attn.qkv.weight": "pytorch_model-00001-of-00003.bin",
693
+ "model.visual.blocks.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
694
+ "model.visual.blocks.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
695
+ "model.visual.blocks.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
696
+ "model.visual.blocks.9.norm1.weight": "pytorch_model-00001-of-00003.bin",
697
+ "model.visual.blocks.9.norm2.weight": "pytorch_model-00001-of-00003.bin",
698
+ "model.visual.downsample.bias": "pytorch_model-00001-of-00003.bin",
699
+ "model.visual.downsample.weight": "pytorch_model-00001-of-00003.bin",
700
+ "model.visual.embeddings.position_embedding.weight": "pytorch_model-00001-of-00003.bin",
701
+ "model.visual.merger.down_proj.weight": "pytorch_model-00001-of-00003.bin",
702
+ "model.visual.merger.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
703
+ "model.visual.merger.post_projection_norm.bias": "pytorch_model-00001-of-00003.bin",
704
+ "model.visual.merger.post_projection_norm.weight": "pytorch_model-00001-of-00003.bin",
705
+ "model.visual.merger.proj.weight": "pytorch_model-00001-of-00003.bin",
706
+ "model.visual.merger.up_proj.weight": "pytorch_model-00001-of-00003.bin",
707
+ "model.visual.patch_embed.proj.bias": "pytorch_model-00001-of-00003.bin",
708
+ "model.visual.patch_embed.proj.weight": "pytorch_model-00001-of-00003.bin",
709
+ "model.visual.post_conv_layernorm.weight": "pytorch_model-00001-of-00003.bin",
710
+ "model.visual.post_layernorm.weight": "pytorch_model-00001-of-00003.bin"
711
+ }
712
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "[MASK]",
5
+ "[gMASK]",
6
+ "[sMASK]",
7
+ "<sop>",
8
+ "<eop>",
9
+ "<|system|>",
10
+ "<|user|>",
11
+ "<|assistant|>",
12
+ "<|observation|>",
13
+ "<|begin_of_image|>",
14
+ "<|end_of_image|>",
15
+ "<|begin_of_video|>",
16
+ "<|end_of_video|>",
17
+ "<|image|>",
18
+ "<|video|>"
19
+ ],
20
+ "eos_token": {
21
+ "content": "<|endoftext|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "pad_token": {
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcc742fc44db1f0870d7320b495e6240cc40e202565fc96786220fa0d9ddb41c
3
+ size 19968183
tokenizer_config.json ADDED
@@ -0,0 +1,220 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "151329": {
4
+ "content": "<|endoftext|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "151330": {
12
+ "content": "[MASK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "151331": {
20
+ "content": "[gMASK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "151332": {
28
+ "content": "[sMASK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "151333": {
36
+ "content": "<sop>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "151334": {
44
+ "content": "<eop>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "151335": {
52
+ "content": "<|system|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "151336": {
60
+ "content": "<|user|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "151337": {
68
+ "content": "<|assistant|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "151338": {
76
+ "content": "<|observation|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "151339": {
84
+ "content": "<|begin_of_image|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "151340": {
92
+ "content": "<|end_of_image|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "151341": {
100
+ "content": "<|begin_of_video|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "151342": {
108
+ "content": "<|end_of_video|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "151343": {
116
+ "content": "<|image|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "151344": {
124
+ "content": "<|video|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "151345": {
132
+ "content": "<think>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "151346": {
140
+ "content": "</think>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "151347": {
148
+ "content": "<answer>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "151348": {
156
+ "content": "</answer>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "151349": {
164
+ "content": "<|begin_of_box|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "151350": {
172
+ "content": "<|end_of_box|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "151351": {
180
+ "content": "<|sep|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ }
187
+ },
188
+ "additional_special_tokens": [
189
+ "<|endoftext|>",
190
+ "[MASK]",
191
+ "[gMASK]",
192
+ "[sMASK]",
193
+ "<sop>",
194
+ "<eop>",
195
+ "<|system|>",
196
+ "<|user|>",
197
+ "<|assistant|>",
198
+ "<|observation|>",
199
+ "<|begin_of_image|>",
200
+ "<|end_of_image|>",
201
+ "<|begin_of_video|>",
202
+ "<|end_of_video|>",
203
+ "<|image|>",
204
+ "<|video|>"
205
+ ],
206
+ "clean_up_tokenization_spaces": false,
207
+ "do_lower_case": false,
208
+ "eos_token": "<|endoftext|>",
209
+ "extra_special_tokens": {},
210
+ "model_input_names": [
211
+ "input_ids",
212
+ "attention_mask"
213
+ ],
214
+ "model_max_length": 65536,
215
+ "pad_token": "<|endoftext|>",
216
+ "padding_side": "left",
217
+ "processor_class": "Glm4vProcessor",
218
+ "remove_space": false,
219
+ "tokenizer_class": "PreTrainedTokenizerFast"
220
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "do_center_crop": null,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_pad": null,
10
+ "do_rescale": true,
11
+ "do_resize": true,
12
+ "do_sample_frames": true,
13
+ "fps": 2,
14
+ "image_mean": [
15
+ 0.48145466,
16
+ 0.4578275,
17
+ 0.40821073
18
+ ],
19
+ "image_std": [
20
+ 0.26862954,
21
+ 0.26130258,
22
+ 0.27577711
23
+ ],
24
+ "input_data_format": null,
25
+ "max_image_size": {
26
+ "longest_edge": 47040000
27
+ },
28
+ "merge_size": 2,
29
+ "num_frames": 16,
30
+ "patch_size": 14,
31
+ "processor_class": "Glm4vProcessor",
32
+ "resample": 3,
33
+ "rescale_factor": 0.00392156862745098,
34
+ "size": {
35
+ "longest_edge": 47040000,
36
+ "shortest_edge": 12544
37
+ },
38
+ "size_divisor": null,
39
+ "temporal_patch_size": 2,
40
+ "video_metadata": null,
41
+ "video_processor_type": "Glm4vVideoProcessor"
42
+ }