agokrani commited on
Commit
54b11bc
·
verified ·
1 Parent(s): 6b67275

Upload folder using huggingface_hub

Browse files
.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
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
config.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/Phi-4-mini-instruct",
3
+ "architectures": [
4
+ "Phi3ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "microsoft/Phi-4-mini-instruct--configuration_phi3.Phi3Config",
10
+ "AutoModelForCausalLM": "microsoft/Phi-4-mini-instruct--modeling_phi3.Phi3ForCausalLM",
11
+ "AutoTokenizer": "microsoft/Phi-4-mini-instruct--Xenova/gpt-4o"
12
+ },
13
+ "bos_token_id": 199999,
14
+ "embd_pdrop": 0.0,
15
+ "eos_token_id": 151645,
16
+ "full_attn_mod": 1,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 3072,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 8192,
21
+ "interpolate_factor": 1,
22
+ "lm_head_bias": false,
23
+ "max_position_embeddings": 131072,
24
+ "mlp_bias": false,
25
+ "model_type": "phi3",
26
+ "num_attention_heads": 24,
27
+ "num_hidden_layers": 32,
28
+ "num_key_value_heads": 8,
29
+ "original_max_position_embeddings": 4096,
30
+ "pad_token_id": 151643,
31
+ "partial_rotary_factor": 0.75,
32
+ "resid_pdrop": 0.0,
33
+ "rms_norm_eps": 1e-05,
34
+ "rope_scaling": {
35
+ "long_factor": [
36
+ 1,
37
+ 1.118320672,
38
+ 1.250641126,
39
+ 1.398617824,
40
+ 1.564103225,
41
+ 1.74916897,
42
+ 1.956131817,
43
+ 2.187582649,
44
+ 2.446418898,
45
+ 2.735880826,
46
+ 3.059592084,
47
+ 3.421605075,
48
+ 3.826451687,
49
+ 4.279200023,
50
+ 4.785517845,
51
+ 5.351743533,
52
+ 5.984965424,
53
+ 6.693110555,
54
+ 7.485043894,
55
+ 8.370679318,
56
+ 9.36110372,
57
+ 10.4687158,
58
+ 11.70738129,
59
+ 13.09260651,
60
+ 14.64173252,
61
+ 16.37415215,
62
+ 18.31155283,
63
+ 20.47818807,
64
+ 22.90118105,
65
+ 25.61086418,
66
+ 28.64115884,
67
+ 32.03,
68
+ 32.1,
69
+ 32.13,
70
+ 32.23,
71
+ 32.6,
72
+ 32.61,
73
+ 32.64,
74
+ 32.66,
75
+ 32.7,
76
+ 32.71,
77
+ 32.93,
78
+ 32.97,
79
+ 33.28,
80
+ 33.49,
81
+ 33.5,
82
+ 44.16,
83
+ 47.77
84
+ ],
85
+ "short_factor": [
86
+ 1.0,
87
+ 1.0,
88
+ 1.0,
89
+ 1.0,
90
+ 1.0,
91
+ 1.0,
92
+ 1.0,
93
+ 1.0,
94
+ 1.0,
95
+ 1.0,
96
+ 1.0,
97
+ 1.0,
98
+ 1.0,
99
+ 1.0,
100
+ 1.0,
101
+ 1.0,
102
+ 1.0,
103
+ 1.0,
104
+ 1.0,
105
+ 1.0,
106
+ 1.0,
107
+ 1.0,
108
+ 1.0,
109
+ 1.0,
110
+ 1.0,
111
+ 1.0,
112
+ 1.0,
113
+ 1.0,
114
+ 1.0,
115
+ 1.0,
116
+ 1.0,
117
+ 1.0,
118
+ 1.0,
119
+ 1.0,
120
+ 1.0,
121
+ 1.0,
122
+ 1.0,
123
+ 1.0,
124
+ 1.0,
125
+ 1.0,
126
+ 1.0,
127
+ 1.0,
128
+ 1.0,
129
+ 1.0,
130
+ 1.0,
131
+ 1.0,
132
+ 1.0,
133
+ 1.0
134
+ ],
135
+ "type": "longrope"
136
+ },
137
+ "rope_theta": 10000.0,
138
+ "sliding_window": 262144,
139
+ "tie_word_embeddings": true,
140
+ "torch_dtype": "float32",
141
+ "transformers_version": "4.49.0",
142
+ "use_cache": true,
143
+ "vocab_size": 151669
144
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 199999,
4
+ "eos_token_id": [
5
+ 200020,
6
+ 199999
7
+ ],
8
+ "pad_token_id": 199999,
9
+ "transformers_version": "4.49.0"
10
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8099877261c7c5e8cb6a81837f3413ee1f7455004c22900fd6c7dc1b4741fbbe
3
+ size 4984448224
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1d668a3e411d0d0598f356808c4ab7d3ae29853413c6f29ec1a0354d6421266
3
+ size 4970578560
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3941bf3f2057ab8fc678cf17ed1dd23efc13cc8f20c9180e0d2ccbcdc38ff02
3
+ size 4794405032
model.safetensors.index.json ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14749409280
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
20
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
21
+ "model.layers.10.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
22
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
23
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
24
+ "model.layers.10.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
25
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
26
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
27
+ "model.layers.11.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
28
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
29
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
30
+ "model.layers.11.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
31
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
32
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
33
+ "model.layers.12.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
34
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
35
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.12.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
38
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.13.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
41
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
42
+ "model.layers.13.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
43
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
44
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.14.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.14.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.15.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.15.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.16.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.16.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.17.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.17.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.18.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.18.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.19.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.19.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
80
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
81
+ "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
82
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
83
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
84
+ "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
85
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
86
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
87
+ "model.layers.20.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
88
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
89
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.20.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
91
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
92
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
93
+ "model.layers.21.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
94
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
95
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
96
+ "model.layers.21.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
97
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
98
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
99
+ "model.layers.22.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
100
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
101
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
102
+ "model.layers.22.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
103
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
104
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
105
+ "model.layers.23.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
106
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
107
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
108
+ "model.layers.23.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
109
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
110
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
111
+ "model.layers.24.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
112
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
113
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
114
+ "model.layers.24.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
115
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
116
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
117
+ "model.layers.25.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
118
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
119
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
120
+ "model.layers.25.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
121
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
122
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
123
+ "model.layers.26.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
124
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
125
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
126
+ "model.layers.26.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
127
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
128
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
129
+ "model.layers.27.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
130
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
131
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
132
+ "model.layers.27.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
133
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
134
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
135
+ "model.layers.28.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
136
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
137
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
138
+ "model.layers.28.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
139
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
140
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
141
+ "model.layers.29.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
142
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
143
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
144
+ "model.layers.29.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
145
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
146
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
147
+ "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
148
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
149
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
150
+ "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
151
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
152
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.30.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
155
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
156
+ "model.layers.30.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
158
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
159
+ "model.layers.31.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
160
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
161
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.31.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
164
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
165
+ "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
166
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
167
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
168
+ "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
169
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
170
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
171
+ "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
172
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
173
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
174
+ "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
175
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
176
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
177
+ "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
178
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
179
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
180
+ "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
181
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
182
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
183
+ "model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
184
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
185
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
186
+ "model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
187
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
188
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
189
+ "model.layers.8.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
190
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
191
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
192
+ "model.layers.8.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
193
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
194
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
195
+ "model.layers.9.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
196
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
197
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
198
+ "model.layers.9.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
199
+ "model.norm.weight": "model-00003-of-00003.safetensors"
200
+ }
201
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- '' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" and not message.tool_calls %}\n {%- set content = message.content %}\n {%- if not loop.last %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- if not loop.last %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n<think>\\n' }}\n{%- endif %}\n",
231
+ "clean_up_tokenization_spaces": false,
232
+ "eos_token": "<|im_end|>",
233
+ "errors": "replace",
234
+ "extra_special_tokens": {},
235
+ "model_max_length": 131072,
236
+ "pad_token": "<|endoftext|>",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff