win10 commited on
Commit
53a8d5b
1 Parent(s): 82778b5

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - win10/phi-3.5-Sakura-Yuzu-v1.5
4
+ library_name: transformers
5
+ tags:
6
+ - mergekit
7
+ - merge
8
+
9
+ ---
10
+ # merge
11
+
12
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
13
+
14
+ ## Merge Details
15
+ ### Merge Method
16
+
17
+ This model was merged using the passthrough merge method.
18
+
19
+ ### Models Merged
20
+
21
+ The following models were included in the merge:
22
+ * [win10/phi-3.5-Sakura-Yuzu-v1.5](https://huggingface.co/win10/phi-3.5-Sakura-Yuzu-v1.5)
23
+
24
+ ### Configuration
25
+
26
+ The following YAML configuration was used to produce this model:
27
+
28
+ ```yaml
29
+ dtype: float16
30
+ merge_method: passthrough
31
+ slices:
32
+ - sources:
33
+ - layer_range: [0, 2]
34
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
35
+ - sources:
36
+ - layer_range: [1, 3]
37
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
38
+ - sources:
39
+ - layer_range: [2, 4]
40
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
41
+ - sources:
42
+ - layer_range: [3, 5]
43
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
44
+ - sources:
45
+ - layer_range: [4, 6]
46
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
47
+ - sources:
48
+ - layer_range: [5, 7]
49
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
50
+ - sources:
51
+ - layer_range: [6, 8]
52
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
53
+ - sources:
54
+ - layer_range: [7, 9]
55
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
56
+ - sources:
57
+ - layer_range: [8, 10]
58
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
59
+ - sources:
60
+ - layer_range: [9, 11]
61
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
62
+ - sources:
63
+ - layer_range: [10, 12]
64
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
65
+ - sources:
66
+ - layer_range: [11, 13]
67
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
68
+ - sources:
69
+ - layer_range: [12, 14]
70
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
71
+ - sources:
72
+ - layer_range: [13, 15]
73
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
74
+ - sources:
75
+ - layer_range: [14, 16]
76
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
77
+ - sources:
78
+ - layer_range: [15, 17]
79
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
80
+ - sources:
81
+ - layer_range: [16, 18]
82
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
83
+ - sources:
84
+ - layer_range: [17, 19]
85
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
86
+ - sources:
87
+ - layer_range: [18, 20]
88
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
89
+ - sources:
90
+ - layer_range: [19, 21]
91
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
92
+ - sources:
93
+ - layer_range: [20, 22]
94
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
95
+ - sources:
96
+ - layer_range: [21, 23]
97
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
98
+ - sources:
99
+ - layer_range: [22, 24]
100
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
101
+ - sources:
102
+ - layer_range: [23, 25]
103
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
104
+ - sources:
105
+ - layer_range: [24, 26]
106
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
107
+ - sources:
108
+ - layer_range: [25, 27]
109
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
110
+ - sources:
111
+ - layer_range: [26, 28]
112
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
113
+ - sources:
114
+ - layer_range: [27, 29]
115
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
116
+ - sources:
117
+ - layer_range: [28, 30]
118
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
119
+ - sources:
120
+ - layer_range: [29, 31]
121
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
122
+ - sources:
123
+ - layer_range: [30, 32]
124
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
125
+
126
+ ```
added_tokens.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|assistant|>": 32001,
3
+ "<|endoftext|>": 32000,
4
+ "<|end|>": 32007,
5
+ "<|placeholder1|>": 32002,
6
+ "<|placeholder2|>": 32003,
7
+ "<|placeholder3|>": 32004,
8
+ "<|placeholder4|>": 32005,
9
+ "<|placeholder5|>": 32008,
10
+ "<|placeholder6|>": 32009,
11
+ "<|system|>": 32006,
12
+ "<|user|>": 32010
13
+ }
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "win10/phi-3.5-Sakura-Yuzu-v1.5",
3
+ "architectures": [
4
+ "Phi3ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "FreedomIntelligence/Apollo2-3.8B--configuration_phi3.Phi3Config",
9
+ "AutoModelForCausalLM": "FreedomIntelligence/Apollo2-3.8B--modeling_phi3.Phi3ForCausalLM"
10
+ },
11
+ "bos_token_id": 1,
12
+ "embd_pdrop": 0.0,
13
+ "eos_token_id": 32000,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 3072,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 8192,
18
+ "max_position_embeddings": 4096,
19
+ "model_type": "phi3",
20
+ "num_attention_heads": 32,
21
+ "num_hidden_layers": 62,
22
+ "num_key_value_heads": 32,
23
+ "original_max_position_embeddings": 4096,
24
+ "pad_token_id": 32000,
25
+ "resid_pdrop": 0.0,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": null,
28
+ "rope_theta": 10000.0,
29
+ "sliding_window": 2047,
30
+ "tie_word_embeddings": false,
31
+ "torch_dtype": "float16",
32
+ "transformers_version": "4.45.1",
33
+ "use_cache": true,
34
+ "vocab_size": 32064
35
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ dtype: float16
2
+ merge_method: passthrough
3
+ slices:
4
+ - sources:
5
+ - layer_range: [0, 2]
6
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
7
+ - sources:
8
+ - layer_range: [1, 3]
9
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
10
+ - sources:
11
+ - layer_range: [2, 4]
12
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
13
+ - sources:
14
+ - layer_range: [3, 5]
15
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
16
+ - sources:
17
+ - layer_range: [4, 6]
18
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
19
+ - sources:
20
+ - layer_range: [5, 7]
21
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
22
+ - sources:
23
+ - layer_range: [6, 8]
24
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
25
+ - sources:
26
+ - layer_range: [7, 9]
27
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
28
+ - sources:
29
+ - layer_range: [8, 10]
30
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
31
+ - sources:
32
+ - layer_range: [9, 11]
33
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
34
+ - sources:
35
+ - layer_range: [10, 12]
36
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
37
+ - sources:
38
+ - layer_range: [11, 13]
39
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
40
+ - sources:
41
+ - layer_range: [12, 14]
42
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
43
+ - sources:
44
+ - layer_range: [13, 15]
45
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
46
+ - sources:
47
+ - layer_range: [14, 16]
48
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
49
+ - sources:
50
+ - layer_range: [15, 17]
51
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
52
+ - sources:
53
+ - layer_range: [16, 18]
54
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
55
+ - sources:
56
+ - layer_range: [17, 19]
57
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
58
+ - sources:
59
+ - layer_range: [18, 20]
60
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
61
+ - sources:
62
+ - layer_range: [19, 21]
63
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
64
+ - sources:
65
+ - layer_range: [20, 22]
66
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
67
+ - sources:
68
+ - layer_range: [21, 23]
69
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
70
+ - sources:
71
+ - layer_range: [22, 24]
72
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
73
+ - sources:
74
+ - layer_range: [23, 25]
75
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
76
+ - sources:
77
+ - layer_range: [24, 26]
78
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
79
+ - sources:
80
+ - layer_range: [25, 27]
81
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
82
+ - sources:
83
+ - layer_range: [26, 28]
84
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
85
+ - sources:
86
+ - layer_range: [27, 29]
87
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
88
+ - sources:
89
+ - layer_range: [28, 30]
90
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
91
+ - sources:
92
+ - layer_range: [29, 31]
93
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
94
+ - sources:
95
+ - layer_range: [30, 32]
96
+ model: win10/phi-3.5-Sakura-Yuzu-v1.5
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:032ca79e3f794fb3bb449b9973fe710c3e09e7607432160ccb48f15825afc297
3
+ size 4999620656
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eca13ad546ec2e3d923bc6973efebbcb7e631604833fea5c451008d23e62313
3
+ size 4983118824
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:453f72489b4c3ef9996676e423eeb654b7031ce28e42a275c50d563ef75be30b
3
+ size 4454604248
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.4", "total_size": 14437300224}, "weight_map": {"lm_head.weight": "model-00001-of-00003.safetensors", "model.embed_tokens.weight": "model-00001-of-00003.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.26.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.26.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.28.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.27.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.28.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", "model.layers.27.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.30.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.29.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.30.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", "model.layers.29.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", "model.layers.32.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.32.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.31.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.32.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", "model.layers.31.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", "model.layers.34.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.33.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.34.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.33.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.34.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", "model.layers.33.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors", "model.layers.36.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.35.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.36.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.35.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", "model.layers.38.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.37.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.38.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.38.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", "model.layers.40.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.39.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.40.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.39.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.40.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", "model.layers.39.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", "model.layers.42.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.41.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.42.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.41.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.42.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", "model.layers.41.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.43.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", "model.layers.46.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.45.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.46.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.45.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.46.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", "model.layers.45.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", "model.layers.48.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.47.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.48.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.47.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.48.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", "model.layers.47.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", "model.layers.50.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.49.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.50.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.49.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.50.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", "model.layers.49.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", "model.layers.52.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.51.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.52.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.51.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.52.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", "model.layers.51.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", "model.layers.54.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.53.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.54.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.53.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.54.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", "model.layers.53.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors", "model.layers.56.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.55.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.56.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.55.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.56.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors", "model.layers.55.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors", "model.layers.58.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.57.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.58.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.57.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.58.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors", "model.layers.57.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors", "model.layers.60.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.59.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.60.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.59.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.60.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors", "model.layers.59.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors", "model.layers.61.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.61.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.61.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.10.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.10.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.12.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.11.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.12.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors", "model.layers.11.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.14.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.13.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.14.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors", "model.layers.13.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.16.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.15.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.16.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors", "model.layers.15.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.18.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.17.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.18.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors", "model.layers.17.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors", "model.norm.weight": "model-00003-of-00003.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|placeholder1|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|placeholder2|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|placeholder3|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|placeholder4|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|placeholder5|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|placeholder6|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ }
118
+ },
119
+ "bos_token": "<s>",
120
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
121
+ "clean_up_tokenization_spaces": false,
122
+ "eos_token": "<|endoftext|>",
123
+ "legacy": false,
124
+ "max_length": null,
125
+ "model_max_length": 4096,
126
+ "pad_to_multiple_of": null,
127
+ "pad_token": "<unk>",
128
+ "pad_token_type_id": 0,
129
+ "padding_side": "left",
130
+ "sp_model_kwargs": {},
131
+ "tokenizer_class": "LlamaTokenizer",
132
+ "unk_token": "<unk>",
133
+ "use_default_system_prompt": false
134
+ }