SicariusSicariiStuff commited on
Commit
f3a3be9
1 Parent(s): d29e18e

Upload 10 files

Browse files
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 +1,138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "SicariusSicariiStuff/Phi-3.5-mini-instruct_Uncensored",
3
+ "architectures": [
4
+ "Phi3ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "configuration_phi3.Phi3Config",
10
+ "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
11
+ },
12
+ "bos_token_id": 1,
13
+ "embd_pdrop": 0.0,
14
+ "eos_token_id": 32000,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 3072,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 131072,
20
+ "model_type": "phi3",
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 32,
23
+ "num_key_value_heads": 32,
24
+ "original_max_position_embeddings": 4096,
25
+ "pad_token_id": 32000,
26
+ "resid_pdrop": 0.0,
27
+ "rms_norm_eps": 1e-05,
28
+ "rope_scaling": {
29
+ "long_factor": [
30
+ 1.0800000429153442,
31
+ 1.1100000143051147,
32
+ 1.1399999856948853,
33
+ 1.340000033378601,
34
+ 1.5899999141693115,
35
+ 1.600000023841858,
36
+ 1.6200000047683716,
37
+ 2.620000123977661,
38
+ 3.2300000190734863,
39
+ 3.2300000190734863,
40
+ 4.789999961853027,
41
+ 7.400000095367432,
42
+ 7.700000286102295,
43
+ 9.09000015258789,
44
+ 12.199999809265137,
45
+ 17.670000076293945,
46
+ 24.46000099182129,
47
+ 28.57000160217285,
48
+ 30.420001983642578,
49
+ 30.840002059936523,
50
+ 32.590003967285156,
51
+ 32.93000411987305,
52
+ 42.320003509521484,
53
+ 44.96000289916992,
54
+ 50.340003967285156,
55
+ 50.45000457763672,
56
+ 57.55000305175781,
57
+ 57.93000411987305,
58
+ 58.21000289916992,
59
+ 60.1400032043457,
60
+ 62.61000442504883,
61
+ 62.62000274658203,
62
+ 62.71000289916992,
63
+ 63.1400032043457,
64
+ 63.1400032043457,
65
+ 63.77000427246094,
66
+ 63.93000411987305,
67
+ 63.96000289916992,
68
+ 63.970001220703125,
69
+ 64.02999877929688,
70
+ 64.06999969482422,
71
+ 64.08000183105469,
72
+ 64.12000274658203,
73
+ 64.41000366210938,
74
+ 64.4800033569336,
75
+ 64.51000213623047,
76
+ 64.52999877929688,
77
+ 64.83999633789062
78
+ ],
79
+ "short_factor": [
80
+ 1.0,
81
+ 1.0199999809265137,
82
+ 1.0299999713897705,
83
+ 1.0299999713897705,
84
+ 1.0499999523162842,
85
+ 1.0499999523162842,
86
+ 1.0499999523162842,
87
+ 1.0499999523162842,
88
+ 1.0499999523162842,
89
+ 1.0699999332427979,
90
+ 1.0999999046325684,
91
+ 1.1099998950958252,
92
+ 1.1599998474121094,
93
+ 1.1599998474121094,
94
+ 1.1699998378753662,
95
+ 1.2899998426437378,
96
+ 1.339999794960022,
97
+ 1.679999828338623,
98
+ 1.7899998426437378,
99
+ 1.8199998140335083,
100
+ 1.8499997854232788,
101
+ 1.8799997568130493,
102
+ 1.9099997282028198,
103
+ 1.9399996995925903,
104
+ 1.9899996519088745,
105
+ 2.0199997425079346,
106
+ 2.0199997425079346,
107
+ 2.0199997425079346,
108
+ 2.0199997425079346,
109
+ 2.0199997425079346,
110
+ 2.0199997425079346,
111
+ 2.0299997329711914,
112
+ 2.0299997329711914,
113
+ 2.0299997329711914,
114
+ 2.0299997329711914,
115
+ 2.0299997329711914,
116
+ 2.0299997329711914,
117
+ 2.0299997329711914,
118
+ 2.0299997329711914,
119
+ 2.0299997329711914,
120
+ 2.0799996852874756,
121
+ 2.0899996757507324,
122
+ 2.189999580383301,
123
+ 2.2199995517730713,
124
+ 2.5899994373321533,
125
+ 2.729999542236328,
126
+ 2.749999523162842,
127
+ 2.8399994373321533
128
+ ],
129
+ "type": "longrope"
130
+ },
131
+ "rope_theta": 10000.0,
132
+ "sliding_window": 262144,
133
+ "tie_word_embeddings": false,
134
+ "torch_dtype": "float16",
135
+ "transformers_version": "4.44.0.dev0",
136
+ "use_cache": false,
137
+ "vocab_size": 32064
138
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 32007,
7
+ 32001,
8
+ 32000
9
+ ],
10
+ "pad_token_id": 32000,
11
+ "transformers_version": "4.44.0.dev0"
12
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a09e5ffd3a9222b5f932828b1c186b7fc9b47402cd1d498f08ec79210fab7fa1
3
+ size 4972489200
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:149000cbe88be9188b8975a5f6e223156c0371b547594f76510cd3359a8a8869
3
+ size 2669692488
model.safetensors.index.json ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 7642159104
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.10.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.11.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.12.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.13.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.13.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.14.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.14.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.15.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.15.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.16.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.16.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.17.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.17.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.18.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.18.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.19.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.19.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.20.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.20.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
93
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
94
+ "model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
95
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
96
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
98
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
99
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
100
+ "model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
101
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
102
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
103
+ "model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
104
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
105
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
106
+ "model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
107
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
108
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
109
+ "model.layers.23.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
110
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
111
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
112
+ "model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
113
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
114
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
115
+ "model.layers.24.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
116
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
117
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
118
+ "model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
119
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
120
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
121
+ "model.layers.25.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
122
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
123
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
124
+ "model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
125
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
126
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
127
+ "model.layers.26.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
128
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
129
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
130
+ "model.layers.27.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
131
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
132
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
133
+ "model.layers.27.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
134
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
135
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
136
+ "model.layers.28.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
137
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
138
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
139
+ "model.layers.28.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
140
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
141
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
142
+ "model.layers.29.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
143
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
144
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
145
+ "model.layers.29.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
146
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
153
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
154
+ "model.layers.30.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
155
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
156
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
157
+ "model.layers.30.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
158
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
159
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
160
+ "model.layers.31.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
161
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
162
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.31.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
164
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
182
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
184
+ "model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
186
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
188
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
190
+ "model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
194
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
196
+ "model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
200
+ "model.norm.weight": "model-00002-of-00002.safetensors"
201
+ }
202
+ }
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": "<|endoftext|>",
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 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
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'] == 'system') %}{{'<|system|>' + '\n' + message['content'] + '<|end|>' + '\n'}}{% elif (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
+ "model_max_length": 131072,
125
+ "pad_token": "<|endoftext|>",
126
+ "padding_side": "left",
127
+ "sp_model_kwargs": {},
128
+ "tokenizer_class": "LlamaTokenizer",
129
+ "unk_token": "<unk>",
130
+ "use_default_system_prompt": false
131
+ }