Lin-K76 commited on
Commit
d3229ca
1 Parent(s): be9f3c1

Upload folder using huggingface_hub

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 +1,177 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/Phi-3-medium-128k-instruct",
3
+ "architectures": [
4
+ "Phi3ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "microsoft/Phi-3-medium-128k-instruct--configuration_phi3.Phi3Config",
10
+ "AutoModelForCausalLM": "microsoft/Phi-3-medium-128k-instruct--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": 5120,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 17920,
19
+ "max_position_embeddings": 131072,
20
+ "model_type": "phi3",
21
+ "num_attention_heads": 40,
22
+ "num_hidden_layers": 40,
23
+ "num_key_value_heads": 10,
24
+ "original_max_position_embeddings": 4096,
25
+ "pad_token_id": null,
26
+ "quantization_config": {
27
+ "activation_scheme": "static",
28
+ "ignored_layers": [
29
+ "lm_head"
30
+ ],
31
+ "quant_method": "fp8"
32
+ },
33
+ "resid_pdrop": 0.0,
34
+ "rms_norm_eps": 1e-05,
35
+ "rope_scaling": {
36
+ "long_factor": [
37
+ 1.0,
38
+ 1.0,
39
+ 1.0,
40
+ 1.0,
41
+ 1.0,
42
+ 1.0,
43
+ 1.0,
44
+ 1.0,
45
+ 1.0,
46
+ 1.0,
47
+ 1.0,
48
+ 1.0,
49
+ 1.0,
50
+ 1.25,
51
+ 1.25,
52
+ 1.5,
53
+ 2.0,
54
+ 2.75,
55
+ 5.75,
56
+ 5.75,
57
+ 6.5,
58
+ 9.25,
59
+ 11.0,
60
+ 13.25,
61
+ 19.25,
62
+ 19.75,
63
+ 19.75,
64
+ 21.25,
65
+ 21.5,
66
+ 26.5,
67
+ 30.0,
68
+ 33.75,
69
+ 35.25,
70
+ 38.5,
71
+ 42.0,
72
+ 42.25,
73
+ 46.0,
74
+ 47.0,
75
+ 50.0,
76
+ 50.5,
77
+ 51.0,
78
+ 52.0,
79
+ 52.75,
80
+ 53.75,
81
+ 54.75,
82
+ 57.0,
83
+ 57.25,
84
+ 58.5,
85
+ 59.25,
86
+ 59.5,
87
+ 62.0,
88
+ 62.5,
89
+ 62.75,
90
+ 63.25,
91
+ 63.25,
92
+ 63.25,
93
+ 63.75,
94
+ 64.0,
95
+ 64.0,
96
+ 64.25,
97
+ 64.5,
98
+ 64.5,
99
+ 65.0,
100
+ 65.0
101
+ ],
102
+ "short_factor": [
103
+ 1.0,
104
+ 1.0,
105
+ 1.0,
106
+ 1.0,
107
+ 1.0,
108
+ 1.0,
109
+ 1.01,
110
+ 1.02,
111
+ 1.02,
112
+ 1.04,
113
+ 1.04,
114
+ 1.07,
115
+ 1.07,
116
+ 1.1,
117
+ 1.3000000000000003,
118
+ 1.3000000000000003,
119
+ 1.5000000000000004,
120
+ 1.5700000000000005,
121
+ 1.9000000000000008,
122
+ 2.3100000000000014,
123
+ 2.759999999999992,
124
+ 3.3899999999999784,
125
+ 3.9399999999999666,
126
+ 4.009999999999965,
127
+ 4.289999999999959,
128
+ 4.349999999999958,
129
+ 5.349999999999937,
130
+ 6.659999999999909,
131
+ 7.029999999999901,
132
+ 7.51999999999989,
133
+ 8.00999999999988,
134
+ 8.249999999999876,
135
+ 8.279999999999875,
136
+ 9.629999999999846,
137
+ 9.89999999999984,
138
+ 10.589999999999826,
139
+ 11.049999999999816,
140
+ 11.7899999999998,
141
+ 12.189999999999792,
142
+ 12.889999999999777,
143
+ 13.129999999999772,
144
+ 13.16999999999977,
145
+ 13.20999999999977,
146
+ 13.479999999999764,
147
+ 13.539999999999763,
148
+ 13.779999999999758,
149
+ 13.929999999999755,
150
+ 14.429999999999744,
151
+ 14.759999999999737,
152
+ 15.149999999999729,
153
+ 15.419999999999723,
154
+ 15.53999999999972,
155
+ 15.659999999999718,
156
+ 15.749999999999716,
157
+ 15.759999999999716,
158
+ 15.799999999999715,
159
+ 16.05999999999971,
160
+ 16.079999999999714,
161
+ 16.11999999999972,
162
+ 16.11999999999972,
163
+ 16.18999999999973,
164
+ 16.31999999999975,
165
+ 16.539999999999786,
166
+ 16.799999999999827
167
+ ],
168
+ "type": "su"
169
+ },
170
+ "rope_theta": 10000.0,
171
+ "sliding_window": 131072,
172
+ "tie_word_embeddings": false,
173
+ "torch_dtype": "bfloat16",
174
+ "transformers_version": "4.41.2",
175
+ "use_cache": true,
176
+ "vocab_size": 32064
177
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 32000,
6
+ 32001,
7
+ 32007
8
+ ],
9
+ "pad_token_id": 32000,
10
+ "transformers_version": "4.41.2"
11
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2794ba1b4be797712dc26b0eb6e6f53cee7740116ea6a8300a0b5a6c43d0e66
3
+ size 4824391816
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae5f044542bf9db041c5be9b3aba41cd9a5b53742c591c375c72d227c8926f7a
3
+ size 4954829984
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79cd42568d7fe4ad8f09d11fb80d3b5e10ebe9e9afaaeba5e8b96200a16c3829
3
+ size 4509827824
model.safetensors.index.json ADDED
@@ -0,0 +1,570 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14288989440
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.mlp.gate_up_proj.input_scale": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.mlp.gate_up_proj.weight_scale": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
17
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
19
+ "model.layers.0.self_attn.qkv_proj.input_scale": "model-00001-of-00003.safetensors",
20
+ "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.0.self_attn.qkv_proj.weight_scale": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
26
+ "model.layers.1.mlp.gate_up_proj.input_scale": "model-00001-of-00003.safetensors",
27
+ "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
28
+ "model.layers.1.mlp.gate_up_proj.weight_scale": "model-00001-of-00003.safetensors",
29
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.1.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
31
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
33
+ "model.layers.1.self_attn.qkv_proj.input_scale": "model-00001-of-00003.safetensors",
34
+ "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.1.self_attn.qkv_proj.weight_scale": "model-00001-of-00003.safetensors",
36
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
37
+ "model.layers.10.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
38
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
39
+ "model.layers.10.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
40
+ "model.layers.10.mlp.gate_up_proj.input_scale": "model-00001-of-00003.safetensors",
41
+ "model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
42
+ "model.layers.10.mlp.gate_up_proj.weight_scale": "model-00001-of-00003.safetensors",
43
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
44
+ "model.layers.10.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
45
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
46
+ "model.layers.10.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
47
+ "model.layers.10.self_attn.qkv_proj.input_scale": "model-00001-of-00003.safetensors",
48
+ "model.layers.10.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
49
+ "model.layers.10.self_attn.qkv_proj.weight_scale": "model-00001-of-00003.safetensors",
50
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
51
+ "model.layers.11.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
52
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
53
+ "model.layers.11.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
54
+ "model.layers.11.mlp.gate_up_proj.input_scale": "model-00001-of-00003.safetensors",
55
+ "model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
56
+ "model.layers.11.mlp.gate_up_proj.weight_scale": "model-00001-of-00003.safetensors",
57
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
58
+ "model.layers.11.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
59
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
60
+ "model.layers.11.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
61
+ "model.layers.11.self_attn.qkv_proj.input_scale": "model-00001-of-00003.safetensors",
62
+ "model.layers.11.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
63
+ "model.layers.11.self_attn.qkv_proj.weight_scale": "model-00001-of-00003.safetensors",
64
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
65
+ "model.layers.12.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
66
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
67
+ "model.layers.12.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
68
+ "model.layers.12.mlp.gate_up_proj.input_scale": "model-00001-of-00003.safetensors",
69
+ "model.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
70
+ "model.layers.12.mlp.gate_up_proj.weight_scale": "model-00001-of-00003.safetensors",
71
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
72
+ "model.layers.12.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
73
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
74
+ "model.layers.12.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
75
+ "model.layers.12.self_attn.qkv_proj.input_scale": "model-00001-of-00003.safetensors",
76
+ "model.layers.12.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
77
+ "model.layers.12.self_attn.qkv_proj.weight_scale": "model-00001-of-00003.safetensors",
78
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.13.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
80
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.13.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
82
+ "model.layers.13.mlp.gate_up_proj.input_scale": "model-00002-of-00003.safetensors",
83
+ "model.layers.13.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.13.mlp.gate_up_proj.weight_scale": "model-00002-of-00003.safetensors",
85
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.13.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
87
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
88
+ "model.layers.13.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
89
+ "model.layers.13.self_attn.qkv_proj.input_scale": "model-00001-of-00003.safetensors",
90
+ "model.layers.13.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
91
+ "model.layers.13.self_attn.qkv_proj.weight_scale": "model-00001-of-00003.safetensors",
92
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.14.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
94
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.14.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
96
+ "model.layers.14.mlp.gate_up_proj.input_scale": "model-00002-of-00003.safetensors",
97
+ "model.layers.14.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.14.mlp.gate_up_proj.weight_scale": "model-00002-of-00003.safetensors",
99
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.14.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
101
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.14.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
103
+ "model.layers.14.self_attn.qkv_proj.input_scale": "model-00002-of-00003.safetensors",
104
+ "model.layers.14.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.14.self_attn.qkv_proj.weight_scale": "model-00002-of-00003.safetensors",
106
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.15.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
108
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.15.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
110
+ "model.layers.15.mlp.gate_up_proj.input_scale": "model-00002-of-00003.safetensors",
111
+ "model.layers.15.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.15.mlp.gate_up_proj.weight_scale": "model-00002-of-00003.safetensors",
113
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.15.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
115
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.15.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
117
+ "model.layers.15.self_attn.qkv_proj.input_scale": "model-00002-of-00003.safetensors",
118
+ "model.layers.15.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
119
+ "model.layers.15.self_attn.qkv_proj.weight_scale": "model-00002-of-00003.safetensors",
120
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
121
+ "model.layers.16.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
122
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
123
+ "model.layers.16.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
124
+ "model.layers.16.mlp.gate_up_proj.input_scale": "model-00002-of-00003.safetensors",
125
+ "model.layers.16.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.16.mlp.gate_up_proj.weight_scale": "model-00002-of-00003.safetensors",
127
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.16.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
129
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.16.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
131
+ "model.layers.16.self_attn.qkv_proj.input_scale": "model-00002-of-00003.safetensors",
132
+ "model.layers.16.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.16.self_attn.qkv_proj.weight_scale": "model-00002-of-00003.safetensors",
134
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.17.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
136
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.17.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
138
+ "model.layers.17.mlp.gate_up_proj.input_scale": "model-00002-of-00003.safetensors",
139
+ "model.layers.17.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.17.mlp.gate_up_proj.weight_scale": "model-00002-of-00003.safetensors",
141
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.17.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
143
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
144
+ "model.layers.17.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
145
+ "model.layers.17.self_attn.qkv_proj.input_scale": "model-00002-of-00003.safetensors",
146
+ "model.layers.17.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
147
+ "model.layers.17.self_attn.qkv_proj.weight_scale": "model-00002-of-00003.safetensors",
148
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.18.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
150
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.18.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
152
+ "model.layers.18.mlp.gate_up_proj.input_scale": "model-00002-of-00003.safetensors",
153
+ "model.layers.18.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
154
+ "model.layers.18.mlp.gate_up_proj.weight_scale": "model-00002-of-00003.safetensors",
155
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
156
+ "model.layers.18.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
157
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
158
+ "model.layers.18.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
159
+ "model.layers.18.self_attn.qkv_proj.input_scale": "model-00002-of-00003.safetensors",
160
+ "model.layers.18.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
161
+ "model.layers.18.self_attn.qkv_proj.weight_scale": "model-00002-of-00003.safetensors",
162
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
163
+ "model.layers.19.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
164
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
165
+ "model.layers.19.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
166
+ "model.layers.19.mlp.gate_up_proj.input_scale": "model-00002-of-00003.safetensors",
167
+ "model.layers.19.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
168
+ "model.layers.19.mlp.gate_up_proj.weight_scale": "model-00002-of-00003.safetensors",
169
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
170
+ "model.layers.19.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
171
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
172
+ "model.layers.19.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
173
+ "model.layers.19.self_attn.qkv_proj.input_scale": "model-00002-of-00003.safetensors",
174
+ "model.layers.19.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
175
+ "model.layers.19.self_attn.qkv_proj.weight_scale": "model-00002-of-00003.safetensors",
176
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
177
+ "model.layers.2.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
178
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
179
+ "model.layers.2.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
180
+ "model.layers.2.mlp.gate_up_proj.input_scale": "model-00001-of-00003.safetensors",
181
+ "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
182
+ "model.layers.2.mlp.gate_up_proj.weight_scale": "model-00001-of-00003.safetensors",
183
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
184
+ "model.layers.2.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
185
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
186
+ "model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
187
+ "model.layers.2.self_attn.qkv_proj.input_scale": "model-00001-of-00003.safetensors",
188
+ "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
189
+ "model.layers.2.self_attn.qkv_proj.weight_scale": "model-00001-of-00003.safetensors",
190
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
191
+ "model.layers.20.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
192
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
193
+ "model.layers.20.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
194
+ "model.layers.20.mlp.gate_up_proj.input_scale": "model-00002-of-00003.safetensors",
195
+ "model.layers.20.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
196
+ "model.layers.20.mlp.gate_up_proj.weight_scale": "model-00002-of-00003.safetensors",
197
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
198
+ "model.layers.20.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
199
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
200
+ "model.layers.20.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
201
+ "model.layers.20.self_attn.qkv_proj.input_scale": "model-00002-of-00003.safetensors",
202
+ "model.layers.20.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
203
+ "model.layers.20.self_attn.qkv_proj.weight_scale": "model-00002-of-00003.safetensors",
204
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
205
+ "model.layers.21.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
206
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
207
+ "model.layers.21.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
208
+ "model.layers.21.mlp.gate_up_proj.input_scale": "model-00002-of-00003.safetensors",
209
+ "model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
210
+ "model.layers.21.mlp.gate_up_proj.weight_scale": "model-00002-of-00003.safetensors",
211
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
212
+ "model.layers.21.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
213
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
214
+ "model.layers.21.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
215
+ "model.layers.21.self_attn.qkv_proj.input_scale": "model-00002-of-00003.safetensors",
216
+ "model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
217
+ "model.layers.21.self_attn.qkv_proj.weight_scale": "model-00002-of-00003.safetensors",
218
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
219
+ "model.layers.22.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
220
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
221
+ "model.layers.22.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
222
+ "model.layers.22.mlp.gate_up_proj.input_scale": "model-00002-of-00003.safetensors",
223
+ "model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
224
+ "model.layers.22.mlp.gate_up_proj.weight_scale": "model-00002-of-00003.safetensors",
225
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
226
+ "model.layers.22.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
227
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
228
+ "model.layers.22.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
229
+ "model.layers.22.self_attn.qkv_proj.input_scale": "model-00002-of-00003.safetensors",
230
+ "model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
231
+ "model.layers.22.self_attn.qkv_proj.weight_scale": "model-00002-of-00003.safetensors",
232
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
233
+ "model.layers.23.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
234
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
235
+ "model.layers.23.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
236
+ "model.layers.23.mlp.gate_up_proj.input_scale": "model-00002-of-00003.safetensors",
237
+ "model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
238
+ "model.layers.23.mlp.gate_up_proj.weight_scale": "model-00002-of-00003.safetensors",
239
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
240
+ "model.layers.23.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
241
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
242
+ "model.layers.23.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
243
+ "model.layers.23.self_attn.qkv_proj.input_scale": "model-00002-of-00003.safetensors",
244
+ "model.layers.23.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
245
+ "model.layers.23.self_attn.qkv_proj.weight_scale": "model-00002-of-00003.safetensors",
246
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
247
+ "model.layers.24.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
248
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
249
+ "model.layers.24.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
250
+ "model.layers.24.mlp.gate_up_proj.input_scale": "model-00002-of-00003.safetensors",
251
+ "model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
252
+ "model.layers.24.mlp.gate_up_proj.weight_scale": "model-00002-of-00003.safetensors",
253
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
254
+ "model.layers.24.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
255
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
256
+ "model.layers.24.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
257
+ "model.layers.24.self_attn.qkv_proj.input_scale": "model-00002-of-00003.safetensors",
258
+ "model.layers.24.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
259
+ "model.layers.24.self_attn.qkv_proj.weight_scale": "model-00002-of-00003.safetensors",
260
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
261
+ "model.layers.25.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
262
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
263
+ "model.layers.25.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
264
+ "model.layers.25.mlp.gate_up_proj.input_scale": "model-00002-of-00003.safetensors",
265
+ "model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
266
+ "model.layers.25.mlp.gate_up_proj.weight_scale": "model-00002-of-00003.safetensors",
267
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
268
+ "model.layers.25.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
269
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
270
+ "model.layers.25.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
271
+ "model.layers.25.self_attn.qkv_proj.input_scale": "model-00002-of-00003.safetensors",
272
+ "model.layers.25.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
273
+ "model.layers.25.self_attn.qkv_proj.weight_scale": "model-00002-of-00003.safetensors",
274
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
275
+ "model.layers.26.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
276
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
277
+ "model.layers.26.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
278
+ "model.layers.26.mlp.gate_up_proj.input_scale": "model-00002-of-00003.safetensors",
279
+ "model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
280
+ "model.layers.26.mlp.gate_up_proj.weight_scale": "model-00002-of-00003.safetensors",
281
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
282
+ "model.layers.26.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
283
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
284
+ "model.layers.26.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
285
+ "model.layers.26.self_attn.qkv_proj.input_scale": "model-00002-of-00003.safetensors",
286
+ "model.layers.26.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
287
+ "model.layers.26.self_attn.qkv_proj.weight_scale": "model-00002-of-00003.safetensors",
288
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
289
+ "model.layers.27.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
290
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
291
+ "model.layers.27.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
292
+ "model.layers.27.mlp.gate_up_proj.input_scale": "model-00002-of-00003.safetensors",
293
+ "model.layers.27.mlp.gate_up_proj.weight": "model-00002-of-00003.safetensors",
294
+ "model.layers.27.mlp.gate_up_proj.weight_scale": "model-00002-of-00003.safetensors",
295
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
296
+ "model.layers.27.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
297
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
298
+ "model.layers.27.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
299
+ "model.layers.27.self_attn.qkv_proj.input_scale": "model-00002-of-00003.safetensors",
300
+ "model.layers.27.self_attn.qkv_proj.weight": "model-00002-of-00003.safetensors",
301
+ "model.layers.27.self_attn.qkv_proj.weight_scale": "model-00002-of-00003.safetensors",
302
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
303
+ "model.layers.28.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
304
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
305
+ "model.layers.28.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
306
+ "model.layers.28.mlp.gate_up_proj.input_scale": "model-00003-of-00003.safetensors",
307
+ "model.layers.28.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
308
+ "model.layers.28.mlp.gate_up_proj.weight_scale": "model-00003-of-00003.safetensors",
309
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
310
+ "model.layers.28.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
311
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
312
+ "model.layers.28.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
313
+ "model.layers.28.self_attn.qkv_proj.input_scale": "model-00003-of-00003.safetensors",
314
+ "model.layers.28.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
315
+ "model.layers.28.self_attn.qkv_proj.weight_scale": "model-00003-of-00003.safetensors",
316
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
317
+ "model.layers.29.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
318
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
319
+ "model.layers.29.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
320
+ "model.layers.29.mlp.gate_up_proj.input_scale": "model-00003-of-00003.safetensors",
321
+ "model.layers.29.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
322
+ "model.layers.29.mlp.gate_up_proj.weight_scale": "model-00003-of-00003.safetensors",
323
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
324
+ "model.layers.29.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
325
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
326
+ "model.layers.29.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
327
+ "model.layers.29.self_attn.qkv_proj.input_scale": "model-00003-of-00003.safetensors",
328
+ "model.layers.29.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
329
+ "model.layers.29.self_attn.qkv_proj.weight_scale": "model-00003-of-00003.safetensors",
330
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
331
+ "model.layers.3.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
332
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
333
+ "model.layers.3.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
334
+ "model.layers.3.mlp.gate_up_proj.input_scale": "model-00001-of-00003.safetensors",
335
+ "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
336
+ "model.layers.3.mlp.gate_up_proj.weight_scale": "model-00001-of-00003.safetensors",
337
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
338
+ "model.layers.3.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
339
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
340
+ "model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
341
+ "model.layers.3.self_attn.qkv_proj.input_scale": "model-00001-of-00003.safetensors",
342
+ "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
343
+ "model.layers.3.self_attn.qkv_proj.weight_scale": "model-00001-of-00003.safetensors",
344
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
345
+ "model.layers.30.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
346
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
347
+ "model.layers.30.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
348
+ "model.layers.30.mlp.gate_up_proj.input_scale": "model-00003-of-00003.safetensors",
349
+ "model.layers.30.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
350
+ "model.layers.30.mlp.gate_up_proj.weight_scale": "model-00003-of-00003.safetensors",
351
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
352
+ "model.layers.30.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
353
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
354
+ "model.layers.30.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
355
+ "model.layers.30.self_attn.qkv_proj.input_scale": "model-00003-of-00003.safetensors",
356
+ "model.layers.30.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
357
+ "model.layers.30.self_attn.qkv_proj.weight_scale": "model-00003-of-00003.safetensors",
358
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
359
+ "model.layers.31.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
360
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
361
+ "model.layers.31.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
362
+ "model.layers.31.mlp.gate_up_proj.input_scale": "model-00003-of-00003.safetensors",
363
+ "model.layers.31.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
364
+ "model.layers.31.mlp.gate_up_proj.weight_scale": "model-00003-of-00003.safetensors",
365
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
366
+ "model.layers.31.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
367
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
368
+ "model.layers.31.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
369
+ "model.layers.31.self_attn.qkv_proj.input_scale": "model-00003-of-00003.safetensors",
370
+ "model.layers.31.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
371
+ "model.layers.31.self_attn.qkv_proj.weight_scale": "model-00003-of-00003.safetensors",
372
+ "model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
373
+ "model.layers.32.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
374
+ "model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
375
+ "model.layers.32.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
376
+ "model.layers.32.mlp.gate_up_proj.input_scale": "model-00003-of-00003.safetensors",
377
+ "model.layers.32.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
378
+ "model.layers.32.mlp.gate_up_proj.weight_scale": "model-00003-of-00003.safetensors",
379
+ "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
380
+ "model.layers.32.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
381
+ "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
382
+ "model.layers.32.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
383
+ "model.layers.32.self_attn.qkv_proj.input_scale": "model-00003-of-00003.safetensors",
384
+ "model.layers.32.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
385
+ "model.layers.32.self_attn.qkv_proj.weight_scale": "model-00003-of-00003.safetensors",
386
+ "model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
387
+ "model.layers.33.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
388
+ "model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
389
+ "model.layers.33.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
390
+ "model.layers.33.mlp.gate_up_proj.input_scale": "model-00003-of-00003.safetensors",
391
+ "model.layers.33.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
392
+ "model.layers.33.mlp.gate_up_proj.weight_scale": "model-00003-of-00003.safetensors",
393
+ "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
394
+ "model.layers.33.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
395
+ "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
396
+ "model.layers.33.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
397
+ "model.layers.33.self_attn.qkv_proj.input_scale": "model-00003-of-00003.safetensors",
398
+ "model.layers.33.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
399
+ "model.layers.33.self_attn.qkv_proj.weight_scale": "model-00003-of-00003.safetensors",
400
+ "model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
401
+ "model.layers.34.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
402
+ "model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
403
+ "model.layers.34.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
404
+ "model.layers.34.mlp.gate_up_proj.input_scale": "model-00003-of-00003.safetensors",
405
+ "model.layers.34.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
406
+ "model.layers.34.mlp.gate_up_proj.weight_scale": "model-00003-of-00003.safetensors",
407
+ "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
408
+ "model.layers.34.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
409
+ "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
410
+ "model.layers.34.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
411
+ "model.layers.34.self_attn.qkv_proj.input_scale": "model-00003-of-00003.safetensors",
412
+ "model.layers.34.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
413
+ "model.layers.34.self_attn.qkv_proj.weight_scale": "model-00003-of-00003.safetensors",
414
+ "model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
415
+ "model.layers.35.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
416
+ "model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
417
+ "model.layers.35.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
418
+ "model.layers.35.mlp.gate_up_proj.input_scale": "model-00003-of-00003.safetensors",
419
+ "model.layers.35.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
420
+ "model.layers.35.mlp.gate_up_proj.weight_scale": "model-00003-of-00003.safetensors",
421
+ "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
422
+ "model.layers.35.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
423
+ "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
424
+ "model.layers.35.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
425
+ "model.layers.35.self_attn.qkv_proj.input_scale": "model-00003-of-00003.safetensors",
426
+ "model.layers.35.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
427
+ "model.layers.35.self_attn.qkv_proj.weight_scale": "model-00003-of-00003.safetensors",
428
+ "model.layers.36.input_layernorm.weight": "model-00003-of-00003.safetensors",
429
+ "model.layers.36.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
430
+ "model.layers.36.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
431
+ "model.layers.36.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
432
+ "model.layers.36.mlp.gate_up_proj.input_scale": "model-00003-of-00003.safetensors",
433
+ "model.layers.36.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
434
+ "model.layers.36.mlp.gate_up_proj.weight_scale": "model-00003-of-00003.safetensors",
435
+ "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
436
+ "model.layers.36.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
437
+ "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
438
+ "model.layers.36.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
439
+ "model.layers.36.self_attn.qkv_proj.input_scale": "model-00003-of-00003.safetensors",
440
+ "model.layers.36.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
441
+ "model.layers.36.self_attn.qkv_proj.weight_scale": "model-00003-of-00003.safetensors",
442
+ "model.layers.37.input_layernorm.weight": "model-00003-of-00003.safetensors",
443
+ "model.layers.37.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
444
+ "model.layers.37.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
445
+ "model.layers.37.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
446
+ "model.layers.37.mlp.gate_up_proj.input_scale": "model-00003-of-00003.safetensors",
447
+ "model.layers.37.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
448
+ "model.layers.37.mlp.gate_up_proj.weight_scale": "model-00003-of-00003.safetensors",
449
+ "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
450
+ "model.layers.37.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
451
+ "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
452
+ "model.layers.37.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
453
+ "model.layers.37.self_attn.qkv_proj.input_scale": "model-00003-of-00003.safetensors",
454
+ "model.layers.37.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
455
+ "model.layers.37.self_attn.qkv_proj.weight_scale": "model-00003-of-00003.safetensors",
456
+ "model.layers.38.input_layernorm.weight": "model-00003-of-00003.safetensors",
457
+ "model.layers.38.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
458
+ "model.layers.38.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
459
+ "model.layers.38.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
460
+ "model.layers.38.mlp.gate_up_proj.input_scale": "model-00003-of-00003.safetensors",
461
+ "model.layers.38.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
462
+ "model.layers.38.mlp.gate_up_proj.weight_scale": "model-00003-of-00003.safetensors",
463
+ "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
464
+ "model.layers.38.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
465
+ "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
466
+ "model.layers.38.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
467
+ "model.layers.38.self_attn.qkv_proj.input_scale": "model-00003-of-00003.safetensors",
468
+ "model.layers.38.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
469
+ "model.layers.38.self_attn.qkv_proj.weight_scale": "model-00003-of-00003.safetensors",
470
+ "model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors",
471
+ "model.layers.39.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
472
+ "model.layers.39.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
473
+ "model.layers.39.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
474
+ "model.layers.39.mlp.gate_up_proj.input_scale": "model-00003-of-00003.safetensors",
475
+ "model.layers.39.mlp.gate_up_proj.weight": "model-00003-of-00003.safetensors",
476
+ "model.layers.39.mlp.gate_up_proj.weight_scale": "model-00003-of-00003.safetensors",
477
+ "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
478
+ "model.layers.39.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
479
+ "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
480
+ "model.layers.39.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
481
+ "model.layers.39.self_attn.qkv_proj.input_scale": "model-00003-of-00003.safetensors",
482
+ "model.layers.39.self_attn.qkv_proj.weight": "model-00003-of-00003.safetensors",
483
+ "model.layers.39.self_attn.qkv_proj.weight_scale": "model-00003-of-00003.safetensors",
484
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
485
+ "model.layers.4.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
486
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
487
+ "model.layers.4.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
488
+ "model.layers.4.mlp.gate_up_proj.input_scale": "model-00001-of-00003.safetensors",
489
+ "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
490
+ "model.layers.4.mlp.gate_up_proj.weight_scale": "model-00001-of-00003.safetensors",
491
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
492
+ "model.layers.4.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
493
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
494
+ "model.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
495
+ "model.layers.4.self_attn.qkv_proj.input_scale": "model-00001-of-00003.safetensors",
496
+ "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
497
+ "model.layers.4.self_attn.qkv_proj.weight_scale": "model-00001-of-00003.safetensors",
498
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
499
+ "model.layers.5.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
500
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
501
+ "model.layers.5.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
502
+ "model.layers.5.mlp.gate_up_proj.input_scale": "model-00001-of-00003.safetensors",
503
+ "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
504
+ "model.layers.5.mlp.gate_up_proj.weight_scale": "model-00001-of-00003.safetensors",
505
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
506
+ "model.layers.5.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
507
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
508
+ "model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
509
+ "model.layers.5.self_attn.qkv_proj.input_scale": "model-00001-of-00003.safetensors",
510
+ "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
511
+ "model.layers.5.self_attn.qkv_proj.weight_scale": "model-00001-of-00003.safetensors",
512
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
513
+ "model.layers.6.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
514
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
515
+ "model.layers.6.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
516
+ "model.layers.6.mlp.gate_up_proj.input_scale": "model-00001-of-00003.safetensors",
517
+ "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
518
+ "model.layers.6.mlp.gate_up_proj.weight_scale": "model-00001-of-00003.safetensors",
519
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
520
+ "model.layers.6.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
521
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
522
+ "model.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
523
+ "model.layers.6.self_attn.qkv_proj.input_scale": "model-00001-of-00003.safetensors",
524
+ "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
525
+ "model.layers.6.self_attn.qkv_proj.weight_scale": "model-00001-of-00003.safetensors",
526
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
527
+ "model.layers.7.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
528
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
529
+ "model.layers.7.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
530
+ "model.layers.7.mlp.gate_up_proj.input_scale": "model-00001-of-00003.safetensors",
531
+ "model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
532
+ "model.layers.7.mlp.gate_up_proj.weight_scale": "model-00001-of-00003.safetensors",
533
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
534
+ "model.layers.7.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
535
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
536
+ "model.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
537
+ "model.layers.7.self_attn.qkv_proj.input_scale": "model-00001-of-00003.safetensors",
538
+ "model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
539
+ "model.layers.7.self_attn.qkv_proj.weight_scale": "model-00001-of-00003.safetensors",
540
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
541
+ "model.layers.8.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
542
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
543
+ "model.layers.8.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
544
+ "model.layers.8.mlp.gate_up_proj.input_scale": "model-00001-of-00003.safetensors",
545
+ "model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
546
+ "model.layers.8.mlp.gate_up_proj.weight_scale": "model-00001-of-00003.safetensors",
547
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
548
+ "model.layers.8.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
549
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
550
+ "model.layers.8.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
551
+ "model.layers.8.self_attn.qkv_proj.input_scale": "model-00001-of-00003.safetensors",
552
+ "model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
553
+ "model.layers.8.self_attn.qkv_proj.weight_scale": "model-00001-of-00003.safetensors",
554
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
555
+ "model.layers.9.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
556
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
557
+ "model.layers.9.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
558
+ "model.layers.9.mlp.gate_up_proj.input_scale": "model-00001-of-00003.safetensors",
559
+ "model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00003.safetensors",
560
+ "model.layers.9.mlp.gate_up_proj.weight_scale": "model-00001-of-00003.safetensors",
561
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
562
+ "model.layers.9.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
563
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
564
+ "model.layers.9.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
565
+ "model.layers.9.self_attn.qkv_proj.input_scale": "model-00001-of-00003.safetensors",
566
+ "model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00003.safetensors",
567
+ "model.layers.9.self_attn.qkv_proj.weight_scale": "model-00001-of-00003.safetensors",
568
+ "model.norm.weight": "model-00003-of-00003.safetensors"
569
+ }
570
+ }
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 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": true,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "32000": {
30
+ "content": "<|endoftext|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|assistant|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": true,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "<|placeholder1|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": true,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32003": {
54
+ "content": "<|placeholder2|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": true,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "32004": {
62
+ "content": "<|placeholder3|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": true,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "32005": {
70
+ "content": "<|placeholder4|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": true,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "32006": {
78
+ "content": "<|system|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": true,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "32007": {
86
+ "content": "<|end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": true,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "32008": {
94
+ "content": "<|placeholder5|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": true,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "32009": {
102
+ "content": "<|placeholder6|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": true,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "32010": {
110
+ "content": "<|user|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": true,
114
+ "single_word": false,
115
+ "special": true
116
+ }
117
+ },
118
+ "bos_token": "<s>",
119
+ "chat_template": "{% 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 %}",
120
+ "clean_up_tokenization_spaces": false,
121
+ "eos_token": "<|endoftext|>",
122
+ "legacy": false,
123
+ "model_max_length": 131072,
124
+ "pad_token": "<|endoftext|>",
125
+ "padding_side": "left",
126
+ "sp_model_kwargs": {},
127
+ "tokenizer_class": "LlamaTokenizer",
128
+ "unk_token": "<unk>",
129
+ "use_default_system_prompt": false
130
+ }