sosoai commited on
Commit
0913b85
1 Parent(s): d87e373

2cc43c0eede22f77a4cc91257b654627d0abc62cdfdd4487acf6ca59283ab90f

Browse files
README.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - mlx
4
+ ---
5
+
6
+ # sosoai/hansoldeco-phi3-4k-instruct-v0.1-mlx
7
+
8
+ The Model [sosoai/hansoldeco-phi3-4k-instruct-v0.1-mlx](https://huggingface.co/sosoai/hansoldeco-phi3-4k-instruct-v0.1-mlx) was converted to MLX format from [sosoai/hansoldeco-phi3-4k-instruct-v0.1](https://huggingface.co/sosoai/hansoldeco-phi3-4k-instruct-v0.1) using mlx-lm version **0.13.0**.
9
+
10
+ ## Use with mlx
11
+
12
+ ```bash
13
+ pip install mlx-lm
14
+ ```
15
+
16
+ ```python
17
+ from mlx_lm import load, generate
18
+
19
+ model, tokenizer = load("sosoai/hansoldeco-phi3-4k-instruct-v0.1-mlx")
20
+ response = generate(model, tokenizer, prompt="hello", verbose=True)
21
+ ```
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Phi3ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "auto_map": {
7
+ "AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config",
8
+ "AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM"
9
+ },
10
+ "bos_token_id": 1,
11
+ "embd_pdrop": 0.0,
12
+ "eos_token_id": 32000,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 3072,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 8192,
17
+ "max_position_embeddings": 4096,
18
+ "model_type": "phi3",
19
+ "num_attention_heads": 32,
20
+ "num_hidden_layers": 32,
21
+ "num_key_value_heads": 32,
22
+ "original_max_position_embeddings": 4096,
23
+ "pad_token_id": 32000,
24
+ "quantization": {
25
+ "group_size": 64,
26
+ "bits": 4
27
+ },
28
+ "resid_pdrop": 0.0,
29
+ "rms_norm_eps": 1e-05,
30
+ "rope_scaling": null,
31
+ "rope_theta": 10000.0,
32
+ "sliding_window": 2048,
33
+ "tie_word_embeddings": false,
34
+ "torch_dtype": "bfloat16",
35
+ "transformers_version": "4.40.0",
36
+ "use_cache": true,
37
+ "vocab_size": 32064
38
+ }
model.safetensors.index.json ADDED
@@ -0,0 +1,462 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 2149644288
4
+ },
5
+ "weight_map": {
6
+ "lm_head.biases": "model.safetensors",
7
+ "lm_head.scales": "model.safetensors",
8
+ "lm_head.weight": "model.safetensors",
9
+ "model.embed_tokens.biases": "model.safetensors",
10
+ "model.embed_tokens.scales": "model.safetensors",
11
+ "model.embed_tokens.weight": "model.safetensors",
12
+ "model.layers.0.input_layernorm.weight": "model.safetensors",
13
+ "model.layers.0.mlp.down_proj.biases": "model.safetensors",
14
+ "model.layers.0.mlp.down_proj.scales": "model.safetensors",
15
+ "model.layers.0.mlp.down_proj.weight": "model.safetensors",
16
+ "model.layers.0.mlp.gate_up_proj.biases": "model.safetensors",
17
+ "model.layers.0.mlp.gate_up_proj.scales": "model.safetensors",
18
+ "model.layers.0.mlp.gate_up_proj.weight": "model.safetensors",
19
+ "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
20
+ "model.layers.0.self_attn.o_proj.biases": "model.safetensors",
21
+ "model.layers.0.self_attn.o_proj.scales": "model.safetensors",
22
+ "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
23
+ "model.layers.0.self_attn.qkv_proj.biases": "model.safetensors",
24
+ "model.layers.0.self_attn.qkv_proj.scales": "model.safetensors",
25
+ "model.layers.0.self_attn.qkv_proj.weight": "model.safetensors",
26
+ "model.layers.1.input_layernorm.weight": "model.safetensors",
27
+ "model.layers.1.mlp.down_proj.biases": "model.safetensors",
28
+ "model.layers.1.mlp.down_proj.scales": "model.safetensors",
29
+ "model.layers.1.mlp.down_proj.weight": "model.safetensors",
30
+ "model.layers.1.mlp.gate_up_proj.biases": "model.safetensors",
31
+ "model.layers.1.mlp.gate_up_proj.scales": "model.safetensors",
32
+ "model.layers.1.mlp.gate_up_proj.weight": "model.safetensors",
33
+ "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
34
+ "model.layers.1.self_attn.o_proj.biases": "model.safetensors",
35
+ "model.layers.1.self_attn.o_proj.scales": "model.safetensors",
36
+ "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
37
+ "model.layers.1.self_attn.qkv_proj.biases": "model.safetensors",
38
+ "model.layers.1.self_attn.qkv_proj.scales": "model.safetensors",
39
+ "model.layers.1.self_attn.qkv_proj.weight": "model.safetensors",
40
+ "model.layers.10.input_layernorm.weight": "model.safetensors",
41
+ "model.layers.10.mlp.down_proj.biases": "model.safetensors",
42
+ "model.layers.10.mlp.down_proj.scales": "model.safetensors",
43
+ "model.layers.10.mlp.down_proj.weight": "model.safetensors",
44
+ "model.layers.10.mlp.gate_up_proj.biases": "model.safetensors",
45
+ "model.layers.10.mlp.gate_up_proj.scales": "model.safetensors",
46
+ "model.layers.10.mlp.gate_up_proj.weight": "model.safetensors",
47
+ "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
48
+ "model.layers.10.self_attn.o_proj.biases": "model.safetensors",
49
+ "model.layers.10.self_attn.o_proj.scales": "model.safetensors",
50
+ "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
51
+ "model.layers.10.self_attn.qkv_proj.biases": "model.safetensors",
52
+ "model.layers.10.self_attn.qkv_proj.scales": "model.safetensors",
53
+ "model.layers.10.self_attn.qkv_proj.weight": "model.safetensors",
54
+ "model.layers.11.input_layernorm.weight": "model.safetensors",
55
+ "model.layers.11.mlp.down_proj.biases": "model.safetensors",
56
+ "model.layers.11.mlp.down_proj.scales": "model.safetensors",
57
+ "model.layers.11.mlp.down_proj.weight": "model.safetensors",
58
+ "model.layers.11.mlp.gate_up_proj.biases": "model.safetensors",
59
+ "model.layers.11.mlp.gate_up_proj.scales": "model.safetensors",
60
+ "model.layers.11.mlp.gate_up_proj.weight": "model.safetensors",
61
+ "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
62
+ "model.layers.11.self_attn.o_proj.biases": "model.safetensors",
63
+ "model.layers.11.self_attn.o_proj.scales": "model.safetensors",
64
+ "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
65
+ "model.layers.11.self_attn.qkv_proj.biases": "model.safetensors",
66
+ "model.layers.11.self_attn.qkv_proj.scales": "model.safetensors",
67
+ "model.layers.11.self_attn.qkv_proj.weight": "model.safetensors",
68
+ "model.layers.12.input_layernorm.weight": "model.safetensors",
69
+ "model.layers.12.mlp.down_proj.biases": "model.safetensors",
70
+ "model.layers.12.mlp.down_proj.scales": "model.safetensors",
71
+ "model.layers.12.mlp.down_proj.weight": "model.safetensors",
72
+ "model.layers.12.mlp.gate_up_proj.biases": "model.safetensors",
73
+ "model.layers.12.mlp.gate_up_proj.scales": "model.safetensors",
74
+ "model.layers.12.mlp.gate_up_proj.weight": "model.safetensors",
75
+ "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
76
+ "model.layers.12.self_attn.o_proj.biases": "model.safetensors",
77
+ "model.layers.12.self_attn.o_proj.scales": "model.safetensors",
78
+ "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
79
+ "model.layers.12.self_attn.qkv_proj.biases": "model.safetensors",
80
+ "model.layers.12.self_attn.qkv_proj.scales": "model.safetensors",
81
+ "model.layers.12.self_attn.qkv_proj.weight": "model.safetensors",
82
+ "model.layers.13.input_layernorm.weight": "model.safetensors",
83
+ "model.layers.13.mlp.down_proj.biases": "model.safetensors",
84
+ "model.layers.13.mlp.down_proj.scales": "model.safetensors",
85
+ "model.layers.13.mlp.down_proj.weight": "model.safetensors",
86
+ "model.layers.13.mlp.gate_up_proj.biases": "model.safetensors",
87
+ "model.layers.13.mlp.gate_up_proj.scales": "model.safetensors",
88
+ "model.layers.13.mlp.gate_up_proj.weight": "model.safetensors",
89
+ "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
90
+ "model.layers.13.self_attn.o_proj.biases": "model.safetensors",
91
+ "model.layers.13.self_attn.o_proj.scales": "model.safetensors",
92
+ "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
93
+ "model.layers.13.self_attn.qkv_proj.biases": "model.safetensors",
94
+ "model.layers.13.self_attn.qkv_proj.scales": "model.safetensors",
95
+ "model.layers.13.self_attn.qkv_proj.weight": "model.safetensors",
96
+ "model.layers.14.input_layernorm.weight": "model.safetensors",
97
+ "model.layers.14.mlp.down_proj.biases": "model.safetensors",
98
+ "model.layers.14.mlp.down_proj.scales": "model.safetensors",
99
+ "model.layers.14.mlp.down_proj.weight": "model.safetensors",
100
+ "model.layers.14.mlp.gate_up_proj.biases": "model.safetensors",
101
+ "model.layers.14.mlp.gate_up_proj.scales": "model.safetensors",
102
+ "model.layers.14.mlp.gate_up_proj.weight": "model.safetensors",
103
+ "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
104
+ "model.layers.14.self_attn.o_proj.biases": "model.safetensors",
105
+ "model.layers.14.self_attn.o_proj.scales": "model.safetensors",
106
+ "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
107
+ "model.layers.14.self_attn.qkv_proj.biases": "model.safetensors",
108
+ "model.layers.14.self_attn.qkv_proj.scales": "model.safetensors",
109
+ "model.layers.14.self_attn.qkv_proj.weight": "model.safetensors",
110
+ "model.layers.15.input_layernorm.weight": "model.safetensors",
111
+ "model.layers.15.mlp.down_proj.biases": "model.safetensors",
112
+ "model.layers.15.mlp.down_proj.scales": "model.safetensors",
113
+ "model.layers.15.mlp.down_proj.weight": "model.safetensors",
114
+ "model.layers.15.mlp.gate_up_proj.biases": "model.safetensors",
115
+ "model.layers.15.mlp.gate_up_proj.scales": "model.safetensors",
116
+ "model.layers.15.mlp.gate_up_proj.weight": "model.safetensors",
117
+ "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
118
+ "model.layers.15.self_attn.o_proj.biases": "model.safetensors",
119
+ "model.layers.15.self_attn.o_proj.scales": "model.safetensors",
120
+ "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
121
+ "model.layers.15.self_attn.qkv_proj.biases": "model.safetensors",
122
+ "model.layers.15.self_attn.qkv_proj.scales": "model.safetensors",
123
+ "model.layers.15.self_attn.qkv_proj.weight": "model.safetensors",
124
+ "model.layers.16.input_layernorm.weight": "model.safetensors",
125
+ "model.layers.16.mlp.down_proj.biases": "model.safetensors",
126
+ "model.layers.16.mlp.down_proj.scales": "model.safetensors",
127
+ "model.layers.16.mlp.down_proj.weight": "model.safetensors",
128
+ "model.layers.16.mlp.gate_up_proj.biases": "model.safetensors",
129
+ "model.layers.16.mlp.gate_up_proj.scales": "model.safetensors",
130
+ "model.layers.16.mlp.gate_up_proj.weight": "model.safetensors",
131
+ "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
132
+ "model.layers.16.self_attn.o_proj.biases": "model.safetensors",
133
+ "model.layers.16.self_attn.o_proj.scales": "model.safetensors",
134
+ "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
135
+ "model.layers.16.self_attn.qkv_proj.biases": "model.safetensors",
136
+ "model.layers.16.self_attn.qkv_proj.scales": "model.safetensors",
137
+ "model.layers.16.self_attn.qkv_proj.weight": "model.safetensors",
138
+ "model.layers.17.input_layernorm.weight": "model.safetensors",
139
+ "model.layers.17.mlp.down_proj.biases": "model.safetensors",
140
+ "model.layers.17.mlp.down_proj.scales": "model.safetensors",
141
+ "model.layers.17.mlp.down_proj.weight": "model.safetensors",
142
+ "model.layers.17.mlp.gate_up_proj.biases": "model.safetensors",
143
+ "model.layers.17.mlp.gate_up_proj.scales": "model.safetensors",
144
+ "model.layers.17.mlp.gate_up_proj.weight": "model.safetensors",
145
+ "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
146
+ "model.layers.17.self_attn.o_proj.biases": "model.safetensors",
147
+ "model.layers.17.self_attn.o_proj.scales": "model.safetensors",
148
+ "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
149
+ "model.layers.17.self_attn.qkv_proj.biases": "model.safetensors",
150
+ "model.layers.17.self_attn.qkv_proj.scales": "model.safetensors",
151
+ "model.layers.17.self_attn.qkv_proj.weight": "model.safetensors",
152
+ "model.layers.18.input_layernorm.weight": "model.safetensors",
153
+ "model.layers.18.mlp.down_proj.biases": "model.safetensors",
154
+ "model.layers.18.mlp.down_proj.scales": "model.safetensors",
155
+ "model.layers.18.mlp.down_proj.weight": "model.safetensors",
156
+ "model.layers.18.mlp.gate_up_proj.biases": "model.safetensors",
157
+ "model.layers.18.mlp.gate_up_proj.scales": "model.safetensors",
158
+ "model.layers.18.mlp.gate_up_proj.weight": "model.safetensors",
159
+ "model.layers.18.post_attention_layernorm.weight": "model.safetensors",
160
+ "model.layers.18.self_attn.o_proj.biases": "model.safetensors",
161
+ "model.layers.18.self_attn.o_proj.scales": "model.safetensors",
162
+ "model.layers.18.self_attn.o_proj.weight": "model.safetensors",
163
+ "model.layers.18.self_attn.qkv_proj.biases": "model.safetensors",
164
+ "model.layers.18.self_attn.qkv_proj.scales": "model.safetensors",
165
+ "model.layers.18.self_attn.qkv_proj.weight": "model.safetensors",
166
+ "model.layers.19.input_layernorm.weight": "model.safetensors",
167
+ "model.layers.19.mlp.down_proj.biases": "model.safetensors",
168
+ "model.layers.19.mlp.down_proj.scales": "model.safetensors",
169
+ "model.layers.19.mlp.down_proj.weight": "model.safetensors",
170
+ "model.layers.19.mlp.gate_up_proj.biases": "model.safetensors",
171
+ "model.layers.19.mlp.gate_up_proj.scales": "model.safetensors",
172
+ "model.layers.19.mlp.gate_up_proj.weight": "model.safetensors",
173
+ "model.layers.19.post_attention_layernorm.weight": "model.safetensors",
174
+ "model.layers.19.self_attn.o_proj.biases": "model.safetensors",
175
+ "model.layers.19.self_attn.o_proj.scales": "model.safetensors",
176
+ "model.layers.19.self_attn.o_proj.weight": "model.safetensors",
177
+ "model.layers.19.self_attn.qkv_proj.biases": "model.safetensors",
178
+ "model.layers.19.self_attn.qkv_proj.scales": "model.safetensors",
179
+ "model.layers.19.self_attn.qkv_proj.weight": "model.safetensors",
180
+ "model.layers.2.input_layernorm.weight": "model.safetensors",
181
+ "model.layers.2.mlp.down_proj.biases": "model.safetensors",
182
+ "model.layers.2.mlp.down_proj.scales": "model.safetensors",
183
+ "model.layers.2.mlp.down_proj.weight": "model.safetensors",
184
+ "model.layers.2.mlp.gate_up_proj.biases": "model.safetensors",
185
+ "model.layers.2.mlp.gate_up_proj.scales": "model.safetensors",
186
+ "model.layers.2.mlp.gate_up_proj.weight": "model.safetensors",
187
+ "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
188
+ "model.layers.2.self_attn.o_proj.biases": "model.safetensors",
189
+ "model.layers.2.self_attn.o_proj.scales": "model.safetensors",
190
+ "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
191
+ "model.layers.2.self_attn.qkv_proj.biases": "model.safetensors",
192
+ "model.layers.2.self_attn.qkv_proj.scales": "model.safetensors",
193
+ "model.layers.2.self_attn.qkv_proj.weight": "model.safetensors",
194
+ "model.layers.20.input_layernorm.weight": "model.safetensors",
195
+ "model.layers.20.mlp.down_proj.biases": "model.safetensors",
196
+ "model.layers.20.mlp.down_proj.scales": "model.safetensors",
197
+ "model.layers.20.mlp.down_proj.weight": "model.safetensors",
198
+ "model.layers.20.mlp.gate_up_proj.biases": "model.safetensors",
199
+ "model.layers.20.mlp.gate_up_proj.scales": "model.safetensors",
200
+ "model.layers.20.mlp.gate_up_proj.weight": "model.safetensors",
201
+ "model.layers.20.post_attention_layernorm.weight": "model.safetensors",
202
+ "model.layers.20.self_attn.o_proj.biases": "model.safetensors",
203
+ "model.layers.20.self_attn.o_proj.scales": "model.safetensors",
204
+ "model.layers.20.self_attn.o_proj.weight": "model.safetensors",
205
+ "model.layers.20.self_attn.qkv_proj.biases": "model.safetensors",
206
+ "model.layers.20.self_attn.qkv_proj.scales": "model.safetensors",
207
+ "model.layers.20.self_attn.qkv_proj.weight": "model.safetensors",
208
+ "model.layers.21.input_layernorm.weight": "model.safetensors",
209
+ "model.layers.21.mlp.down_proj.biases": "model.safetensors",
210
+ "model.layers.21.mlp.down_proj.scales": "model.safetensors",
211
+ "model.layers.21.mlp.down_proj.weight": "model.safetensors",
212
+ "model.layers.21.mlp.gate_up_proj.biases": "model.safetensors",
213
+ "model.layers.21.mlp.gate_up_proj.scales": "model.safetensors",
214
+ "model.layers.21.mlp.gate_up_proj.weight": "model.safetensors",
215
+ "model.layers.21.post_attention_layernorm.weight": "model.safetensors",
216
+ "model.layers.21.self_attn.o_proj.biases": "model.safetensors",
217
+ "model.layers.21.self_attn.o_proj.scales": "model.safetensors",
218
+ "model.layers.21.self_attn.o_proj.weight": "model.safetensors",
219
+ "model.layers.21.self_attn.qkv_proj.biases": "model.safetensors",
220
+ "model.layers.21.self_attn.qkv_proj.scales": "model.safetensors",
221
+ "model.layers.21.self_attn.qkv_proj.weight": "model.safetensors",
222
+ "model.layers.22.input_layernorm.weight": "model.safetensors",
223
+ "model.layers.22.mlp.down_proj.biases": "model.safetensors",
224
+ "model.layers.22.mlp.down_proj.scales": "model.safetensors",
225
+ "model.layers.22.mlp.down_proj.weight": "model.safetensors",
226
+ "model.layers.22.mlp.gate_up_proj.biases": "model.safetensors",
227
+ "model.layers.22.mlp.gate_up_proj.scales": "model.safetensors",
228
+ "model.layers.22.mlp.gate_up_proj.weight": "model.safetensors",
229
+ "model.layers.22.post_attention_layernorm.weight": "model.safetensors",
230
+ "model.layers.22.self_attn.o_proj.biases": "model.safetensors",
231
+ "model.layers.22.self_attn.o_proj.scales": "model.safetensors",
232
+ "model.layers.22.self_attn.o_proj.weight": "model.safetensors",
233
+ "model.layers.22.self_attn.qkv_proj.biases": "model.safetensors",
234
+ "model.layers.22.self_attn.qkv_proj.scales": "model.safetensors",
235
+ "model.layers.22.self_attn.qkv_proj.weight": "model.safetensors",
236
+ "model.layers.23.input_layernorm.weight": "model.safetensors",
237
+ "model.layers.23.mlp.down_proj.biases": "model.safetensors",
238
+ "model.layers.23.mlp.down_proj.scales": "model.safetensors",
239
+ "model.layers.23.mlp.down_proj.weight": "model.safetensors",
240
+ "model.layers.23.mlp.gate_up_proj.biases": "model.safetensors",
241
+ "model.layers.23.mlp.gate_up_proj.scales": "model.safetensors",
242
+ "model.layers.23.mlp.gate_up_proj.weight": "model.safetensors",
243
+ "model.layers.23.post_attention_layernorm.weight": "model.safetensors",
244
+ "model.layers.23.self_attn.o_proj.biases": "model.safetensors",
245
+ "model.layers.23.self_attn.o_proj.scales": "model.safetensors",
246
+ "model.layers.23.self_attn.o_proj.weight": "model.safetensors",
247
+ "model.layers.23.self_attn.qkv_proj.biases": "model.safetensors",
248
+ "model.layers.23.self_attn.qkv_proj.scales": "model.safetensors",
249
+ "model.layers.23.self_attn.qkv_proj.weight": "model.safetensors",
250
+ "model.layers.24.input_layernorm.weight": "model.safetensors",
251
+ "model.layers.24.mlp.down_proj.biases": "model.safetensors",
252
+ "model.layers.24.mlp.down_proj.scales": "model.safetensors",
253
+ "model.layers.24.mlp.down_proj.weight": "model.safetensors",
254
+ "model.layers.24.mlp.gate_up_proj.biases": "model.safetensors",
255
+ "model.layers.24.mlp.gate_up_proj.scales": "model.safetensors",
256
+ "model.layers.24.mlp.gate_up_proj.weight": "model.safetensors",
257
+ "model.layers.24.post_attention_layernorm.weight": "model.safetensors",
258
+ "model.layers.24.self_attn.o_proj.biases": "model.safetensors",
259
+ "model.layers.24.self_attn.o_proj.scales": "model.safetensors",
260
+ "model.layers.24.self_attn.o_proj.weight": "model.safetensors",
261
+ "model.layers.24.self_attn.qkv_proj.biases": "model.safetensors",
262
+ "model.layers.24.self_attn.qkv_proj.scales": "model.safetensors",
263
+ "model.layers.24.self_attn.qkv_proj.weight": "model.safetensors",
264
+ "model.layers.25.input_layernorm.weight": "model.safetensors",
265
+ "model.layers.25.mlp.down_proj.biases": "model.safetensors",
266
+ "model.layers.25.mlp.down_proj.scales": "model.safetensors",
267
+ "model.layers.25.mlp.down_proj.weight": "model.safetensors",
268
+ "model.layers.25.mlp.gate_up_proj.biases": "model.safetensors",
269
+ "model.layers.25.mlp.gate_up_proj.scales": "model.safetensors",
270
+ "model.layers.25.mlp.gate_up_proj.weight": "model.safetensors",
271
+ "model.layers.25.post_attention_layernorm.weight": "model.safetensors",
272
+ "model.layers.25.self_attn.o_proj.biases": "model.safetensors",
273
+ "model.layers.25.self_attn.o_proj.scales": "model.safetensors",
274
+ "model.layers.25.self_attn.o_proj.weight": "model.safetensors",
275
+ "model.layers.25.self_attn.qkv_proj.biases": "model.safetensors",
276
+ "model.layers.25.self_attn.qkv_proj.scales": "model.safetensors",
277
+ "model.layers.25.self_attn.qkv_proj.weight": "model.safetensors",
278
+ "model.layers.26.input_layernorm.weight": "model.safetensors",
279
+ "model.layers.26.mlp.down_proj.biases": "model.safetensors",
280
+ "model.layers.26.mlp.down_proj.scales": "model.safetensors",
281
+ "model.layers.26.mlp.down_proj.weight": "model.safetensors",
282
+ "model.layers.26.mlp.gate_up_proj.biases": "model.safetensors",
283
+ "model.layers.26.mlp.gate_up_proj.scales": "model.safetensors",
284
+ "model.layers.26.mlp.gate_up_proj.weight": "model.safetensors",
285
+ "model.layers.26.post_attention_layernorm.weight": "model.safetensors",
286
+ "model.layers.26.self_attn.o_proj.biases": "model.safetensors",
287
+ "model.layers.26.self_attn.o_proj.scales": "model.safetensors",
288
+ "model.layers.26.self_attn.o_proj.weight": "model.safetensors",
289
+ "model.layers.26.self_attn.qkv_proj.biases": "model.safetensors",
290
+ "model.layers.26.self_attn.qkv_proj.scales": "model.safetensors",
291
+ "model.layers.26.self_attn.qkv_proj.weight": "model.safetensors",
292
+ "model.layers.27.input_layernorm.weight": "model.safetensors",
293
+ "model.layers.27.mlp.down_proj.biases": "model.safetensors",
294
+ "model.layers.27.mlp.down_proj.scales": "model.safetensors",
295
+ "model.layers.27.mlp.down_proj.weight": "model.safetensors",
296
+ "model.layers.27.mlp.gate_up_proj.biases": "model.safetensors",
297
+ "model.layers.27.mlp.gate_up_proj.scales": "model.safetensors",
298
+ "model.layers.27.mlp.gate_up_proj.weight": "model.safetensors",
299
+ "model.layers.27.post_attention_layernorm.weight": "model.safetensors",
300
+ "model.layers.27.self_attn.o_proj.biases": "model.safetensors",
301
+ "model.layers.27.self_attn.o_proj.scales": "model.safetensors",
302
+ "model.layers.27.self_attn.o_proj.weight": "model.safetensors",
303
+ "model.layers.27.self_attn.qkv_proj.biases": "model.safetensors",
304
+ "model.layers.27.self_attn.qkv_proj.scales": "model.safetensors",
305
+ "model.layers.27.self_attn.qkv_proj.weight": "model.safetensors",
306
+ "model.layers.28.input_layernorm.weight": "model.safetensors",
307
+ "model.layers.28.mlp.down_proj.biases": "model.safetensors",
308
+ "model.layers.28.mlp.down_proj.scales": "model.safetensors",
309
+ "model.layers.28.mlp.down_proj.weight": "model.safetensors",
310
+ "model.layers.28.mlp.gate_up_proj.biases": "model.safetensors",
311
+ "model.layers.28.mlp.gate_up_proj.scales": "model.safetensors",
312
+ "model.layers.28.mlp.gate_up_proj.weight": "model.safetensors",
313
+ "model.layers.28.post_attention_layernorm.weight": "model.safetensors",
314
+ "model.layers.28.self_attn.o_proj.biases": "model.safetensors",
315
+ "model.layers.28.self_attn.o_proj.scales": "model.safetensors",
316
+ "model.layers.28.self_attn.o_proj.weight": "model.safetensors",
317
+ "model.layers.28.self_attn.qkv_proj.biases": "model.safetensors",
318
+ "model.layers.28.self_attn.qkv_proj.scales": "model.safetensors",
319
+ "model.layers.28.self_attn.qkv_proj.weight": "model.safetensors",
320
+ "model.layers.29.input_layernorm.weight": "model.safetensors",
321
+ "model.layers.29.mlp.down_proj.biases": "model.safetensors",
322
+ "model.layers.29.mlp.down_proj.scales": "model.safetensors",
323
+ "model.layers.29.mlp.down_proj.weight": "model.safetensors",
324
+ "model.layers.29.mlp.gate_up_proj.biases": "model.safetensors",
325
+ "model.layers.29.mlp.gate_up_proj.scales": "model.safetensors",
326
+ "model.layers.29.mlp.gate_up_proj.weight": "model.safetensors",
327
+ "model.layers.29.post_attention_layernorm.weight": "model.safetensors",
328
+ "model.layers.29.self_attn.o_proj.biases": "model.safetensors",
329
+ "model.layers.29.self_attn.o_proj.scales": "model.safetensors",
330
+ "model.layers.29.self_attn.o_proj.weight": "model.safetensors",
331
+ "model.layers.29.self_attn.qkv_proj.biases": "model.safetensors",
332
+ "model.layers.29.self_attn.qkv_proj.scales": "model.safetensors",
333
+ "model.layers.29.self_attn.qkv_proj.weight": "model.safetensors",
334
+ "model.layers.3.input_layernorm.weight": "model.safetensors",
335
+ "model.layers.3.mlp.down_proj.biases": "model.safetensors",
336
+ "model.layers.3.mlp.down_proj.scales": "model.safetensors",
337
+ "model.layers.3.mlp.down_proj.weight": "model.safetensors",
338
+ "model.layers.3.mlp.gate_up_proj.biases": "model.safetensors",
339
+ "model.layers.3.mlp.gate_up_proj.scales": "model.safetensors",
340
+ "model.layers.3.mlp.gate_up_proj.weight": "model.safetensors",
341
+ "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
342
+ "model.layers.3.self_attn.o_proj.biases": "model.safetensors",
343
+ "model.layers.3.self_attn.o_proj.scales": "model.safetensors",
344
+ "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
345
+ "model.layers.3.self_attn.qkv_proj.biases": "model.safetensors",
346
+ "model.layers.3.self_attn.qkv_proj.scales": "model.safetensors",
347
+ "model.layers.3.self_attn.qkv_proj.weight": "model.safetensors",
348
+ "model.layers.30.input_layernorm.weight": "model.safetensors",
349
+ "model.layers.30.mlp.down_proj.biases": "model.safetensors",
350
+ "model.layers.30.mlp.down_proj.scales": "model.safetensors",
351
+ "model.layers.30.mlp.down_proj.weight": "model.safetensors",
352
+ "model.layers.30.mlp.gate_up_proj.biases": "model.safetensors",
353
+ "model.layers.30.mlp.gate_up_proj.scales": "model.safetensors",
354
+ "model.layers.30.mlp.gate_up_proj.weight": "model.safetensors",
355
+ "model.layers.30.post_attention_layernorm.weight": "model.safetensors",
356
+ "model.layers.30.self_attn.o_proj.biases": "model.safetensors",
357
+ "model.layers.30.self_attn.o_proj.scales": "model.safetensors",
358
+ "model.layers.30.self_attn.o_proj.weight": "model.safetensors",
359
+ "model.layers.30.self_attn.qkv_proj.biases": "model.safetensors",
360
+ "model.layers.30.self_attn.qkv_proj.scales": "model.safetensors",
361
+ "model.layers.30.self_attn.qkv_proj.weight": "model.safetensors",
362
+ "model.layers.31.input_layernorm.weight": "model.safetensors",
363
+ "model.layers.31.mlp.down_proj.biases": "model.safetensors",
364
+ "model.layers.31.mlp.down_proj.scales": "model.safetensors",
365
+ "model.layers.31.mlp.down_proj.weight": "model.safetensors",
366
+ "model.layers.31.mlp.gate_up_proj.biases": "model.safetensors",
367
+ "model.layers.31.mlp.gate_up_proj.scales": "model.safetensors",
368
+ "model.layers.31.mlp.gate_up_proj.weight": "model.safetensors",
369
+ "model.layers.31.post_attention_layernorm.weight": "model.safetensors",
370
+ "model.layers.31.self_attn.o_proj.biases": "model.safetensors",
371
+ "model.layers.31.self_attn.o_proj.scales": "model.safetensors",
372
+ "model.layers.31.self_attn.o_proj.weight": "model.safetensors",
373
+ "model.layers.31.self_attn.qkv_proj.biases": "model.safetensors",
374
+ "model.layers.31.self_attn.qkv_proj.scales": "model.safetensors",
375
+ "model.layers.31.self_attn.qkv_proj.weight": "model.safetensors",
376
+ "model.layers.4.input_layernorm.weight": "model.safetensors",
377
+ "model.layers.4.mlp.down_proj.biases": "model.safetensors",
378
+ "model.layers.4.mlp.down_proj.scales": "model.safetensors",
379
+ "model.layers.4.mlp.down_proj.weight": "model.safetensors",
380
+ "model.layers.4.mlp.gate_up_proj.biases": "model.safetensors",
381
+ "model.layers.4.mlp.gate_up_proj.scales": "model.safetensors",
382
+ "model.layers.4.mlp.gate_up_proj.weight": "model.safetensors",
383
+ "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
384
+ "model.layers.4.self_attn.o_proj.biases": "model.safetensors",
385
+ "model.layers.4.self_attn.o_proj.scales": "model.safetensors",
386
+ "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
387
+ "model.layers.4.self_attn.qkv_proj.biases": "model.safetensors",
388
+ "model.layers.4.self_attn.qkv_proj.scales": "model.safetensors",
389
+ "model.layers.4.self_attn.qkv_proj.weight": "model.safetensors",
390
+ "model.layers.5.input_layernorm.weight": "model.safetensors",
391
+ "model.layers.5.mlp.down_proj.biases": "model.safetensors",
392
+ "model.layers.5.mlp.down_proj.scales": "model.safetensors",
393
+ "model.layers.5.mlp.down_proj.weight": "model.safetensors",
394
+ "model.layers.5.mlp.gate_up_proj.biases": "model.safetensors",
395
+ "model.layers.5.mlp.gate_up_proj.scales": "model.safetensors",
396
+ "model.layers.5.mlp.gate_up_proj.weight": "model.safetensors",
397
+ "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
398
+ "model.layers.5.self_attn.o_proj.biases": "model.safetensors",
399
+ "model.layers.5.self_attn.o_proj.scales": "model.safetensors",
400
+ "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
401
+ "model.layers.5.self_attn.qkv_proj.biases": "model.safetensors",
402
+ "model.layers.5.self_attn.qkv_proj.scales": "model.safetensors",
403
+ "model.layers.5.self_attn.qkv_proj.weight": "model.safetensors",
404
+ "model.layers.6.input_layernorm.weight": "model.safetensors",
405
+ "model.layers.6.mlp.down_proj.biases": "model.safetensors",
406
+ "model.layers.6.mlp.down_proj.scales": "model.safetensors",
407
+ "model.layers.6.mlp.down_proj.weight": "model.safetensors",
408
+ "model.layers.6.mlp.gate_up_proj.biases": "model.safetensors",
409
+ "model.layers.6.mlp.gate_up_proj.scales": "model.safetensors",
410
+ "model.layers.6.mlp.gate_up_proj.weight": "model.safetensors",
411
+ "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
412
+ "model.layers.6.self_attn.o_proj.biases": "model.safetensors",
413
+ "model.layers.6.self_attn.o_proj.scales": "model.safetensors",
414
+ "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
415
+ "model.layers.6.self_attn.qkv_proj.biases": "model.safetensors",
416
+ "model.layers.6.self_attn.qkv_proj.scales": "model.safetensors",
417
+ "model.layers.6.self_attn.qkv_proj.weight": "model.safetensors",
418
+ "model.layers.7.input_layernorm.weight": "model.safetensors",
419
+ "model.layers.7.mlp.down_proj.biases": "model.safetensors",
420
+ "model.layers.7.mlp.down_proj.scales": "model.safetensors",
421
+ "model.layers.7.mlp.down_proj.weight": "model.safetensors",
422
+ "model.layers.7.mlp.gate_up_proj.biases": "model.safetensors",
423
+ "model.layers.7.mlp.gate_up_proj.scales": "model.safetensors",
424
+ "model.layers.7.mlp.gate_up_proj.weight": "model.safetensors",
425
+ "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
426
+ "model.layers.7.self_attn.o_proj.biases": "model.safetensors",
427
+ "model.layers.7.self_attn.o_proj.scales": "model.safetensors",
428
+ "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
429
+ "model.layers.7.self_attn.qkv_proj.biases": "model.safetensors",
430
+ "model.layers.7.self_attn.qkv_proj.scales": "model.safetensors",
431
+ "model.layers.7.self_attn.qkv_proj.weight": "model.safetensors",
432
+ "model.layers.8.input_layernorm.weight": "model.safetensors",
433
+ "model.layers.8.mlp.down_proj.biases": "model.safetensors",
434
+ "model.layers.8.mlp.down_proj.scales": "model.safetensors",
435
+ "model.layers.8.mlp.down_proj.weight": "model.safetensors",
436
+ "model.layers.8.mlp.gate_up_proj.biases": "model.safetensors",
437
+ "model.layers.8.mlp.gate_up_proj.scales": "model.safetensors",
438
+ "model.layers.8.mlp.gate_up_proj.weight": "model.safetensors",
439
+ "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
440
+ "model.layers.8.self_attn.o_proj.biases": "model.safetensors",
441
+ "model.layers.8.self_attn.o_proj.scales": "model.safetensors",
442
+ "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
443
+ "model.layers.8.self_attn.qkv_proj.biases": "model.safetensors",
444
+ "model.layers.8.self_attn.qkv_proj.scales": "model.safetensors",
445
+ "model.layers.8.self_attn.qkv_proj.weight": "model.safetensors",
446
+ "model.layers.9.input_layernorm.weight": "model.safetensors",
447
+ "model.layers.9.mlp.down_proj.biases": "model.safetensors",
448
+ "model.layers.9.mlp.down_proj.scales": "model.safetensors",
449
+ "model.layers.9.mlp.down_proj.weight": "model.safetensors",
450
+ "model.layers.9.mlp.gate_up_proj.biases": "model.safetensors",
451
+ "model.layers.9.mlp.gate_up_proj.scales": "model.safetensors",
452
+ "model.layers.9.mlp.gate_up_proj.weight": "model.safetensors",
453
+ "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
454
+ "model.layers.9.self_attn.o_proj.biases": "model.safetensors",
455
+ "model.layers.9.self_attn.o_proj.scales": "model.safetensors",
456
+ "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
457
+ "model.layers.9.self_attn.qkv_proj.biases": "model.safetensors",
458
+ "model.layers.9.self_attn.qkv_proj.scales": "model.safetensors",
459
+ "model.layers.9.self_attn.qkv_proj.weight": "model.safetensors",
460
+ "model.norm.weight": "model.safetensors"
461
+ }
462
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|/inst|>"
4
+ ],
5
+ "bos_token": {
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "pad_token": {
20
+ "content": "<|endoftext|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,349 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
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": "<|step|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": true,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32003": {
54
+ "content": "<|function_output|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": true,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "32004": {
62
+ "content": "<|tag|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": true,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "32005": {
70
+ "content": "<|function_call|>",
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": "<|raw|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": true,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "32009": {
102
+ "content": "<|continue|>",
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
+ "32011": {
118
+ "content": "<|function_list|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": true,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "32012": {
126
+ "content": "<|calc|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": true,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "32013": {
134
+ "content": "<|code|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": true,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "32014": {
142
+ "content": "<|/code|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": true,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "32015": {
150
+ "content": "<|summary|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": true,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "32016": {
158
+ "content": "<|resource|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": true,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "32017": {
166
+ "content": "<|assistant_mask|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": true,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "32018": {
174
+ "content": "<|start|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": true,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "32019": {
182
+ "content": "<|message|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": true,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "32020": {
190
+ "content": "<|fim_prefix|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": true,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "32021": {
198
+ "content": "<|fim_middle|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": true,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "32022": {
206
+ "content": "<|fim_suffix|>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": true,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "32023": {
214
+ "content": "<|meta_start|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": true,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "32024": {
222
+ "content": "<|ipynb_marker|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": true,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "32025": {
230
+ "content": "<|diff_marker|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": true,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "32026": {
238
+ "content": "<|ghissue|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": true,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "32027": {
246
+ "content": "<|ghreview|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": true,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "32028": {
254
+ "content": "<|disc_start|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": true,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "32029": {
262
+ "content": "<|disc_sep|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": true,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "32030": {
270
+ "content": "<|disc_thread|><|query|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": true,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "32031": {
278
+ "content": "<|/query|>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": true,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "32032": {
286
+ "content": "<|data|>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": true,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "32033": {
294
+ "content": "<|/data|>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": true,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "32034": {
302
+ "content": "<|sys|>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": true,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "32035": {
310
+ "content": "<|/sys|>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": true,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "32036": {
318
+ "content": "<|inst|>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": true,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "32037": {
326
+ "content": "<|/inst|>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": true,
330
+ "single_word": false,
331
+ "special": true
332
+ }
333
+ },
334
+ "additional_special_tokens": [
335
+ "<|/inst|>"
336
+ ],
337
+ "bos_token": "<s>",
338
+ "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 %}",
339
+ "clean_up_tokenization_spaces": false,
340
+ "eos_token": "<|endoftext|>",
341
+ "legacy": false,
342
+ "model_max_length": 4096,
343
+ "pad_token": "<|endoftext|>",
344
+ "padding_side": "left",
345
+ "sp_model_kwargs": {},
346
+ "tokenizer_class": "LlamaTokenizer",
347
+ "unk_token": "<unk>",
348
+ "use_default_system_prompt": false
349
+ }