stojchet commited on
Commit
298e28b
1 Parent(s): 63b7def

Training in progress, step 56

Browse files
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "deepseek-ai/deepseek-coder-1.3b-base",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 32013,
9
+ "eos_token_id": 32014,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5504,
14
+ "max_position_embeddings": 16384,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "num_key_value_heads": 16,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-06,
22
+ "rope_scaling": {
23
+ "factor": 4.0,
24
+ "type": "linear"
25
+ },
26
+ "rope_theta": 100000,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.43.0.dev0",
30
+ "use_cache": true,
31
+ "vocab_size": 32256
32
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71166f44124977ccd0af1d20130ebe770ebe0ca0f4be3ed4a840884c03b15b38
3
+ size 4986380064
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adb5c1fe85b766e1e215f4e652b52c1e7887d37f7b493ea3043212bf4eb1df1e
3
+ size 399532808
model.safetensors.index.json ADDED
@@ -0,0 +1,226 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5385887744
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
182
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
184
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
186
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
188
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
190
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
194
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
196
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
202
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
206
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
208
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
210
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
212
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
224
+ "model.norm.weight": "model-00002-of-00002.safetensors"
225
+ }
226
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin▁of▁sentence|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end▁of▁sentence|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end▁of▁sentence|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,193 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "32000": {
7
+ "content": "õ",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": false
13
+ },
14
+ "32001": {
15
+ "content": "÷",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": false
21
+ },
22
+ "32002": {
23
+ "content": "Á",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32003": {
31
+ "content": "ý",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "32004": {
39
+ "content": "À",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "32005": {
47
+ "content": "ÿ",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "32006": {
55
+ "content": "ø",
56
+ "lstrip": false,
57
+ "normalized": true,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "32007": {
63
+ "content": "ú",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "32008": {
71
+ "content": "þ",
72
+ "lstrip": false,
73
+ "normalized": true,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "32009": {
79
+ "content": "ü",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "32010": {
87
+ "content": "ù",
88
+ "lstrip": false,
89
+ "normalized": true,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "32011": {
95
+ "content": "ö",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "32012": {
103
+ "content": "û",
104
+ "lstrip": false,
105
+ "normalized": true,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "32013": {
111
+ "content": "<|begin▁of▁sentence|>",
112
+ "lstrip": false,
113
+ "normalized": true,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "32014": {
119
+ "content": "<|end▁of▁sentence|>",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": true
125
+ },
126
+ "32015": {
127
+ "content": "<|fim▁hole|>",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "32016": {
135
+ "content": "<|fim▁begin|>",
136
+ "lstrip": false,
137
+ "normalized": true,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "32017": {
143
+ "content": "<|fim▁end|>",
144
+ "lstrip": false,
145
+ "normalized": true,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "32018": {
151
+ "content": "<pad>",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "32019": {
159
+ "content": "<|User|>",
160
+ "lstrip": false,
161
+ "normalized": true,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "32020": {
167
+ "content": "<|Assistant|>",
168
+ "lstrip": false,
169
+ "normalized": true,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "32021": {
175
+ "content": "<|EOT|>",
176
+ "lstrip": false,
177
+ "normalized": true,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ }
182
+ },
183
+ "bos_token": "<|begin▁of▁sentence|>",
184
+ "clean_up_tokenization_spaces": false,
185
+ "eos_token": "<|end▁of▁sentence|>",
186
+ "legacy": true,
187
+ "model_max_length": 16384,
188
+ "pad_token": "<|end▁of▁sentence|>",
189
+ "sp_model_kwargs": {},
190
+ "tokenizer_class": "LlamaTokenizer",
191
+ "unk_token": null,
192
+ "use_default_system_prompt": false
193
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0112276fa380038be4d58db186b3487f3bc037663f68d26075e0f91ae91aa95b
3
+ size 5240