nithish116 commited on
Commit
ec47871
·
verified ·
1 Parent(s): 484b356

Upload model

Browse files
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "deepseek-ai/deepseek-coder-1.3b-base",
3
+ "architectures": [
4
+ "LlamaModel"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 32013,
9
+ "eos_token_id": 32014,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 5504,
15
+ "max_position_embeddings": 16384,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 24,
20
+ "num_key_value_heads": 16,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-06,
23
+ "rope_scaling": {
24
+ "factor": 4.0,
25
+ "rope_type": "linear",
26
+ "type": "linear"
27
+ },
28
+ "rope_theta": 100000,
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.48.1",
32
+ "use_cache": true,
33
+ "vocab_size": 32256
34
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:882e8f4dbc46a5a6cc8e0eac0b09631e76b4056fc55a50223b8e7bf68df724d3
3
+ size 4986378792
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d201c7a535f8af9be7f4f940e7eb0f82e65cb35efe509099eb75973ee4ea222f
3
+ size 135291512
model.safetensors.index.json ADDED
@@ -0,0 +1,225 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5121646592
4
+ },
5
+ "weight_map": {
6
+ "embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
8
+ "layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
9
+ "layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
10
+ "layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
11
+ "layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
12
+ "layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
13
+ "layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
14
+ "layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
15
+ "layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
16
+ "layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
17
+ "layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
18
+ "layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
19
+ "layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
20
+ "layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
21
+ "layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
22
+ "layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
23
+ "layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
24
+ "layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
25
+ "layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
26
+ "layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
27
+ "layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
28
+ "layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
29
+ "layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
30
+ "layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
31
+ "layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
32
+ "layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
33
+ "layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
34
+ "layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
35
+ "layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
36
+ "layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
37
+ "layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
38
+ "layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
39
+ "layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
40
+ "layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
41
+ "layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
42
+ "layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
43
+ "layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
44
+ "layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
45
+ "layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
46
+ "layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
47
+ "layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
48
+ "layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
49
+ "layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
50
+ "layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
51
+ "layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
52
+ "layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
54
+ "layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
55
+ "layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
56
+ "layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
58
+ "layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
59
+ "layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
60
+ "layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
61
+ "layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
62
+ "layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
63
+ "layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
64
+ "layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
65
+ "layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
66
+ "layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
67
+ "layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
68
+ "layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
69
+ "layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
70
+ "layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
71
+ "layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
72
+ "layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
73
+ "layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
74
+ "layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
75
+ "layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
76
+ "layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
77
+ "layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
78
+ "layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
79
+ "layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
81
+ "layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
82
+ "layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
83
+ "layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
84
+ "layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
85
+ "layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
86
+ "layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
87
+ "layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
88
+ "layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
89
+ "layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
90
+ "layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
91
+ "layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
92
+ "layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
93
+ "layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
94
+ "layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
95
+ "layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
96
+ "layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
97
+ "layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
98
+ "layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
99
+ "layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
100
+ "layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
101
+ "layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
102
+ "layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
103
+ "layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
104
+ "layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
105
+ "layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
106
+ "layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
107
+ "layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
108
+ "layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
109
+ "layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
110
+ "layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
111
+ "layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
112
+ "layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
113
+ "layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
114
+ "layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
115
+ "layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
116
+ "layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
117
+ "layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
118
+ "layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
119
+ "layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
120
+ "layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
121
+ "layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
122
+ "layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
123
+ "layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
124
+ "layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
125
+ "layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
126
+ "layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
127
+ "layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
128
+ "layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
129
+ "layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
130
+ "layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
131
+ "layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
132
+ "layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
133
+ "layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
134
+ "layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
135
+ "layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
136
+ "layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
137
+ "layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
138
+ "layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
139
+ "layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
140
+ "layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
141
+ "layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
142
+ "layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
143
+ "layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
144
+ "layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
145
+ "layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
146
+ "layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
147
+ "layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
148
+ "layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
149
+ "layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
150
+ "layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
151
+ "layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
152
+ "layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
153
+ "layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
154
+ "layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
155
+ "layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
156
+ "layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
157
+ "layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
158
+ "layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
159
+ "layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
160
+ "layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
161
+ "layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
162
+ "layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
163
+ "layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
164
+ "layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
165
+ "layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
166
+ "layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
167
+ "layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
168
+ "layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
169
+ "layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
170
+ "layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
171
+ "layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
172
+ "layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
173
+ "layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
174
+ "layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
175
+ "layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
176
+ "layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
177
+ "layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
178
+ "layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
179
+ "layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
180
+ "layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
181
+ "layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
182
+ "layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
183
+ "layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
184
+ "layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
185
+ "layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
186
+ "layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
187
+ "layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
188
+ "layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
189
+ "layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
190
+ "layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
191
+ "layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
192
+ "layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
193
+ "layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
194
+ "layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
195
+ "layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
196
+ "layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
197
+ "layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
198
+ "layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
199
+ "layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
200
+ "layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
201
+ "layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
202
+ "layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
203
+ "layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
204
+ "layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
205
+ "layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
206
+ "layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
207
+ "layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
208
+ "layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
209
+ "layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
210
+ "layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
211
+ "layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
212
+ "layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
213
+ "layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
214
+ "layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
215
+ "layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
216
+ "layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
217
+ "layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
218
+ "layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
219
+ "layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
220
+ "layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
221
+ "layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
222
+ "layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
223
+ "norm.weight": "model-00002-of-00002.safetensors"
224
+ }
225
+ }