jburtoft commited on
Commit
a873653
1 Parent(s): c5f1973

8685c8a80d7524803d0dd247a0d16f785732f2237554c7aa4ebbd826c35a242b

Browse files
Files changed (21) hide show
  1. checkpoint/config.json +26 -0
  2. checkpoint/generation_config.json +6 -0
  3. checkpoint/pytorch_model.bin/key_to_filename.json +293 -0
  4. checkpoint/pytorch_model.bin/p0.model.embed_tokens.weight +3 -0
  5. checkpoint/pytorch_model.bin/p1.model.layers.0.self_attn.q_proj.weight +3 -0
  6. checkpoint/pytorch_model.bin/p10.model.layers.1.self_attn.q_proj.weight +3 -0
  7. checkpoint/pytorch_model.bin/p100.model.layers.11.self_attn.q_proj.weight +3 -0
  8. checkpoint/pytorch_model.bin/p101.model.layers.11.self_attn.k_proj.weight +3 -0
  9. checkpoint/pytorch_model.bin/p102.model.layers.11.self_attn.v_proj.weight +3 -0
  10. checkpoint/pytorch_model.bin/p103.model.layers.11.self_attn.o_proj.weight +3 -0
  11. checkpoint/pytorch_model.bin/p104.model.layers.11.mlp.gate_proj.weight +3 -0
  12. checkpoint/pytorch_model.bin/p105.model.layers.11.mlp.up_proj.weight +3 -0
  13. checkpoint/pytorch_model.bin/p106.model.layers.11.mlp.down_proj.weight +3 -0
  14. checkpoint/pytorch_model.bin/p107.model.layers.11.input_layernorm.weight +0 -0
  15. checkpoint/pytorch_model.bin/p108.model.layers.11.post_attention_layernorm.weight +0 -0
  16. checkpoint/pytorch_model.bin/p109.model.layers.12.self_attn.q_proj.weight +3 -0
  17. checkpoint/pytorch_model.bin/p11.model.layers.1.self_attn.k_proj.weight +3 -0
  18. checkpoint/pytorch_model.bin/p110.model.layers.12.self_attn.k_proj.weight +3 -0
  19. checkpoint/pytorch_model.bin/p111.model.layers.12.self_attn.v_proj.weight +3 -0
  20. checkpoint/pytorch_model.bin/p112.model.layers.12.self_attn.o_proj.weight +3 -0
  21. checkpoint/pytorch_model.bin/p113.model.layers.12.mlp.gate_proj.weight +3 -0
checkpoint/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "CodeLlama-7b-hf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
+ "max_position_embeddings": 16384,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 32,
17
+ "pretraining_tp": 1,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_scaling": null,
20
+ "rope_theta": 1000000,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.33.2",
24
+ "use_cache": true,
25
+ "vocab_size": 32016
26
+ }
checkpoint/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.33.2"
6
+ }
checkpoint/pytorch_model.bin/key_to_filename.json ADDED
@@ -0,0 +1,293 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model.embed_tokens.weight": "p0.model.embed_tokens.weight",
3
+ "model.layers.0.self_attn.q_proj.weight": "p1.model.layers.0.self_attn.q_proj.weight",
4
+ "model.layers.0.self_attn.k_proj.weight": "p2.model.layers.0.self_attn.k_proj.weight",
5
+ "model.layers.0.self_attn.v_proj.weight": "p3.model.layers.0.self_attn.v_proj.weight",
6
+ "model.layers.0.self_attn.o_proj.weight": "p4.model.layers.0.self_attn.o_proj.weight",
7
+ "model.layers.0.mlp.gate_proj.weight": "p5.model.layers.0.mlp.gate_proj.weight",
8
+ "model.layers.0.mlp.up_proj.weight": "p6.model.layers.0.mlp.up_proj.weight",
9
+ "model.layers.0.mlp.down_proj.weight": "p7.model.layers.0.mlp.down_proj.weight",
10
+ "model.layers.0.input_layernorm.weight": "p8.model.layers.0.input_layernorm.weight",
11
+ "model.layers.0.post_attention_layernorm.weight": "p9.model.layers.0.post_attention_layernorm.weight",
12
+ "model.layers.1.self_attn.q_proj.weight": "p10.model.layers.1.self_attn.q_proj.weight",
13
+ "model.layers.1.self_attn.k_proj.weight": "p11.model.layers.1.self_attn.k_proj.weight",
14
+ "model.layers.1.self_attn.v_proj.weight": "p12.model.layers.1.self_attn.v_proj.weight",
15
+ "model.layers.1.self_attn.o_proj.weight": "p13.model.layers.1.self_attn.o_proj.weight",
16
+ "model.layers.1.mlp.gate_proj.weight": "p14.model.layers.1.mlp.gate_proj.weight",
17
+ "model.layers.1.mlp.up_proj.weight": "p15.model.layers.1.mlp.up_proj.weight",
18
+ "model.layers.1.mlp.down_proj.weight": "p16.model.layers.1.mlp.down_proj.weight",
19
+ "model.layers.1.input_layernorm.weight": "p17.model.layers.1.input_layernorm.weight",
20
+ "model.layers.1.post_attention_layernorm.weight": "p18.model.layers.1.post_attention_layernorm.weight",
21
+ "model.layers.2.self_attn.q_proj.weight": "p19.model.layers.2.self_attn.q_proj.weight",
22
+ "model.layers.2.self_attn.k_proj.weight": "p20.model.layers.2.self_attn.k_proj.weight",
23
+ "model.layers.2.self_attn.v_proj.weight": "p21.model.layers.2.self_attn.v_proj.weight",
24
+ "model.layers.2.self_attn.o_proj.weight": "p22.model.layers.2.self_attn.o_proj.weight",
25
+ "model.layers.2.mlp.gate_proj.weight": "p23.model.layers.2.mlp.gate_proj.weight",
26
+ "model.layers.2.mlp.up_proj.weight": "p24.model.layers.2.mlp.up_proj.weight",
27
+ "model.layers.2.mlp.down_proj.weight": "p25.model.layers.2.mlp.down_proj.weight",
28
+ "model.layers.2.input_layernorm.weight": "p26.model.layers.2.input_layernorm.weight",
29
+ "model.layers.2.post_attention_layernorm.weight": "p27.model.layers.2.post_attention_layernorm.weight",
30
+ "model.layers.3.self_attn.q_proj.weight": "p28.model.layers.3.self_attn.q_proj.weight",
31
+ "model.layers.3.self_attn.k_proj.weight": "p29.model.layers.3.self_attn.k_proj.weight",
32
+ "model.layers.3.self_attn.v_proj.weight": "p30.model.layers.3.self_attn.v_proj.weight",
33
+ "model.layers.3.self_attn.o_proj.weight": "p31.model.layers.3.self_attn.o_proj.weight",
34
+ "model.layers.3.mlp.gate_proj.weight": "p32.model.layers.3.mlp.gate_proj.weight",
35
+ "model.layers.3.mlp.up_proj.weight": "p33.model.layers.3.mlp.up_proj.weight",
36
+ "model.layers.3.mlp.down_proj.weight": "p34.model.layers.3.mlp.down_proj.weight",
37
+ "model.layers.3.input_layernorm.weight": "p35.model.layers.3.input_layernorm.weight",
38
+ "model.layers.3.post_attention_layernorm.weight": "p36.model.layers.3.post_attention_layernorm.weight",
39
+ "model.layers.4.self_attn.q_proj.weight": "p37.model.layers.4.self_attn.q_proj.weight",
40
+ "model.layers.4.self_attn.k_proj.weight": "p38.model.layers.4.self_attn.k_proj.weight",
41
+ "model.layers.4.self_attn.v_proj.weight": "p39.model.layers.4.self_attn.v_proj.weight",
42
+ "model.layers.4.self_attn.o_proj.weight": "p40.model.layers.4.self_attn.o_proj.weight",
43
+ "model.layers.4.mlp.gate_proj.weight": "p41.model.layers.4.mlp.gate_proj.weight",
44
+ "model.layers.4.mlp.up_proj.weight": "p42.model.layers.4.mlp.up_proj.weight",
45
+ "model.layers.4.mlp.down_proj.weight": "p43.model.layers.4.mlp.down_proj.weight",
46
+ "model.layers.4.input_layernorm.weight": "p44.model.layers.4.input_layernorm.weight",
47
+ "model.layers.4.post_attention_layernorm.weight": "p45.model.layers.4.post_attention_layernorm.weight",
48
+ "model.layers.5.self_attn.q_proj.weight": "p46.model.layers.5.self_attn.q_proj.weight",
49
+ "model.layers.5.self_attn.k_proj.weight": "p47.model.layers.5.self_attn.k_proj.weight",
50
+ "model.layers.5.self_attn.v_proj.weight": "p48.model.layers.5.self_attn.v_proj.weight",
51
+ "model.layers.5.self_attn.o_proj.weight": "p49.model.layers.5.self_attn.o_proj.weight",
52
+ "model.layers.5.mlp.gate_proj.weight": "p50.model.layers.5.mlp.gate_proj.weight",
53
+ "model.layers.5.mlp.up_proj.weight": "p51.model.layers.5.mlp.up_proj.weight",
54
+ "model.layers.5.mlp.down_proj.weight": "p52.model.layers.5.mlp.down_proj.weight",
55
+ "model.layers.5.input_layernorm.weight": "p53.model.layers.5.input_layernorm.weight",
56
+ "model.layers.5.post_attention_layernorm.weight": "p54.model.layers.5.post_attention_layernorm.weight",
57
+ "model.layers.6.self_attn.q_proj.weight": "p55.model.layers.6.self_attn.q_proj.weight",
58
+ "model.layers.6.self_attn.k_proj.weight": "p56.model.layers.6.self_attn.k_proj.weight",
59
+ "model.layers.6.self_attn.v_proj.weight": "p57.model.layers.6.self_attn.v_proj.weight",
60
+ "model.layers.6.self_attn.o_proj.weight": "p58.model.layers.6.self_attn.o_proj.weight",
61
+ "model.layers.6.mlp.gate_proj.weight": "p59.model.layers.6.mlp.gate_proj.weight",
62
+ "model.layers.6.mlp.up_proj.weight": "p60.model.layers.6.mlp.up_proj.weight",
63
+ "model.layers.6.mlp.down_proj.weight": "p61.model.layers.6.mlp.down_proj.weight",
64
+ "model.layers.6.input_layernorm.weight": "p62.model.layers.6.input_layernorm.weight",
65
+ "model.layers.6.post_attention_layernorm.weight": "p63.model.layers.6.post_attention_layernorm.weight",
66
+ "model.layers.7.self_attn.q_proj.weight": "p64.model.layers.7.self_attn.q_proj.weight",
67
+ "model.layers.7.self_attn.k_proj.weight": "p65.model.layers.7.self_attn.k_proj.weight",
68
+ "model.layers.7.self_attn.v_proj.weight": "p66.model.layers.7.self_attn.v_proj.weight",
69
+ "model.layers.7.self_attn.o_proj.weight": "p67.model.layers.7.self_attn.o_proj.weight",
70
+ "model.layers.7.mlp.gate_proj.weight": "p68.model.layers.7.mlp.gate_proj.weight",
71
+ "model.layers.7.mlp.up_proj.weight": "p69.model.layers.7.mlp.up_proj.weight",
72
+ "model.layers.7.mlp.down_proj.weight": "p70.model.layers.7.mlp.down_proj.weight",
73
+ "model.layers.7.input_layernorm.weight": "p71.model.layers.7.input_layernorm.weight",
74
+ "model.layers.7.post_attention_layernorm.weight": "p72.model.layers.7.post_attention_layernorm.weight",
75
+ "model.layers.8.self_attn.q_proj.weight": "p73.model.layers.8.self_attn.q_proj.weight",
76
+ "model.layers.8.self_attn.k_proj.weight": "p74.model.layers.8.self_attn.k_proj.weight",
77
+ "model.layers.8.self_attn.v_proj.weight": "p75.model.layers.8.self_attn.v_proj.weight",
78
+ "model.layers.8.self_attn.o_proj.weight": "p76.model.layers.8.self_attn.o_proj.weight",
79
+ "model.layers.8.mlp.gate_proj.weight": "p77.model.layers.8.mlp.gate_proj.weight",
80
+ "model.layers.8.mlp.up_proj.weight": "p78.model.layers.8.mlp.up_proj.weight",
81
+ "model.layers.8.mlp.down_proj.weight": "p79.model.layers.8.mlp.down_proj.weight",
82
+ "model.layers.8.input_layernorm.weight": "p80.model.layers.8.input_layernorm.weight",
83
+ "model.layers.8.post_attention_layernorm.weight": "p81.model.layers.8.post_attention_layernorm.weight",
84
+ "model.layers.9.self_attn.q_proj.weight": "p82.model.layers.9.self_attn.q_proj.weight",
85
+ "model.layers.9.self_attn.k_proj.weight": "p83.model.layers.9.self_attn.k_proj.weight",
86
+ "model.layers.9.self_attn.v_proj.weight": "p84.model.layers.9.self_attn.v_proj.weight",
87
+ "model.layers.9.self_attn.o_proj.weight": "p85.model.layers.9.self_attn.o_proj.weight",
88
+ "model.layers.9.mlp.gate_proj.weight": "p86.model.layers.9.mlp.gate_proj.weight",
89
+ "model.layers.9.mlp.up_proj.weight": "p87.model.layers.9.mlp.up_proj.weight",
90
+ "model.layers.9.mlp.down_proj.weight": "p88.model.layers.9.mlp.down_proj.weight",
91
+ "model.layers.9.input_layernorm.weight": "p89.model.layers.9.input_layernorm.weight",
92
+ "model.layers.9.post_attention_layernorm.weight": "p90.model.layers.9.post_attention_layernorm.weight",
93
+ "model.layers.10.self_attn.q_proj.weight": "p91.model.layers.10.self_attn.q_proj.weight",
94
+ "model.layers.10.self_attn.k_proj.weight": "p92.model.layers.10.self_attn.k_proj.weight",
95
+ "model.layers.10.self_attn.v_proj.weight": "p93.model.layers.10.self_attn.v_proj.weight",
96
+ "model.layers.10.self_attn.o_proj.weight": "p94.model.layers.10.self_attn.o_proj.weight",
97
+ "model.layers.10.mlp.gate_proj.weight": "p95.model.layers.10.mlp.gate_proj.weight",
98
+ "model.layers.10.mlp.up_proj.weight": "p96.model.layers.10.mlp.up_proj.weight",
99
+ "model.layers.10.mlp.down_proj.weight": "p97.model.layers.10.mlp.down_proj.weight",
100
+ "model.layers.10.input_layernorm.weight": "p98.model.layers.10.input_layernorm.weight",
101
+ "model.layers.10.post_attention_layernorm.weight": "p99.model.layers.10.post_attention_layernorm.weight",
102
+ "model.layers.11.self_attn.q_proj.weight": "p100.model.layers.11.self_attn.q_proj.weight",
103
+ "model.layers.11.self_attn.k_proj.weight": "p101.model.layers.11.self_attn.k_proj.weight",
104
+ "model.layers.11.self_attn.v_proj.weight": "p102.model.layers.11.self_attn.v_proj.weight",
105
+ "model.layers.11.self_attn.o_proj.weight": "p103.model.layers.11.self_attn.o_proj.weight",
106
+ "model.layers.11.mlp.gate_proj.weight": "p104.model.layers.11.mlp.gate_proj.weight",
107
+ "model.layers.11.mlp.up_proj.weight": "p105.model.layers.11.mlp.up_proj.weight",
108
+ "model.layers.11.mlp.down_proj.weight": "p106.model.layers.11.mlp.down_proj.weight",
109
+ "model.layers.11.input_layernorm.weight": "p107.model.layers.11.input_layernorm.weight",
110
+ "model.layers.11.post_attention_layernorm.weight": "p108.model.layers.11.post_attention_layernorm.weight",
111
+ "model.layers.12.self_attn.q_proj.weight": "p109.model.layers.12.self_attn.q_proj.weight",
112
+ "model.layers.12.self_attn.k_proj.weight": "p110.model.layers.12.self_attn.k_proj.weight",
113
+ "model.layers.12.self_attn.v_proj.weight": "p111.model.layers.12.self_attn.v_proj.weight",
114
+ "model.layers.12.self_attn.o_proj.weight": "p112.model.layers.12.self_attn.o_proj.weight",
115
+ "model.layers.12.mlp.gate_proj.weight": "p113.model.layers.12.mlp.gate_proj.weight",
116
+ "model.layers.12.mlp.up_proj.weight": "p114.model.layers.12.mlp.up_proj.weight",
117
+ "model.layers.12.mlp.down_proj.weight": "p115.model.layers.12.mlp.down_proj.weight",
118
+ "model.layers.12.input_layernorm.weight": "p116.model.layers.12.input_layernorm.weight",
119
+ "model.layers.12.post_attention_layernorm.weight": "p117.model.layers.12.post_attention_layernorm.weight",
120
+ "model.layers.13.self_attn.q_proj.weight": "p118.model.layers.13.self_attn.q_proj.weight",
121
+ "model.layers.13.self_attn.k_proj.weight": "p119.model.layers.13.self_attn.k_proj.weight",
122
+ "model.layers.13.self_attn.v_proj.weight": "p120.model.layers.13.self_attn.v_proj.weight",
123
+ "model.layers.13.self_attn.o_proj.weight": "p121.model.layers.13.self_attn.o_proj.weight",
124
+ "model.layers.13.mlp.gate_proj.weight": "p122.model.layers.13.mlp.gate_proj.weight",
125
+ "model.layers.13.mlp.up_proj.weight": "p123.model.layers.13.mlp.up_proj.weight",
126
+ "model.layers.13.mlp.down_proj.weight": "p124.model.layers.13.mlp.down_proj.weight",
127
+ "model.layers.13.input_layernorm.weight": "p125.model.layers.13.input_layernorm.weight",
128
+ "model.layers.13.post_attention_layernorm.weight": "p126.model.layers.13.post_attention_layernorm.weight",
129
+ "model.layers.14.self_attn.q_proj.weight": "p127.model.layers.14.self_attn.q_proj.weight",
130
+ "model.layers.14.self_attn.k_proj.weight": "p128.model.layers.14.self_attn.k_proj.weight",
131
+ "model.layers.14.self_attn.v_proj.weight": "p129.model.layers.14.self_attn.v_proj.weight",
132
+ "model.layers.14.self_attn.o_proj.weight": "p130.model.layers.14.self_attn.o_proj.weight",
133
+ "model.layers.14.mlp.gate_proj.weight": "p131.model.layers.14.mlp.gate_proj.weight",
134
+ "model.layers.14.mlp.up_proj.weight": "p132.model.layers.14.mlp.up_proj.weight",
135
+ "model.layers.14.mlp.down_proj.weight": "p133.model.layers.14.mlp.down_proj.weight",
136
+ "model.layers.14.input_layernorm.weight": "p134.model.layers.14.input_layernorm.weight",
137
+ "model.layers.14.post_attention_layernorm.weight": "p135.model.layers.14.post_attention_layernorm.weight",
138
+ "model.layers.15.self_attn.q_proj.weight": "p136.model.layers.15.self_attn.q_proj.weight",
139
+ "model.layers.15.self_attn.k_proj.weight": "p137.model.layers.15.self_attn.k_proj.weight",
140
+ "model.layers.15.self_attn.v_proj.weight": "p138.model.layers.15.self_attn.v_proj.weight",
141
+ "model.layers.15.self_attn.o_proj.weight": "p139.model.layers.15.self_attn.o_proj.weight",
142
+ "model.layers.15.mlp.gate_proj.weight": "p140.model.layers.15.mlp.gate_proj.weight",
143
+ "model.layers.15.mlp.up_proj.weight": "p141.model.layers.15.mlp.up_proj.weight",
144
+ "model.layers.15.mlp.down_proj.weight": "p142.model.layers.15.mlp.down_proj.weight",
145
+ "model.layers.15.input_layernorm.weight": "p143.model.layers.15.input_layernorm.weight",
146
+ "model.layers.15.post_attention_layernorm.weight": "p144.model.layers.15.post_attention_layernorm.weight",
147
+ "model.layers.16.self_attn.q_proj.weight": "p145.model.layers.16.self_attn.q_proj.weight",
148
+ "model.layers.16.self_attn.k_proj.weight": "p146.model.layers.16.self_attn.k_proj.weight",
149
+ "model.layers.16.self_attn.v_proj.weight": "p147.model.layers.16.self_attn.v_proj.weight",
150
+ "model.layers.16.self_attn.o_proj.weight": "p148.model.layers.16.self_attn.o_proj.weight",
151
+ "model.layers.16.mlp.gate_proj.weight": "p149.model.layers.16.mlp.gate_proj.weight",
152
+ "model.layers.16.mlp.up_proj.weight": "p150.model.layers.16.mlp.up_proj.weight",
153
+ "model.layers.16.mlp.down_proj.weight": "p151.model.layers.16.mlp.down_proj.weight",
154
+ "model.layers.16.input_layernorm.weight": "p152.model.layers.16.input_layernorm.weight",
155
+ "model.layers.16.post_attention_layernorm.weight": "p153.model.layers.16.post_attention_layernorm.weight",
156
+ "model.layers.17.self_attn.q_proj.weight": "p154.model.layers.17.self_attn.q_proj.weight",
157
+ "model.layers.17.self_attn.k_proj.weight": "p155.model.layers.17.self_attn.k_proj.weight",
158
+ "model.layers.17.self_attn.v_proj.weight": "p156.model.layers.17.self_attn.v_proj.weight",
159
+ "model.layers.17.self_attn.o_proj.weight": "p157.model.layers.17.self_attn.o_proj.weight",
160
+ "model.layers.17.mlp.gate_proj.weight": "p158.model.layers.17.mlp.gate_proj.weight",
161
+ "model.layers.17.mlp.up_proj.weight": "p159.model.layers.17.mlp.up_proj.weight",
162
+ "model.layers.17.mlp.down_proj.weight": "p160.model.layers.17.mlp.down_proj.weight",
163
+ "model.layers.17.input_layernorm.weight": "p161.model.layers.17.input_layernorm.weight",
164
+ "model.layers.17.post_attention_layernorm.weight": "p162.model.layers.17.post_attention_layernorm.weight",
165
+ "model.layers.18.self_attn.q_proj.weight": "p163.model.layers.18.self_attn.q_proj.weight",
166
+ "model.layers.18.self_attn.k_proj.weight": "p164.model.layers.18.self_attn.k_proj.weight",
167
+ "model.layers.18.self_attn.v_proj.weight": "p165.model.layers.18.self_attn.v_proj.weight",
168
+ "model.layers.18.self_attn.o_proj.weight": "p166.model.layers.18.self_attn.o_proj.weight",
169
+ "model.layers.18.mlp.gate_proj.weight": "p167.model.layers.18.mlp.gate_proj.weight",
170
+ "model.layers.18.mlp.up_proj.weight": "p168.model.layers.18.mlp.up_proj.weight",
171
+ "model.layers.18.mlp.down_proj.weight": "p169.model.layers.18.mlp.down_proj.weight",
172
+ "model.layers.18.input_layernorm.weight": "p170.model.layers.18.input_layernorm.weight",
173
+ "model.layers.18.post_attention_layernorm.weight": "p171.model.layers.18.post_attention_layernorm.weight",
174
+ "model.layers.19.self_attn.q_proj.weight": "p172.model.layers.19.self_attn.q_proj.weight",
175
+ "model.layers.19.self_attn.k_proj.weight": "p173.model.layers.19.self_attn.k_proj.weight",
176
+ "model.layers.19.self_attn.v_proj.weight": "p174.model.layers.19.self_attn.v_proj.weight",
177
+ "model.layers.19.self_attn.o_proj.weight": "p175.model.layers.19.self_attn.o_proj.weight",
178
+ "model.layers.19.mlp.gate_proj.weight": "p176.model.layers.19.mlp.gate_proj.weight",
179
+ "model.layers.19.mlp.up_proj.weight": "p177.model.layers.19.mlp.up_proj.weight",
180
+ "model.layers.19.mlp.down_proj.weight": "p178.model.layers.19.mlp.down_proj.weight",
181
+ "model.layers.19.input_layernorm.weight": "p179.model.layers.19.input_layernorm.weight",
182
+ "model.layers.19.post_attention_layernorm.weight": "p180.model.layers.19.post_attention_layernorm.weight",
183
+ "model.layers.20.self_attn.q_proj.weight": "p181.model.layers.20.self_attn.q_proj.weight",
184
+ "model.layers.20.self_attn.k_proj.weight": "p182.model.layers.20.self_attn.k_proj.weight",
185
+ "model.layers.20.self_attn.v_proj.weight": "p183.model.layers.20.self_attn.v_proj.weight",
186
+ "model.layers.20.self_attn.o_proj.weight": "p184.model.layers.20.self_attn.o_proj.weight",
187
+ "model.layers.20.mlp.gate_proj.weight": "p185.model.layers.20.mlp.gate_proj.weight",
188
+ "model.layers.20.mlp.up_proj.weight": "p186.model.layers.20.mlp.up_proj.weight",
189
+ "model.layers.20.mlp.down_proj.weight": "p187.model.layers.20.mlp.down_proj.weight",
190
+ "model.layers.20.input_layernorm.weight": "p188.model.layers.20.input_layernorm.weight",
191
+ "model.layers.20.post_attention_layernorm.weight": "p189.model.layers.20.post_attention_layernorm.weight",
192
+ "model.layers.21.self_attn.q_proj.weight": "p190.model.layers.21.self_attn.q_proj.weight",
193
+ "model.layers.21.self_attn.k_proj.weight": "p191.model.layers.21.self_attn.k_proj.weight",
194
+ "model.layers.21.self_attn.v_proj.weight": "p192.model.layers.21.self_attn.v_proj.weight",
195
+ "model.layers.21.self_attn.o_proj.weight": "p193.model.layers.21.self_attn.o_proj.weight",
196
+ "model.layers.21.mlp.gate_proj.weight": "p194.model.layers.21.mlp.gate_proj.weight",
197
+ "model.layers.21.mlp.up_proj.weight": "p195.model.layers.21.mlp.up_proj.weight",
198
+ "model.layers.21.mlp.down_proj.weight": "p196.model.layers.21.mlp.down_proj.weight",
199
+ "model.layers.21.input_layernorm.weight": "p197.model.layers.21.input_layernorm.weight",
200
+ "model.layers.21.post_attention_layernorm.weight": "p198.model.layers.21.post_attention_layernorm.weight",
201
+ "model.layers.22.self_attn.q_proj.weight": "p199.model.layers.22.self_attn.q_proj.weight",
202
+ "model.layers.22.self_attn.k_proj.weight": "p200.model.layers.22.self_attn.k_proj.weight",
203
+ "model.layers.22.self_attn.v_proj.weight": "p201.model.layers.22.self_attn.v_proj.weight",
204
+ "model.layers.22.self_attn.o_proj.weight": "p202.model.layers.22.self_attn.o_proj.weight",
205
+ "model.layers.22.mlp.gate_proj.weight": "p203.model.layers.22.mlp.gate_proj.weight",
206
+ "model.layers.22.mlp.up_proj.weight": "p204.model.layers.22.mlp.up_proj.weight",
207
+ "model.layers.22.mlp.down_proj.weight": "p205.model.layers.22.mlp.down_proj.weight",
208
+ "model.layers.22.input_layernorm.weight": "p206.model.layers.22.input_layernorm.weight",
209
+ "model.layers.22.post_attention_layernorm.weight": "p207.model.layers.22.post_attention_layernorm.weight",
210
+ "model.layers.23.self_attn.q_proj.weight": "p208.model.layers.23.self_attn.q_proj.weight",
211
+ "model.layers.23.self_attn.k_proj.weight": "p209.model.layers.23.self_attn.k_proj.weight",
212
+ "model.layers.23.self_attn.v_proj.weight": "p210.model.layers.23.self_attn.v_proj.weight",
213
+ "model.layers.23.self_attn.o_proj.weight": "p211.model.layers.23.self_attn.o_proj.weight",
214
+ "model.layers.23.mlp.gate_proj.weight": "p212.model.layers.23.mlp.gate_proj.weight",
215
+ "model.layers.23.mlp.up_proj.weight": "p213.model.layers.23.mlp.up_proj.weight",
216
+ "model.layers.23.mlp.down_proj.weight": "p214.model.layers.23.mlp.down_proj.weight",
217
+ "model.layers.23.input_layernorm.weight": "p215.model.layers.23.input_layernorm.weight",
218
+ "model.layers.23.post_attention_layernorm.weight": "p216.model.layers.23.post_attention_layernorm.weight",
219
+ "model.layers.24.self_attn.q_proj.weight": "p217.model.layers.24.self_attn.q_proj.weight",
220
+ "model.layers.24.self_attn.k_proj.weight": "p218.model.layers.24.self_attn.k_proj.weight",
221
+ "model.layers.24.self_attn.v_proj.weight": "p219.model.layers.24.self_attn.v_proj.weight",
222
+ "model.layers.24.self_attn.o_proj.weight": "p220.model.layers.24.self_attn.o_proj.weight",
223
+ "model.layers.24.mlp.gate_proj.weight": "p221.model.layers.24.mlp.gate_proj.weight",
224
+ "model.layers.24.mlp.up_proj.weight": "p222.model.layers.24.mlp.up_proj.weight",
225
+ "model.layers.24.mlp.down_proj.weight": "p223.model.layers.24.mlp.down_proj.weight",
226
+ "model.layers.24.input_layernorm.weight": "p224.model.layers.24.input_layernorm.weight",
227
+ "model.layers.24.post_attention_layernorm.weight": "p225.model.layers.24.post_attention_layernorm.weight",
228
+ "model.layers.25.self_attn.q_proj.weight": "p226.model.layers.25.self_attn.q_proj.weight",
229
+ "model.layers.25.self_attn.k_proj.weight": "p227.model.layers.25.self_attn.k_proj.weight",
230
+ "model.layers.25.self_attn.v_proj.weight": "p228.model.layers.25.self_attn.v_proj.weight",
231
+ "model.layers.25.self_attn.o_proj.weight": "p229.model.layers.25.self_attn.o_proj.weight",
232
+ "model.layers.25.mlp.gate_proj.weight": "p230.model.layers.25.mlp.gate_proj.weight",
233
+ "model.layers.25.mlp.up_proj.weight": "p231.model.layers.25.mlp.up_proj.weight",
234
+ "model.layers.25.mlp.down_proj.weight": "p232.model.layers.25.mlp.down_proj.weight",
235
+ "model.layers.25.input_layernorm.weight": "p233.model.layers.25.input_layernorm.weight",
236
+ "model.layers.25.post_attention_layernorm.weight": "p234.model.layers.25.post_attention_layernorm.weight",
237
+ "model.layers.26.self_attn.q_proj.weight": "p235.model.layers.26.self_attn.q_proj.weight",
238
+ "model.layers.26.self_attn.k_proj.weight": "p236.model.layers.26.self_attn.k_proj.weight",
239
+ "model.layers.26.self_attn.v_proj.weight": "p237.model.layers.26.self_attn.v_proj.weight",
240
+ "model.layers.26.self_attn.o_proj.weight": "p238.model.layers.26.self_attn.o_proj.weight",
241
+ "model.layers.26.mlp.gate_proj.weight": "p239.model.layers.26.mlp.gate_proj.weight",
242
+ "model.layers.26.mlp.up_proj.weight": "p240.model.layers.26.mlp.up_proj.weight",
243
+ "model.layers.26.mlp.down_proj.weight": "p241.model.layers.26.mlp.down_proj.weight",
244
+ "model.layers.26.input_layernorm.weight": "p242.model.layers.26.input_layernorm.weight",
245
+ "model.layers.26.post_attention_layernorm.weight": "p243.model.layers.26.post_attention_layernorm.weight",
246
+ "model.layers.27.self_attn.q_proj.weight": "p244.model.layers.27.self_attn.q_proj.weight",
247
+ "model.layers.27.self_attn.k_proj.weight": "p245.model.layers.27.self_attn.k_proj.weight",
248
+ "model.layers.27.self_attn.v_proj.weight": "p246.model.layers.27.self_attn.v_proj.weight",
249
+ "model.layers.27.self_attn.o_proj.weight": "p247.model.layers.27.self_attn.o_proj.weight",
250
+ "model.layers.27.mlp.gate_proj.weight": "p248.model.layers.27.mlp.gate_proj.weight",
251
+ "model.layers.27.mlp.up_proj.weight": "p249.model.layers.27.mlp.up_proj.weight",
252
+ "model.layers.27.mlp.down_proj.weight": "p250.model.layers.27.mlp.down_proj.weight",
253
+ "model.layers.27.input_layernorm.weight": "p251.model.layers.27.input_layernorm.weight",
254
+ "model.layers.27.post_attention_layernorm.weight": "p252.model.layers.27.post_attention_layernorm.weight",
255
+ "model.layers.28.self_attn.q_proj.weight": "p253.model.layers.28.self_attn.q_proj.weight",
256
+ "model.layers.28.self_attn.k_proj.weight": "p254.model.layers.28.self_attn.k_proj.weight",
257
+ "model.layers.28.self_attn.v_proj.weight": "p255.model.layers.28.self_attn.v_proj.weight",
258
+ "model.layers.28.self_attn.o_proj.weight": "p256.model.layers.28.self_attn.o_proj.weight",
259
+ "model.layers.28.mlp.gate_proj.weight": "p257.model.layers.28.mlp.gate_proj.weight",
260
+ "model.layers.28.mlp.up_proj.weight": "p258.model.layers.28.mlp.up_proj.weight",
261
+ "model.layers.28.mlp.down_proj.weight": "p259.model.layers.28.mlp.down_proj.weight",
262
+ "model.layers.28.input_layernorm.weight": "p260.model.layers.28.input_layernorm.weight",
263
+ "model.layers.28.post_attention_layernorm.weight": "p261.model.layers.28.post_attention_layernorm.weight",
264
+ "model.layers.29.self_attn.q_proj.weight": "p262.model.layers.29.self_attn.q_proj.weight",
265
+ "model.layers.29.self_attn.k_proj.weight": "p263.model.layers.29.self_attn.k_proj.weight",
266
+ "model.layers.29.self_attn.v_proj.weight": "p264.model.layers.29.self_attn.v_proj.weight",
267
+ "model.layers.29.self_attn.o_proj.weight": "p265.model.layers.29.self_attn.o_proj.weight",
268
+ "model.layers.29.mlp.gate_proj.weight": "p266.model.layers.29.mlp.gate_proj.weight",
269
+ "model.layers.29.mlp.up_proj.weight": "p267.model.layers.29.mlp.up_proj.weight",
270
+ "model.layers.29.mlp.down_proj.weight": "p268.model.layers.29.mlp.down_proj.weight",
271
+ "model.layers.29.input_layernorm.weight": "p269.model.layers.29.input_layernorm.weight",
272
+ "model.layers.29.post_attention_layernorm.weight": "p270.model.layers.29.post_attention_layernorm.weight",
273
+ "model.layers.30.self_attn.q_proj.weight": "p271.model.layers.30.self_attn.q_proj.weight",
274
+ "model.layers.30.self_attn.k_proj.weight": "p272.model.layers.30.self_attn.k_proj.weight",
275
+ "model.layers.30.self_attn.v_proj.weight": "p273.model.layers.30.self_attn.v_proj.weight",
276
+ "model.layers.30.self_attn.o_proj.weight": "p274.model.layers.30.self_attn.o_proj.weight",
277
+ "model.layers.30.mlp.gate_proj.weight": "p275.model.layers.30.mlp.gate_proj.weight",
278
+ "model.layers.30.mlp.up_proj.weight": "p276.model.layers.30.mlp.up_proj.weight",
279
+ "model.layers.30.mlp.down_proj.weight": "p277.model.layers.30.mlp.down_proj.weight",
280
+ "model.layers.30.input_layernorm.weight": "p278.model.layers.30.input_layernorm.weight",
281
+ "model.layers.30.post_attention_layernorm.weight": "p279.model.layers.30.post_attention_layernorm.weight",
282
+ "model.layers.31.self_attn.q_proj.weight": "p280.model.layers.31.self_attn.q_proj.weight",
283
+ "model.layers.31.self_attn.k_proj.weight": "p281.model.layers.31.self_attn.k_proj.weight",
284
+ "model.layers.31.self_attn.v_proj.weight": "p282.model.layers.31.self_attn.v_proj.weight",
285
+ "model.layers.31.self_attn.o_proj.weight": "p283.model.layers.31.self_attn.o_proj.weight",
286
+ "model.layers.31.mlp.gate_proj.weight": "p284.model.layers.31.mlp.gate_proj.weight",
287
+ "model.layers.31.mlp.up_proj.weight": "p285.model.layers.31.mlp.up_proj.weight",
288
+ "model.layers.31.mlp.down_proj.weight": "p286.model.layers.31.mlp.down_proj.weight",
289
+ "model.layers.31.input_layernorm.weight": "p287.model.layers.31.input_layernorm.weight",
290
+ "model.layers.31.post_attention_layernorm.weight": "p288.model.layers.31.post_attention_layernorm.weight",
291
+ "model.norm.weight": "p289.model.norm.weight",
292
+ "lm_head.weight": "p290.lm_head.weight"
293
+ }
checkpoint/pytorch_model.bin/p0.model.embed_tokens.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02880085a6e38c1508b165e4f9ef3153e547bfb05cbf8f726d19a65e7065f9d4
3
+ size 524550933
checkpoint/pytorch_model.bin/p1.model.layers.0.self_attn.q_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10221e79b0035ee43cc07cf312bdd69cf881b502237fba732cfd1e9273c3cd28
3
+ size 67109756
checkpoint/pytorch_model.bin/p10.model.layers.1.self_attn.q_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:464b67b02acbea78c2340bf435e7474eb44328ed97252bcd020ae489d39fc9d1
3
+ size 67109759
checkpoint/pytorch_model.bin/p100.model.layers.11.self_attn.q_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53538f84484c9be4371a6264905227458127bee342828873cc424521861ac16e
3
+ size 67109765
checkpoint/pytorch_model.bin/p101.model.layers.11.self_attn.k_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6540d8e6f3da9988e96d9a558cee61345de0d4d98aa799f604b614e9d5918062
3
+ size 67109765
checkpoint/pytorch_model.bin/p102.model.layers.11.self_attn.v_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:203d4ce65a1f37eda88d5a0aac20d068f149be796720fc325da53ce78a303bc9
3
+ size 67109765
checkpoint/pytorch_model.bin/p103.model.layers.11.self_attn.o_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8232d382b4395fa60a2da84e490b40c1174631aaed1bd9edeb4cfcc23c828a51
3
+ size 67109765
checkpoint/pytorch_model.bin/p104.model.layers.11.mlp.gate_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0e18b1d88233f2cfe1c32e2c6c779abb6585fc3ad075e0ede7d6e26cddf152f
3
+ size 180355964
checkpoint/pytorch_model.bin/p105.model.layers.11.mlp.up_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca7fb2bd08b7ebcdb33343dd7a6a20b2d6ca8dcd402ad0b2fc13b92f73303110
3
+ size 180355958
checkpoint/pytorch_model.bin/p106.model.layers.11.mlp.down_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be48a10aeadc6e2e2dcc80a412d0c5e93b452aeb611bf170ad65925ec7869bcc
3
+ size 180355964
checkpoint/pytorch_model.bin/p107.model.layers.11.input_layernorm.weight ADDED
Binary file (17.3 kB). View file
 
checkpoint/pytorch_model.bin/p108.model.layers.11.post_attention_layernorm.weight ADDED
Binary file (17.3 kB). View file
 
checkpoint/pytorch_model.bin/p109.model.layers.12.self_attn.q_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:303a5a7f56988887f59e760b46cc518cf78ea3116b90485a35de695c3dee6c9b
3
+ size 67109765
checkpoint/pytorch_model.bin/p11.model.layers.1.self_attn.k_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e590f20e02bf77acf94cf8abbd5be10ce3f3ef64c1cd1cdb2e6604b0c153145
3
+ size 67109759
checkpoint/pytorch_model.bin/p110.model.layers.12.self_attn.k_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9cfa098c7af7a7aa1d3728df317769ff62fa3383344816804b0dfb8ed071cca
3
+ size 67109765
checkpoint/pytorch_model.bin/p111.model.layers.12.self_attn.v_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d533dde9a22ed9dd8c7b6bed804a5e75b945de2daeae015b3f7636c9393e06de
3
+ size 67109765
checkpoint/pytorch_model.bin/p112.model.layers.12.self_attn.o_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f849dafaf04545f7a50b12cee0db9774393390a4749ba82e9f4dd37c71c4ff5
3
+ size 67109765
checkpoint/pytorch_model.bin/p113.model.layers.12.mlp.gate_proj.weight ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95ac59ea1df7d7679c9ea168b213484908a4cc658d542bf3bdb7e85e62b3f345
3
+ size 180355964