alkahestry commited on
Commit
7d82604
1 Parent(s): 9fd1f7b

Upload 26 files

Browse files
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 6144,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 16384,
12
+ "max_position_embeddings": 32768,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 48,
15
+ "num_hidden_layers": 48,
16
+ "num_key_value_heads": 8,
17
+ "pad_token_id": 2,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_scaling": {
20
+ "factor": 3.0,
21
+ "type": "dynamic"
22
+ },
23
+ "rope_theta": 1000000,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float16",
26
+ "transformers_version": "4.29.2",
27
+ "use_cache": true,
28
+ "vocab_size": 92544
29
+ }
pytorch_model-00001-of-00021.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de091c9ed6cef5b9ce53b381a9aba47de9fe739943b24042a1728b0a2fbd636b
3
+ size 1917349982
pytorch_model-00002-of-00021.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1505c1051f23083b38514ce72e7117e84392ccc601e905bdddd3b4d5d3e489b
3
+ size 1937825864
pytorch_model-00003-of-00021.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6249d31bf96f5b13a262da402ee51e2023026cb42caa39bd1fe39f5c4d475b81
3
+ size 1963015990
pytorch_model-00004-of-00021.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eba55b3f95869441136eb5239230d38588a3ae7fb9439dd3993b055a37de44b3
3
+ size 1937825864
pytorch_model-00005-of-00021.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9015ebbe473bf85f67deeb7feb24bc0d9f930a2a0241bce5c39a552a29180b30
3
+ size 1963016042
pytorch_model-00006-of-00021.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c125da65c3a2267831328605c9c59ff21058a701390b860d3bdccdfb8057240e
3
+ size 1937825982
pytorch_model-00007-of-00021.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a998ceabec31123ca2807f573e6871c2c786d57d8dd51bf7d3b0b0dea706121c
3
+ size 1963015990
pytorch_model-00008-of-00021.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aaa53bc8944bdedd86d6fa89486d3711cc941bd88b582a766ea3e8cfe6e4f2a
3
+ size 1937825928
pytorch_model-00009-of-00021.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:833b0d849edab5dfa132ba824e0da4fd87d35838686f260b7cef585b12882573
3
+ size 1963015990
pytorch_model-00010-of-00021.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f3f2cdc230acd85cf33c09ac65c512c2356bdb59a05cd3768169f1c4deffae7
3
+ size 1937825928
pytorch_model-00011-of-00021.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b58b51366cd47ffcd8aba27c867d19f3e563111c108d535b8a61e20ff1210903
3
+ size 1963015990
pytorch_model-00012-of-00021.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f63833e4f2cc16fad92bfadca58d59ecec92e30f2520d062b6e2e9194aabd9c
3
+ size 1937825928
pytorch_model-00013-of-00021.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb8a84dc5288d9084b9d70d1d3f30d08ce8d90a3636b11167b24621de95c8382
3
+ size 1963015990
pytorch_model-00014-of-00021.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06d130a4da6ba54303919d0b616f4a13327522f3918e07ebac57079a08d3f7a1
3
+ size 1937825928
pytorch_model-00015-of-00021.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:111e01c92368793078317614cc9a7b18a6566c215c44e0b9f85a4d0461ea0f12
3
+ size 1963015990
pytorch_model-00016-of-00021.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bca7cb24352c909769c78cbc14263b49b2470def6890fd22250ebdb6c1438479
3
+ size 1937825928
pytorch_model-00017-of-00021.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09b5b9a10a96b9cb6246d38a180b229c822b83aad5a57e78d42c28c6200c96eb
3
+ size 1963015990
pytorch_model-00018-of-00021.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5e0603af18fee90d359a7be474d520836ad67bc1af9d790c8c4757902745c29
3
+ size 1937825928
pytorch_model-00019-of-00021.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c76a8996d821b2b7e34dbd470ff75445de656055f25716efe92964c40f67fb1
3
+ size 1963015990
pytorch_model-00020-of-00021.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e042107ce9de9ce42c27cbfc8823ad5a43030affd18651c421bfd06e4c6d9d4a
3
+ size 1560349568
pytorch_model-00021-of-00021.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6f55a4074f779821030063927953560a2eef93b19dbaeeac0a732262f8e15aa
3
+ size 1137182085
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,442 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 39722299392
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00021.bin",
7
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00021.bin",
8
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00021.bin",
9
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00021.bin",
10
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00021.bin",
11
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00021.bin",
12
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00021.bin",
13
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00021.bin",
14
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00021.bin",
15
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00021.bin",
16
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00021.bin",
17
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00021.bin",
18
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00021.bin",
19
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00021.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002-of-00021.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00021.bin",
22
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00021.bin",
23
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00021.bin",
24
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00021.bin",
25
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00021.bin",
26
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00021.bin",
27
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00021.bin",
28
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00021.bin",
29
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00002-of-00021.bin",
30
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00021.bin",
31
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00021.bin",
32
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00021.bin",
33
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00021.bin",
34
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00021.bin",
35
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00021.bin",
36
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00021.bin",
37
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00021.bin",
38
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00021.bin",
39
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00003-of-00021.bin",
40
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00003-of-00021.bin",
41
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00003-of-00021.bin",
42
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00003-of-00021.bin",
43
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00021.bin",
44
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00021.bin",
45
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00021.bin",
46
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00003-of-00021.bin",
47
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00003-of-00021.bin",
48
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00003-of-00021.bin",
49
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00003-of-00021.bin",
50
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00021.bin",
51
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00021.bin",
52
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00021.bin",
53
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00021.bin",
54
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00021.bin",
55
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00003-of-00021.bin",
56
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00003-of-00021.bin",
57
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00003-of-00021.bin",
58
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00003-of-00021.bin",
59
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00021.bin",
60
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00021.bin",
61
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00004-of-00021.bin",
62
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00004-of-00021.bin",
63
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00004-of-00021.bin",
64
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00004-of-00021.bin",
65
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00004-of-00021.bin",
66
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00004-of-00021.bin",
67
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00004-of-00021.bin",
68
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00004-of-00021.bin",
69
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00021.bin",
70
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00004-of-00021.bin",
71
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00004-of-00021.bin",
72
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00004-of-00021.bin",
73
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00004-of-00021.bin",
74
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00004-of-00021.bin",
75
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00004-of-00021.bin",
76
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00004-of-00021.bin",
77
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00004-of-00021.bin",
78
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00004-of-00021.bin",
79
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00004-of-00021.bin",
80
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00004-of-00021.bin",
81
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00004-of-00021.bin",
82
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00004-of-00021.bin",
83
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00004-of-00021.bin",
84
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00005-of-00021_2.bin",
85
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00005-of-00021_2.bin",
86
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00005-of-00021_2.bin",
87
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00005-of-00021_2.bin",
88
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00005-of-00021_2.bin",
89
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00005-of-00021_2.bin",
90
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00005-of-00021_2.bin",
91
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00005-of-00021_2.bin",
92
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00005-of-00021_2.bin",
93
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00005-of-00021_2.bin",
94
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00005-of-00021_2.bin",
95
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00005-of-00021_2.bin",
96
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00005-of-00021_2.bin",
97
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00005-of-00021_2.bin",
98
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00005-of-00021_2.bin",
99
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00005-of-00021_2.bin",
100
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00005-of-00021_2.bin",
101
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00005-of-00021_2.bin",
102
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00005-of-00021_2.bin",
103
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00005-of-00021_2.bin",
104
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00005-of-00021_2.bin",
105
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00005-of-00021_2.bin",
106
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00006-of-00021_2.bin",
107
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00006-of-00021_2.bin",
108
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00006-of-00021_2.bin",
109
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00006-of-00021_2.bin",
110
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00006-of-00021_2.bin",
111
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00006-of-00021_2.bin",
112
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00006-of-00021_2.bin",
113
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00006-of-00021_2.bin",
114
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00006-of-00021_2.bin",
115
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00006-of-00021_2.bin",
116
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00006-of-00021_2.bin",
117
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00006-of-00021_2.bin",
118
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00006-of-00021_2.bin",
119
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00006-of-00021_2.bin",
120
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00006-of-00021_2.bin",
121
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00006-of-00021_2.bin",
122
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00006-of-00021_2.bin",
123
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00006-of-00021_2.bin",
124
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00006-of-00021_2.bin",
125
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00006-of-00021_2.bin",
126
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00006-of-00021_2.bin",
127
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00006-of-00021_2.bin",
128
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00006-of-00021_2.bin",
129
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00007-of-00021.bin",
130
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00007-of-00021.bin",
131
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00007-of-00021.bin",
132
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00007-of-00021.bin",
133
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00007-of-00021.bin",
134
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00007-of-00021.bin",
135
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00007-of-00021.bin",
136
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00007-of-00021.bin",
137
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00007-of-00021.bin",
138
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00007-of-00021.bin",
139
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00007-of-00021.bin",
140
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00007-of-00021.bin",
141
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00007-of-00021.bin",
142
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00007-of-00021.bin",
143
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00007-of-00021.bin",
144
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00007-of-00021.bin",
145
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00007-of-00021.bin",
146
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00007-of-00021.bin",
147
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00007-of-00021.bin",
148
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00007-of-00021.bin",
149
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00007-of-00021.bin",
150
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00007-of-00021.bin",
151
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00008-of-00021.bin",
152
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00008-of-00021.bin",
153
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00008-of-00021.bin",
154
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00008-of-00021.bin",
155
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00008-of-00021.bin",
156
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00008-of-00021.bin",
157
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00008-of-00021.bin",
158
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00008-of-00021.bin",
159
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00008-of-00021.bin",
160
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00008-of-00021.bin",
161
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00008-of-00021.bin",
162
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00008-of-00021.bin",
163
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00008-of-00021.bin",
164
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00008-of-00021.bin",
165
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00008-of-00021.bin",
166
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00008-of-00021.bin",
167
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00008-of-00021.bin",
168
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00008-of-00021.bin",
169
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00008-of-00021.bin",
170
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00008-of-00021.bin",
171
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00008-of-00021.bin",
172
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00008-of-00021.bin",
173
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00008-of-00021.bin",
174
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00009-of-00021.bin",
175
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00009-of-00021.bin",
176
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00009-of-00021.bin",
177
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00009-of-00021.bin",
178
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00009-of-00021.bin",
179
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00009-of-00021.bin",
180
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00009-of-00021.bin",
181
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00009-of-00021.bin",
182
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00009-of-00021.bin",
183
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00009-of-00021.bin",
184
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00009-of-00021.bin",
185
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00009-of-00021.bin",
186
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00009-of-00021.bin",
187
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00009-of-00021.bin",
188
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00009-of-00021.bin",
189
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00009-of-00021.bin",
190
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00009-of-00021.bin",
191
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00009-of-00021.bin",
192
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00009-of-00021.bin",
193
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00009-of-00021.bin",
194
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00009-of-00021.bin",
195
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00009-of-00021.bin",
196
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00010-of-00021.bin",
197
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00010-of-00021.bin",
198
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00010-of-00021.bin",
199
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00010-of-00021.bin",
200
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00010-of-00021.bin",
201
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00010-of-00021.bin",
202
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00010-of-00021.bin",
203
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00010-of-00021.bin",
204
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00010-of-00021.bin",
205
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00010-of-00021.bin",
206
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00010-of-00021.bin",
207
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00010-of-00021.bin",
208
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00010-of-00021.bin",
209
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00010-of-00021.bin",
210
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00010-of-00021.bin",
211
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00010-of-00021.bin",
212
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00010-of-00021.bin",
213
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00010-of-00021.bin",
214
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00010-of-00021.bin",
215
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00010-of-00021.bin",
216
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00010-of-00021.bin",
217
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00010-of-00021.bin",
218
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00010-of-00021.bin",
219
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00011-of-00021.bin",
220
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00011-of-00021.bin",
221
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00011-of-00021.bin",
222
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00011-of-00021.bin",
223
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00011-of-00021.bin",
224
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00011-of-00021.bin",
225
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00011-of-00021.bin",
226
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00011-of-00021.bin",
227
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00011-of-00021.bin",
228
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00011-of-00021.bin",
229
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00011-of-00021.bin",
230
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00011-of-00021.bin",
231
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00011-of-00021.bin",
232
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00011-of-00021.bin",
233
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00011-of-00021.bin",
234
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00011-of-00021.bin",
235
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00011-of-00021.bin",
236
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00011-of-00021.bin",
237
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00011-of-00021.bin",
238
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00011-of-00021.bin",
239
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00011-of-00021.bin",
240
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00011-of-00021.bin",
241
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00012-of-00021.bin",
242
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00012-of-00021.bin",
243
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00012-of-00021.bin",
244
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00012-of-00021.bin",
245
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00012-of-00021.bin",
246
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00012-of-00021.bin",
247
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00012-of-00021.bin",
248
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00012-of-00021.bin",
249
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00012-of-00021.bin",
250
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00012-of-00021.bin",
251
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00012-of-00021.bin",
252
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00012-of-00021.bin",
253
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00012-of-00021.bin",
254
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00012-of-00021.bin",
255
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00012-of-00021.bin",
256
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00012-of-00021.bin",
257
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00012-of-00021.bin",
258
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00012-of-00021.bin",
259
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00012-of-00021.bin",
260
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00012-of-00021.bin",
261
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00012-of-00021.bin",
262
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00012-of-00021.bin",
263
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00012-of-00021.bin",
264
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00013-of-00021.bin",
265
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00013-of-00021.bin",
266
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00013-of-00021.bin",
267
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00013-of-00021.bin",
268
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00013-of-00021.bin",
269
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00013-of-00021.bin",
270
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00013-of-00021.bin",
271
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00013-of-00021.bin",
272
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00013-of-00021.bin",
273
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00013-of-00021.bin",
274
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00013-of-00021.bin",
275
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00013-of-00021.bin",
276
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00013-of-00021.bin",
277
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00013-of-00021.bin",
278
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00013-of-00021.bin",
279
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00013-of-00021.bin",
280
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00013-of-00021.bin",
281
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00013-of-00021.bin",
282
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00013-of-00021.bin",
283
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00013-of-00021.bin",
284
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00013-of-00021.bin",
285
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00013-of-00021.bin",
286
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00014-of-00021.bin",
287
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00014-of-00021.bin",
288
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00014-of-00021.bin",
289
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00014-of-00021.bin",
290
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00014-of-00021.bin",
291
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00014-of-00021.bin",
292
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00014-of-00021.bin",
293
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00014-of-00021.bin",
294
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00014-of-00021.bin",
295
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00014-of-00021.bin",
296
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00014-of-00021.bin",
297
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00014-of-00021.bin",
298
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00014-of-00021.bin",
299
+ "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00014-of-00021.bin",
300
+ "model.layers.32.mlp.up_proj.weight": "pytorch_model-00014-of-00021.bin",
301
+ "model.layers.32.mlp.down_proj.weight": "pytorch_model-00014-of-00021.bin",
302
+ "model.layers.32.input_layernorm.weight": "pytorch_model-00014-of-00021.bin",
303
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00014-of-00021.bin",
304
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00014-of-00021.bin",
305
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00014-of-00021.bin",
306
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00014-of-00021.bin",
307
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00014-of-00021.bin",
308
+ "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00014-of-00021.bin",
309
+ "model.layers.33.mlp.up_proj.weight": "pytorch_model-00015-of-00021.bin",
310
+ "model.layers.33.mlp.down_proj.weight": "pytorch_model-00015-of-00021.bin",
311
+ "model.layers.33.input_layernorm.weight": "pytorch_model-00015-of-00021.bin",
312
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00015-of-00021.bin",
313
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00015-of-00021.bin",
314
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00015-of-00021.bin",
315
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00015-of-00021.bin",
316
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00015-of-00021.bin",
317
+ "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00015-of-00021.bin",
318
+ "model.layers.34.mlp.up_proj.weight": "pytorch_model-00015-of-00021.bin",
319
+ "model.layers.34.mlp.down_proj.weight": "pytorch_model-00015-of-00021.bin",
320
+ "model.layers.34.input_layernorm.weight": "pytorch_model-00015-of-00021.bin",
321
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00015-of-00021.bin",
322
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00015-of-00021.bin",
323
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00015-of-00021.bin",
324
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00015-of-00021.bin",
325
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00015-of-00021.bin",
326
+ "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00015-of-00021.bin",
327
+ "model.layers.35.mlp.up_proj.weight": "pytorch_model-00015-of-00021.bin",
328
+ "model.layers.35.mlp.down_proj.weight": "pytorch_model-00015-of-00021.bin",
329
+ "model.layers.35.input_layernorm.weight": "pytorch_model-00015-of-00021.bin",
330
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00015-of-00021.bin",
331
+ "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00016-of-00021.bin",
332
+ "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00016-of-00021.bin",
333
+ "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00016-of-00021.bin",
334
+ "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00016-of-00021.bin",
335
+ "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00016-of-00021.bin",
336
+ "model.layers.36.mlp.up_proj.weight": "pytorch_model-00016-of-00021.bin",
337
+ "model.layers.36.mlp.down_proj.weight": "pytorch_model-00016-of-00021.bin",
338
+ "model.layers.36.input_layernorm.weight": "pytorch_model-00016-of-00021.bin",
339
+ "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00016-of-00021.bin",
340
+ "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00016-of-00021.bin",
341
+ "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00016-of-00021.bin",
342
+ "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00016-of-00021.bin",
343
+ "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00016-of-00021.bin",
344
+ "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00016-of-00021.bin",
345
+ "model.layers.37.mlp.up_proj.weight": "pytorch_model-00016-of-00021.bin",
346
+ "model.layers.37.mlp.down_proj.weight": "pytorch_model-00016-of-00021.bin",
347
+ "model.layers.37.input_layernorm.weight": "pytorch_model-00016-of-00021.bin",
348
+ "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00016-of-00021.bin",
349
+ "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00016-of-00021.bin",
350
+ "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00016-of-00021.bin",
351
+ "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00016-of-00021.bin",
352
+ "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00016-of-00021.bin",
353
+ "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00016-of-00021.bin",
354
+ "model.layers.38.mlp.up_proj.weight": "pytorch_model-00017-of-00021.bin",
355
+ "model.layers.38.mlp.down_proj.weight": "pytorch_model-00017-of-00021.bin",
356
+ "model.layers.38.input_layernorm.weight": "pytorch_model-00017-of-00021.bin",
357
+ "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00017-of-00021.bin",
358
+ "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00017-of-00021.bin",
359
+ "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00017-of-00021.bin",
360
+ "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00017-of-00021.bin",
361
+ "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00017-of-00021.bin",
362
+ "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00017-of-00021.bin",
363
+ "model.layers.39.mlp.up_proj.weight": "pytorch_model-00017-of-00021.bin",
364
+ "model.layers.39.mlp.down_proj.weight": "pytorch_model-00017-of-00021.bin",
365
+ "model.layers.39.input_layernorm.weight": "pytorch_model-00017-of-00021.bin",
366
+ "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00017-of-00021.bin",
367
+ "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00017-of-00021.bin",
368
+ "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00017-of-00021.bin",
369
+ "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00017-of-00021.bin",
370
+ "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00017-of-00021.bin",
371
+ "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00017-of-00021.bin",
372
+ "model.layers.40.mlp.up_proj.weight": "pytorch_model-00017-of-00021.bin",
373
+ "model.layers.40.mlp.down_proj.weight": "pytorch_model-00017-of-00021.bin",
374
+ "model.layers.40.input_layernorm.weight": "pytorch_model-00017-of-00021.bin",
375
+ "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00017-of-00021.bin",
376
+ "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00018-of-00021.bin",
377
+ "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00018-of-00021.bin",
378
+ "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00018-of-00021.bin",
379
+ "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00018-of-00021.bin",
380
+ "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00018-of-00021.bin",
381
+ "model.layers.41.mlp.up_proj.weight": "pytorch_model-00018-of-00021.bin",
382
+ "model.layers.41.mlp.down_proj.weight": "pytorch_model-00018-of-00021.bin",
383
+ "model.layers.41.input_layernorm.weight": "pytorch_model-00018-of-00021.bin",
384
+ "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00018-of-00021.bin",
385
+ "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00018-of-00021.bin",
386
+ "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00018-of-00021.bin",
387
+ "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00018-of-00021.bin",
388
+ "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00018-of-00021.bin",
389
+ "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00018-of-00021.bin",
390
+ "model.layers.42.mlp.up_proj.weight": "pytorch_model-00018-of-00021.bin",
391
+ "model.layers.42.mlp.down_proj.weight": "pytorch_model-00018-of-00021.bin",
392
+ "model.layers.42.input_layernorm.weight": "pytorch_model-00018-of-00021.bin",
393
+ "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00018-of-00021.bin",
394
+ "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00018-of-00021.bin",
395
+ "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00018-of-00021.bin",
396
+ "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00018-of-00021.bin",
397
+ "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00018-of-00021.bin",
398
+ "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00018-of-00021.bin",
399
+ "model.layers.43.mlp.up_proj.weight": "pytorch_model-00019-of-00021.bin",
400
+ "model.layers.43.mlp.down_proj.weight": "pytorch_model-00019-of-00021.bin",
401
+ "model.layers.43.input_layernorm.weight": "pytorch_model-00019-of-00021.bin",
402
+ "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00019-of-00021.bin",
403
+ "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00019-of-00021.bin",
404
+ "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00019-of-00021.bin",
405
+ "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00019-of-00021.bin",
406
+ "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00019-of-00021.bin",
407
+ "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00019-of-00021.bin",
408
+ "model.layers.44.mlp.up_proj.weight": "pytorch_model-00019-of-00021.bin",
409
+ "model.layers.44.mlp.down_proj.weight": "pytorch_model-00019-of-00021.bin",
410
+ "model.layers.44.input_layernorm.weight": "pytorch_model-00019-of-00021.bin",
411
+ "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00019-of-00021.bin",
412
+ "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00019-of-00021.bin",
413
+ "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00019-of-00021.bin",
414
+ "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00019-of-00021.bin",
415
+ "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00019-of-00021.bin",
416
+ "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00019-of-00021.bin",
417
+ "model.layers.45.mlp.up_proj.weight": "pytorch_model-00019-of-00021.bin",
418
+ "model.layers.45.mlp.down_proj.weight": "pytorch_model-00019-of-00021.bin",
419
+ "model.layers.45.input_layernorm.weight": "pytorch_model-00019-of-00021.bin",
420
+ "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00019-of-00021.bin",
421
+ "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00020-of-00021.bin",
422
+ "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00020-of-00021.bin",
423
+ "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00020-of-00021.bin",
424
+ "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00020-of-00021.bin",
425
+ "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00020-of-00021.bin",
426
+ "model.layers.46.mlp.up_proj.weight": "pytorch_model-00020-of-00021.bin",
427
+ "model.layers.46.mlp.down_proj.weight": "pytorch_model-00020-of-00021.bin",
428
+ "model.layers.46.input_layernorm.weight": "pytorch_model-00020-of-00021.bin",
429
+ "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00020-of-00021.bin",
430
+ "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00020-of-00021.bin",
431
+ "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00020-of-00021.bin",
432
+ "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00020-of-00021.bin",
433
+ "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00020-of-00021.bin",
434
+ "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00020-of-00021.bin",
435
+ "model.layers.47.mlp.up_proj.weight": "pytorch_model-00020-of-00021.bin",
436
+ "model.layers.47.mlp.down_proj.weight": "pytorch_model-00020-of-00021.bin",
437
+ "model.layers.47.input_layernorm.weight": "pytorch_model-00020-of-00021.bin",
438
+ "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00020-of-00021.bin",
439
+ "model.norm.weight": "pytorch_model-00020-of-00021.bin",
440
+ "lm_head.weight": "pytorch_model-00021-of-00021.bin"
441
+ }
442
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "</s>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f868398fc4e05ee1e8aeba95ddf18ddcc45b8bce55d5093bead5bbf80429b48b
3
+ size 1477754
tokenizer_config.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "92538": {
30
+ "content": "<|plugin|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "92539": {
38
+ "content": "<|interpreter|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "92540": {
46
+ "content": "<|action_end|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "92541": {
54
+ "content": "<|action_start|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "92542": {
62
+ "content": "<|im_end|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "92543": {
70
+ "content": "<|im_start|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ }
77
+ },
78
+ "bos_token": {
79
+ "__type": "AddedToken",
80
+ "content": "<s>",
81
+ "lstrip": false,
82
+ "normalized": true,
83
+ "rstrip": false,
84
+ "single_word": false
85
+ },
86
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
87
+ "clean_up_tokenization_spaces": false,
88
+ "eos_token": {
89
+ "__type": "AddedToken",
90
+ "content": "</s>",
91
+ "lstrip": false,
92
+ "normalized": true,
93
+ "rstrip": false,
94
+ "single_word": false
95
+ },
96
+ "model_max_length": 1000000000000000019884624838656,
97
+ "pad_token": {
98
+ "__type": "AddedToken",
99
+ "content": "</s>",
100
+ "lstrip": false,
101
+ "normalized": true,
102
+ "rstrip": false,
103
+ "single_word": false
104
+ },
105
+ "sp_model_kwargs": {},
106
+ "tokenizer_class": "LlamaTokenizer",
107
+ "unk_token": {
108
+ "__type": "AddedToken",
109
+ "content": "<unk>",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false
114
+ }
115
+ }