Feature Extraction
Transformers
PyTorch
llama
text-generation-inference
Inference Endpoints
promise commited on
Commit
ca28f89
1 Parent(s): 5469b24
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/cpfs/user/chennuo/CN/output/deepspeed/xlingual/output_step1_llama_33b_mixV1_2e-5_bf16/",
3
+ "architectures": [
4
+ "LlamaModel"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "end_token_id": 2,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 6656,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 17920,
13
+ "max_position_embeddings": 2048,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 52,
16
+ "num_hidden_layers": 60,
17
+ "pad_token_id": 2,
18
+ "rms_norm_eps": 1e-06,
19
+ "tie_word_embeddings": false,
20
+ "torch_dtype": "float32",
21
+ "transformers_version": "4.29.2",
22
+ "use_cache": true,
23
+ "vocab_size": 32000
24
+ }
pytorch_model-00001-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0725259ca6f4dc8d74e64543db7b87cbfbac576df8faaba432b8e158b1f28865
3
+ size 9944398037
pytorch_model-00002-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad28e073621fed878932ab382abc52b59bfd746023a225b901474afce7a05ac7
3
+ size 9692215789
pytorch_model-00003-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa2b48a9262ee6ff3a24902cf45ded5db40c97611d3cf500c06507e9a44c4bba
3
+ size 9746796245
pytorch_model-00004-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27e10961b230244d5928c5752526b3f8526418d181b85504a16cfcc12770ee02
3
+ size 9992161946
pytorch_model-00005-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f9789d087b9252b5bd184864905cf1b22e2a46e547220da38226c0b3eedf13d
3
+ size 9746742439
pytorch_model-00006-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71c20b5ffcfa95c6a38413d6b3007771b8c67c28002bd4669804dbd92a42ce59
3
+ size 9869478835
pytorch_model-00007-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bd62d752b302acf655c28ac16ef2613668499d38bbdabae275129cb1ca8e5f0
3
+ size 9869425478
pytorch_model-00008-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e51b9a8917179aa3daf14b50cad31a4c4b047d5d6d5adbcad55490aed8b766b3
3
+ size 9746796245
pytorch_model-00009-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28519d2db8b7bc421a6d8e4c035906ea7bd7aca81a0dc781dbd76993583453c5
3
+ size 9992161946
pytorch_model-00010-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c6e2a2f05091ad712cc5f9ccd1aa9491595306a77640007c8ff7b0320c0cc44
3
+ size 9746742439
pytorch_model-00011-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65dacb328c26b1dc29e55d74c0055a7a36403dcc383e159af1605e5a5d4bd575
3
+ size 9869478835
pytorch_model-00012-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e9991d3b1af696e6d84d410c7e7b8d78d0fb1a24c0fbef1866e899490de8592
3
+ size 9869425478
pytorch_model-00013-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed4d5b8616c37a3d9e6cc2df24f94733dfc4d37e0c45e108acd73d95215bc24f
3
+ size 9746796245
pytorch_model-00014-of-00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac44f70ce7f07cd871aeb0fe9a2bc9692cd237a7513f88a8b0552427c00fc19f
3
+ size 1431387991
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,609 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 129263821824
4
+ },
5
+ "weight_map": {
6
+ "embed_tokens.weight": "pytorch_model-00001-of-00014.bin",
7
+ "layers.0.input_layernorm.weight": "pytorch_model-00001-of-00014.bin",
8
+ "layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin",
9
+ "layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
10
+ "layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
11
+ "layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin",
12
+ "layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
13
+ "layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
14
+ "layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
15
+ "layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00014.bin",
16
+ "layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
17
+ "layers.1.input_layernorm.weight": "pytorch_model-00001-of-00014.bin",
18
+ "layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin",
19
+ "layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
20
+ "layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
21
+ "layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin",
22
+ "layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
23
+ "layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
24
+ "layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
25
+ "layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00014.bin",
26
+ "layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
27
+ "layers.10.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
28
+ "layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
29
+ "layers.10.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
30
+ "layers.10.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
31
+ "layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
32
+ "layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
33
+ "layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
34
+ "layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
35
+ "layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00014.bin",
36
+ "layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
37
+ "layers.11.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
38
+ "layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
39
+ "layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
40
+ "layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
41
+ "layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
42
+ "layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
43
+ "layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
44
+ "layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
45
+ "layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00014.bin",
46
+ "layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
47
+ "layers.12.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
48
+ "layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
49
+ "layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
50
+ "layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
51
+ "layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
52
+ "layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
53
+ "layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
54
+ "layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
55
+ "layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00014.bin",
56
+ "layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
57
+ "layers.13.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
58
+ "layers.13.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
59
+ "layers.13.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
60
+ "layers.13.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
61
+ "layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
62
+ "layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
63
+ "layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
64
+ "layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
65
+ "layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00014.bin",
66
+ "layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
67
+ "layers.14.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
68
+ "layers.14.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
69
+ "layers.14.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
70
+ "layers.14.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
71
+ "layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
72
+ "layers.14.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
73
+ "layers.14.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
74
+ "layers.14.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
75
+ "layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00014.bin",
76
+ "layers.14.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
77
+ "layers.15.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
78
+ "layers.15.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
79
+ "layers.15.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
80
+ "layers.15.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
81
+ "layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
82
+ "layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
83
+ "layers.15.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
84
+ "layers.15.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
85
+ "layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00014.bin",
86
+ "layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
87
+ "layers.16.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
88
+ "layers.16.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
89
+ "layers.16.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
90
+ "layers.16.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
91
+ "layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
92
+ "layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
93
+ "layers.16.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
94
+ "layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
95
+ "layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00014.bin",
96
+ "layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
97
+ "layers.17.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
98
+ "layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
99
+ "layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
100
+ "layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
101
+ "layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
102
+ "layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
103
+ "layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
104
+ "layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
105
+ "layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00014.bin",
106
+ "layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
107
+ "layers.18.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
108
+ "layers.18.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
109
+ "layers.18.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
110
+ "layers.18.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
111
+ "layers.18.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
112
+ "layers.18.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
113
+ "layers.18.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
114
+ "layers.18.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
115
+ "layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00014.bin",
116
+ "layers.18.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
117
+ "layers.19.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
118
+ "layers.19.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
119
+ "layers.19.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
120
+ "layers.19.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
121
+ "layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
122
+ "layers.19.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
123
+ "layers.19.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
124
+ "layers.19.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
125
+ "layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00014.bin",
126
+ "layers.19.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
127
+ "layers.2.input_layernorm.weight": "pytorch_model-00001-of-00014.bin",
128
+ "layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin",
129
+ "layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
130
+ "layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
131
+ "layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin",
132
+ "layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
133
+ "layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
134
+ "layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
135
+ "layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00014.bin",
136
+ "layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
137
+ "layers.20.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
138
+ "layers.20.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
139
+ "layers.20.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
140
+ "layers.20.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
141
+ "layers.20.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
142
+ "layers.20.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
143
+ "layers.20.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
144
+ "layers.20.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
145
+ "layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00014.bin",
146
+ "layers.20.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
147
+ "layers.21.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
148
+ "layers.21.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
149
+ "layers.21.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
150
+ "layers.21.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
151
+ "layers.21.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
152
+ "layers.21.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
153
+ "layers.21.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
154
+ "layers.21.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
155
+ "layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00014.bin",
156
+ "layers.21.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
157
+ "layers.22.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
158
+ "layers.22.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
159
+ "layers.22.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
160
+ "layers.22.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
161
+ "layers.22.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
162
+ "layers.22.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
163
+ "layers.22.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
164
+ "layers.22.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
165
+ "layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00014.bin",
166
+ "layers.22.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
167
+ "layers.23.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
168
+ "layers.23.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
169
+ "layers.23.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
170
+ "layers.23.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
171
+ "layers.23.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
172
+ "layers.23.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
173
+ "layers.23.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
174
+ "layers.23.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
175
+ "layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00014.bin",
176
+ "layers.23.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
177
+ "layers.24.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
178
+ "layers.24.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
179
+ "layers.24.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
180
+ "layers.24.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
181
+ "layers.24.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
182
+ "layers.24.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
183
+ "layers.24.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
184
+ "layers.24.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
185
+ "layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00014.bin",
186
+ "layers.24.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
187
+ "layers.25.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
188
+ "layers.25.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
189
+ "layers.25.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
190
+ "layers.25.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
191
+ "layers.25.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
192
+ "layers.25.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
193
+ "layers.25.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
194
+ "layers.25.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
195
+ "layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00014.bin",
196
+ "layers.25.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
197
+ "layers.26.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
198
+ "layers.26.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
199
+ "layers.26.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
200
+ "layers.26.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
201
+ "layers.26.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
202
+ "layers.26.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
203
+ "layers.26.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
204
+ "layers.26.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
205
+ "layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00014.bin",
206
+ "layers.26.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
207
+ "layers.27.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
208
+ "layers.27.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
209
+ "layers.27.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
210
+ "layers.27.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
211
+ "layers.27.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
212
+ "layers.27.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
213
+ "layers.27.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
214
+ "layers.27.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
215
+ "layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00014.bin",
216
+ "layers.27.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
217
+ "layers.28.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
218
+ "layers.28.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
219
+ "layers.28.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
220
+ "layers.28.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
221
+ "layers.28.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
222
+ "layers.28.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
223
+ "layers.28.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
224
+ "layers.28.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
225
+ "layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00014.bin",
226
+ "layers.28.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
227
+ "layers.29.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
228
+ "layers.29.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
229
+ "layers.29.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
230
+ "layers.29.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
231
+ "layers.29.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
232
+ "layers.29.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
233
+ "layers.29.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
234
+ "layers.29.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
235
+ "layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00014.bin",
236
+ "layers.29.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
237
+ "layers.3.input_layernorm.weight": "pytorch_model-00001-of-00014.bin",
238
+ "layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin",
239
+ "layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
240
+ "layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
241
+ "layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin",
242
+ "layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
243
+ "layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
244
+ "layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
245
+ "layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00014.bin",
246
+ "layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
247
+ "layers.30.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
248
+ "layers.30.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
249
+ "layers.30.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
250
+ "layers.30.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
251
+ "layers.30.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
252
+ "layers.30.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
253
+ "layers.30.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
254
+ "layers.30.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
255
+ "layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00014.bin",
256
+ "layers.30.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
257
+ "layers.31.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
258
+ "layers.31.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
259
+ "layers.31.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
260
+ "layers.31.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
261
+ "layers.31.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
262
+ "layers.31.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
263
+ "layers.31.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
264
+ "layers.31.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
265
+ "layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00014.bin",
266
+ "layers.31.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
267
+ "layers.32.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
268
+ "layers.32.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
269
+ "layers.32.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
270
+ "layers.32.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
271
+ "layers.32.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
272
+ "layers.32.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
273
+ "layers.32.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
274
+ "layers.32.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
275
+ "layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00014.bin",
276
+ "layers.32.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
277
+ "layers.33.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
278
+ "layers.33.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
279
+ "layers.33.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
280
+ "layers.33.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
281
+ "layers.33.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
282
+ "layers.33.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
283
+ "layers.33.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
284
+ "layers.33.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
285
+ "layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00014.bin",
286
+ "layers.33.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
287
+ "layers.34.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
288
+ "layers.34.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
289
+ "layers.34.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
290
+ "layers.34.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
291
+ "layers.34.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
292
+ "layers.34.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
293
+ "layers.34.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
294
+ "layers.34.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
295
+ "layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00014.bin",
296
+ "layers.34.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
297
+ "layers.35.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
298
+ "layers.35.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
299
+ "layers.35.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
300
+ "layers.35.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
301
+ "layers.35.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
302
+ "layers.35.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
303
+ "layers.35.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
304
+ "layers.35.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
305
+ "layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00014.bin",
306
+ "layers.35.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
307
+ "layers.36.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
308
+ "layers.36.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
309
+ "layers.36.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
310
+ "layers.36.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
311
+ "layers.36.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
312
+ "layers.36.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
313
+ "layers.36.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
314
+ "layers.36.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
315
+ "layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00014.bin",
316
+ "layers.36.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
317
+ "layers.37.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
318
+ "layers.37.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
319
+ "layers.37.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
320
+ "layers.37.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
321
+ "layers.37.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
322
+ "layers.37.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
323
+ "layers.37.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
324
+ "layers.37.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
325
+ "layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00014.bin",
326
+ "layers.37.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
327
+ "layers.38.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
328
+ "layers.38.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
329
+ "layers.38.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
330
+ "layers.38.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
331
+ "layers.38.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
332
+ "layers.38.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
333
+ "layers.38.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
334
+ "layers.38.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
335
+ "layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00014.bin",
336
+ "layers.38.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
337
+ "layers.39.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
338
+ "layers.39.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
339
+ "layers.39.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
340
+ "layers.39.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
341
+ "layers.39.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
342
+ "layers.39.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
343
+ "layers.39.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
344
+ "layers.39.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
345
+ "layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00014.bin",
346
+ "layers.39.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
347
+ "layers.4.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
348
+ "layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
349
+ "layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
350
+ "layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
351
+ "layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
352
+ "layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
353
+ "layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
354
+ "layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
355
+ "layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00014.bin",
356
+ "layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
357
+ "layers.40.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
358
+ "layers.40.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
359
+ "layers.40.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
360
+ "layers.40.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
361
+ "layers.40.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
362
+ "layers.40.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
363
+ "layers.40.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
364
+ "layers.40.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
365
+ "layers.40.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00014.bin",
366
+ "layers.40.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
367
+ "layers.41.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
368
+ "layers.41.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
369
+ "layers.41.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
370
+ "layers.41.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
371
+ "layers.41.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
372
+ "layers.41.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
373
+ "layers.41.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
374
+ "layers.41.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
375
+ "layers.41.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00014.bin",
376
+ "layers.41.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
377
+ "layers.42.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
378
+ "layers.42.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
379
+ "layers.42.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
380
+ "layers.42.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
381
+ "layers.42.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
382
+ "layers.42.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
383
+ "layers.42.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
384
+ "layers.42.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
385
+ "layers.42.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00014.bin",
386
+ "layers.42.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
387
+ "layers.43.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
388
+ "layers.43.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
389
+ "layers.43.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
390
+ "layers.43.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
391
+ "layers.43.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
392
+ "layers.43.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
393
+ "layers.43.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
394
+ "layers.43.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
395
+ "layers.43.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00014.bin",
396
+ "layers.43.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
397
+ "layers.44.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
398
+ "layers.44.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
399
+ "layers.44.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
400
+ "layers.44.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
401
+ "layers.44.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
402
+ "layers.44.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
403
+ "layers.44.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
404
+ "layers.44.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
405
+ "layers.44.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00014.bin",
406
+ "layers.44.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
407
+ "layers.45.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
408
+ "layers.45.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
409
+ "layers.45.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
410
+ "layers.45.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
411
+ "layers.45.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
412
+ "layers.45.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
413
+ "layers.45.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
414
+ "layers.45.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
415
+ "layers.45.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00014.bin",
416
+ "layers.45.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
417
+ "layers.46.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
418
+ "layers.46.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
419
+ "layers.46.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
420
+ "layers.46.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
421
+ "layers.46.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
422
+ "layers.46.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
423
+ "layers.46.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
424
+ "layers.46.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
425
+ "layers.46.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00014.bin",
426
+ "layers.46.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
427
+ "layers.47.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
428
+ "layers.47.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
429
+ "layers.47.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
430
+ "layers.47.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
431
+ "layers.47.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
432
+ "layers.47.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
433
+ "layers.47.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
434
+ "layers.47.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
435
+ "layers.47.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00014.bin",
436
+ "layers.47.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
437
+ "layers.48.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
438
+ "layers.48.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
439
+ "layers.48.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
440
+ "layers.48.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
441
+ "layers.48.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
442
+ "layers.48.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
443
+ "layers.48.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
444
+ "layers.48.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
445
+ "layers.48.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00014.bin",
446
+ "layers.48.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
447
+ "layers.49.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
448
+ "layers.49.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
449
+ "layers.49.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
450
+ "layers.49.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
451
+ "layers.49.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
452
+ "layers.49.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
453
+ "layers.49.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
454
+ "layers.49.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
455
+ "layers.49.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00014.bin",
456
+ "layers.49.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
457
+ "layers.5.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
458
+ "layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
459
+ "layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
460
+ "layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
461
+ "layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
462
+ "layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
463
+ "layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
464
+ "layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
465
+ "layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00014.bin",
466
+ "layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
467
+ "layers.50.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
468
+ "layers.50.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
469
+ "layers.50.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
470
+ "layers.50.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
471
+ "layers.50.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
472
+ "layers.50.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
473
+ "layers.50.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
474
+ "layers.50.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
475
+ "layers.50.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00014.bin",
476
+ "layers.50.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
477
+ "layers.51.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
478
+ "layers.51.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
479
+ "layers.51.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
480
+ "layers.51.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
481
+ "layers.51.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
482
+ "layers.51.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
483
+ "layers.51.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
484
+ "layers.51.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
485
+ "layers.51.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00014.bin",
486
+ "layers.51.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
487
+ "layers.52.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
488
+ "layers.52.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
489
+ "layers.52.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
490
+ "layers.52.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
491
+ "layers.52.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
492
+ "layers.52.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
493
+ "layers.52.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
494
+ "layers.52.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
495
+ "layers.52.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00014.bin",
496
+ "layers.52.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
497
+ "layers.53.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
498
+ "layers.53.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
499
+ "layers.53.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
500
+ "layers.53.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
501
+ "layers.53.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
502
+ "layers.53.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
503
+ "layers.53.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
504
+ "layers.53.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
505
+ "layers.53.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00014.bin",
506
+ "layers.53.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
507
+ "layers.54.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
508
+ "layers.54.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
509
+ "layers.54.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
510
+ "layers.54.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
511
+ "layers.54.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
512
+ "layers.54.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
513
+ "layers.54.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
514
+ "layers.54.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
515
+ "layers.54.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00014.bin",
516
+ "layers.54.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
517
+ "layers.55.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
518
+ "layers.55.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
519
+ "layers.55.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
520
+ "layers.55.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
521
+ "layers.55.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
522
+ "layers.55.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
523
+ "layers.55.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
524
+ "layers.55.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
525
+ "layers.55.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00014.bin",
526
+ "layers.55.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
527
+ "layers.56.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
528
+ "layers.56.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
529
+ "layers.56.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
530
+ "layers.56.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
531
+ "layers.56.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
532
+ "layers.56.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
533
+ "layers.56.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
534
+ "layers.56.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
535
+ "layers.56.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00014.bin",
536
+ "layers.56.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
537
+ "layers.57.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
538
+ "layers.57.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
539
+ "layers.57.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
540
+ "layers.57.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
541
+ "layers.57.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
542
+ "layers.57.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
543
+ "layers.57.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
544
+ "layers.57.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
545
+ "layers.57.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00014.bin",
546
+ "layers.57.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
547
+ "layers.58.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
548
+ "layers.58.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
549
+ "layers.58.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
550
+ "layers.58.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
551
+ "layers.58.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
552
+ "layers.58.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
553
+ "layers.58.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
554
+ "layers.58.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
555
+ "layers.58.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00014.bin",
556
+ "layers.58.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
557
+ "layers.59.input_layernorm.weight": "pytorch_model-00014-of-00014.bin",
558
+ "layers.59.mlp.down_proj.weight": "pytorch_model-00014-of-00014.bin",
559
+ "layers.59.mlp.gate_proj.weight": "pytorch_model-00014-of-00014.bin",
560
+ "layers.59.mlp.up_proj.weight": "pytorch_model-00014-of-00014.bin",
561
+ "layers.59.post_attention_layernorm.weight": "pytorch_model-00014-of-00014.bin",
562
+ "layers.59.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
563
+ "layers.59.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
564
+ "layers.59.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
565
+ "layers.59.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00014.bin",
566
+ "layers.59.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
567
+ "layers.6.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
568
+ "layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
569
+ "layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
570
+ "layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
571
+ "layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
572
+ "layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
573
+ "layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
574
+ "layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
575
+ "layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00014.bin",
576
+ "layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
577
+ "layers.7.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
578
+ "layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
579
+ "layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
580
+ "layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
581
+ "layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
582
+ "layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
583
+ "layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
584
+ "layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
585
+ "layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00014.bin",
586
+ "layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
587
+ "layers.8.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
588
+ "layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
589
+ "layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
590
+ "layers.8.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
591
+ "layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
592
+ "layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
593
+ "layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
594
+ "layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
595
+ "layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00014.bin",
596
+ "layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
597
+ "layers.9.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
598
+ "layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
599
+ "layers.9.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
600
+ "layers.9.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
601
+ "layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
602
+ "layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
603
+ "layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
604
+ "layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
605
+ "layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00014.bin",
606
+ "layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
607
+ "norm.weight": "pytorch_model-00014-of-00014.bin"
608
+ }
609
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "fast_tokenizer": true,
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": null,
24
+ "sp_model_kwargs": {},
25
+ "tokenizer_class": "LlamaTokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }