Andreas Koepf commited on
Commit
87a4569
1 Parent(s): cd457fe
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "eos_token_id": 32006,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 4096,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 11008,
11
+ "max_position_embeddings": 2048,
12
+ "model_type": "llama",
13
+ "num_attention_heads": 32,
14
+ "num_hidden_layers": 32,
15
+ "num_key_value_heads": 32,
16
+ "pad_token_id": 0,
17
+ "pretraining_tp": 1,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_scaling": null,
20
+ "tie_word_embeddings": false,
21
+ "torch_dtype": "bfloat16",
22
+ "transformers_version": "4.31.0",
23
+ "use_cache": true,
24
+ "vocab_size": 32007
25
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "eos_token_id": 32006,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.31.0"
6
+ }
pytorch_model-00001-of-00008.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe688706d5cdbd6379124c171c7c6f3c84c3763e505182d4d5cb1efe3ed7a1b8
3
+ size 1914838174
pytorch_model-00002-of-00008.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d2011ed5d037437d553c4e1560a0fc684d4414286a52eebbf5e4807e43016ca
3
+ size 1900102374
pytorch_model-00003-of-00008.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5799d91309b7392105e1f7afbdc84e079448fb4ec0dc2c07f60e6fed6ca5e54
3
+ size 1843496394
pytorch_model-00004-of-00008.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:223d9ddf59b6974a22bbcf08a948a9b8a639604a141c220a1ace47eabb25df28
3
+ size 1923187238
pytorch_model-00005-of-00008.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dddfdc359df7a3bdf6f5c8cbd2bd5e81b203ae62da2837a3283645a9c39f230
3
+ size 1900102438
pytorch_model-00006-of-00008.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57bff4043363eb7af7f5d4bd2b07d0951c4bedf1ade47290e23d35c27d15cd52
3
+ size 1843496394
pytorch_model-00007-of-00008.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a25d72a4d6068ff81c8d3bda8f8dbf5362aa76da38d803bfee7b7d85fb692aeb
3
+ size 1889640934
pytorch_model-00008-of-00008.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:721a078f52a1b5680372ef91f75c95490cad5596c3365607de69b2b91dd8f95b
3
+ size 262202757
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,330 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13476954112
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00008-of-00008.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00008.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00008.bin",
17
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
18
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
22
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
23
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
24
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
25
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00008.bin",
27
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
28
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
29
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
30
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
31
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
32
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
33
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
34
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
35
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00008.bin",
37
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
38
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
39
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
40
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
41
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
42
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
43
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
44
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
45
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00008.bin",
47
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
48
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
49
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
50
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
51
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
52
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
53
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
54
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
55
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00008.bin",
57
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
58
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
59
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
60
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
61
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
62
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
63
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
64
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
65
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00008.bin",
67
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
68
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
69
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
70
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
71
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
72
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
73
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
74
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
75
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00008.bin",
77
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
78
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
79
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
80
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
81
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
82
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
83
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
84
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
85
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00008.bin",
87
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
88
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
89
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
90
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
91
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
92
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
93
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
94
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
95
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00008.bin",
97
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
98
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
99
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
100
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
101
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
102
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
103
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
104
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
105
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00008.bin",
107
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
108
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
109
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
110
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
111
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
112
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
113
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
114
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
115
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00008.bin",
117
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
118
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
119
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
120
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
121
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
122
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
123
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
124
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
125
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00008.bin",
127
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
128
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
129
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
130
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
131
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
132
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
133
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
134
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
135
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00008.bin",
137
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
138
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
139
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
140
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
141
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
142
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
143
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
144
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
145
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00008.bin",
147
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
148
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
149
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
150
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
151
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
152
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
153
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
154
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
155
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00008.bin",
157
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
158
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
159
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
160
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
161
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
162
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
163
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
164
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
165
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00008.bin",
167
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
168
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
169
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
170
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
171
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
172
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
173
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
174
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
175
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00008.bin",
177
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
178
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
179
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
180
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
181
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
182
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
183
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
184
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
185
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00008.bin",
187
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
188
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
189
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
190
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
191
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
192
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
193
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
194
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
195
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00008.bin",
197
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
198
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
199
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
200
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
201
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
202
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
203
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
204
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
205
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00008.bin",
207
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
208
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
209
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
210
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
211
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
212
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
213
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
214
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
215
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00008.bin",
217
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
218
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
219
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
220
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
221
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
222
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
223
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
224
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
225
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00008.bin",
227
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
228
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
229
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
230
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
231
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
232
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
233
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
234
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
235
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00008.bin",
237
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
238
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
239
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
240
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
241
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
242
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
243
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
244
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
245
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00008.bin",
247
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
248
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
249
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
250
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
251
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
252
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
253
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
254
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
255
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00008.bin",
257
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
258
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
259
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
260
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
261
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
262
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
263
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
264
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
265
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00008.bin",
267
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
268
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
269
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
270
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
271
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
272
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
273
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
274
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
275
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
276
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00008.bin",
277
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
278
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
279
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
280
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
281
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
282
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
283
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
284
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
285
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
286
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00008.bin",
287
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
288
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
289
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
290
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
291
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
292
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
293
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
294
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
295
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
296
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00008.bin",
297
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
298
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
299
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
300
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
301
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
302
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
303
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
304
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
305
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
306
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00008.bin",
307
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
308
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
309
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
310
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
311
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
312
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
313
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
314
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
315
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
316
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00008.bin",
317
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
318
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
319
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
320
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
321
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
322
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
323
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
324
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
325
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
326
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00008.bin",
327
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
328
+ "model.norm.weight": "pytorch_model-00007-of-00008.bin"
329
+ }
330
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "clean_up_tokenization_spaces": false,
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "legacy": false,
20
+ "model_max_length": 1000000000000000019884624838656,
21
+ "pad_token": null,
22
+ "padding_side": "right",
23
+ "sp_model_kwargs": {},
24
+ "tokenizer_class": "LlamaTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }