jondurbin commited on
Commit
1d8ca34
1 Parent(s): 9a3051b

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/workspace/airoboros-uncensored-13b",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 5120,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 13824,
12
+ "max_position_embeddings": 2048,
13
+ "max_sequence_length": 2048,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 40,
16
+ "num_hidden_layers": 40,
17
+ "pad_token_id": 0,
18
+ "rms_norm_eps": 1e-06,
19
+ "tie_word_embeddings": false,
20
+ "torch_dtype": "float32",
21
+ "transformers_version": "4.28.1",
22
+ "use_cache": false,
23
+ "vocab_size": 32000
24
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.28.1"
7
+ }
pytorch_model-00001-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39a2a1d61ccb8bfc83ec95c692ed8044a7c6e0e4e0c9c2f3fa69a45903c6a10a
3
+ size 9956543883
pytorch_model-00002-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85522380b06b94e1ed8b969b671aea2d6da22e7bff2b02cb3ee1b6cdf99cc4d6
3
+ size 9940856385
pytorch_model-00003-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ee5ba0e5e4423c7ccd20f392e4c89c40be8f421ef802a023e7a8197745a650c
3
+ size 9940856943
pytorch_model-00004-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:054257127ba7f20f6e29cd80e50e1c6fbea783a4a03a66172a902734ee8482d9
3
+ size 9867415289
pytorch_model-00005-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e759e2293df2a5a27d967c0a0dcc2d8f0ad382cf946c41d2643a6633f3d3497
3
+ size 9867456961
pytorch_model-00006-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d056b40f5e4303e9f51c0bef698ea23a3111ad1672bcd1413691097759e6978
3
+ size 2490476207
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,410 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 52063467520
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00006-of-00006.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00006.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
17
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
18
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
22
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
23
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
24
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
25
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
27
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
28
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
29
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
30
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
31
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
32
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
33
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
34
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
35
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
37
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
38
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
39
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
40
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
41
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
42
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
43
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
44
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
45
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
47
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
48
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
49
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
50
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
51
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
52
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
53
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
54
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
55
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
57
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
58
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
59
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
60
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
61
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
62
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
63
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
64
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
65
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
67
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
68
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
69
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
70
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
71
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
72
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
73
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
74
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
75
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
77
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
78
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
79
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
80
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
81
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
82
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
83
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
84
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
85
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
87
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
88
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
89
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
90
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
91
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
92
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
93
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
94
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
95
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
97
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
98
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
99
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
100
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
101
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
102
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
103
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
104
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
105
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
107
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
108
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
109
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
110
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
111
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
112
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
113
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
114
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
115
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
117
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
118
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
119
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
120
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
121
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
122
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
123
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
124
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
125
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
127
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
128
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
129
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
130
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
131
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
132
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
133
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
134
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
135
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
137
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
138
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
139
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
140
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
141
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
142
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
143
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
144
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
145
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
147
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
148
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
149
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
150
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
151
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
152
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
153
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
154
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
155
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
157
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
158
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
159
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
160
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
161
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
162
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
163
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
164
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
165
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
167
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
168
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
169
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
170
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
171
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
172
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
173
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
174
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
175
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
177
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
178
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
179
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
180
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
181
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
182
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
183
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
184
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
185
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
187
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
188
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
189
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
190
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
191
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
192
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
193
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
194
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
195
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
197
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
198
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
199
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
200
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
201
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
202
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
203
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
204
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
205
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
207
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
208
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
209
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
210
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
211
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
212
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
213
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
214
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
215
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
217
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
218
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
219
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
220
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
221
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
222
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
223
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
224
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
225
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
227
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
228
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
229
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
230
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
231
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
232
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
233
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
234
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
235
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
237
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
238
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
239
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
240
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
241
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
242
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
243
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
244
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
245
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
247
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
248
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
249
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
250
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
251
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
252
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
253
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
254
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
255
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
257
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
258
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
259
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
260
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
261
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
262
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
263
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
264
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
265
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
267
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
268
+ "model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
269
+ "model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
270
+ "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
271
+ "model.layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
272
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
273
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
274
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
275
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
276
+ "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
277
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
278
+ "model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
279
+ "model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
280
+ "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
281
+ "model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
282
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
283
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
284
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
285
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
286
+ "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
287
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
288
+ "model.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
289
+ "model.layers.34.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
290
+ "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
291
+ "model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
292
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
293
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
294
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
295
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
296
+ "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
297
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
298
+ "model.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
299
+ "model.layers.35.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
300
+ "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
301
+ "model.layers.35.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
302
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
303
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
304
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
305
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
306
+ "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
307
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
308
+ "model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
309
+ "model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
310
+ "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
311
+ "model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
312
+ "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
313
+ "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
314
+ "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
315
+ "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
316
+ "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
317
+ "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
318
+ "model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
319
+ "model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
320
+ "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
321
+ "model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
322
+ "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
323
+ "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
324
+ "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
325
+ "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
326
+ "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
327
+ "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
328
+ "model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
329
+ "model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
330
+ "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
331
+ "model.layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
332
+ "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
333
+ "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
334
+ "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
335
+ "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
336
+ "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
337
+ "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
338
+ "model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
339
+ "model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
340
+ "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
341
+ "model.layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
342
+ "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
343
+ "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
344
+ "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
345
+ "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
346
+ "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00006.bin",
347
+ "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
348
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
349
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
350
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
351
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
352
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
353
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
354
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
355
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
356
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
357
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
358
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
359
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
360
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
361
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
362
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
363
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
364
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
365
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
366
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
367
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
368
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
369
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
370
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
371
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
372
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
373
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
374
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
375
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
376
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
377
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
378
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
379
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
380
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
381
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
382
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
383
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
384
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
385
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
386
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
387
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
388
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
389
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
390
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
391
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
392
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
393
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
394
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
395
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
396
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
397
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
398
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
399
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
400
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
401
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
402
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
403
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
404
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
405
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
406
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
407
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
408
+ "model.norm.weight": "pytorch_model-00006-of-00006.bin"
409
+ }
410
+ }
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": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
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 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "model_max_length": 2048,
22
+ "pad_token": null,
23
+ "padding_side": "right",
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
+ }
trainer_state.json ADDED
@@ -0,0 +1,241 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.945945945945946,
5
+ "global_step": 36,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.05,
12
+ "learning_rate": 1e-05,
13
+ "loss": 0.4805,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.11,
18
+ "learning_rate": 2e-05,
19
+ "loss": 0.5187,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 0.16,
24
+ "learning_rate": 1.9957341762950346e-05,
25
+ "loss": 0.4365,
26
+ "step": 3
27
+ },
28
+ {
29
+ "epoch": 0.22,
30
+ "learning_rate": 1.982973099683902e-05,
31
+ "loss": 0.4007,
32
+ "step": 4
33
+ },
34
+ {
35
+ "epoch": 0.27,
36
+ "learning_rate": 1.961825643172819e-05,
37
+ "loss": 0.3944,
38
+ "step": 5
39
+ },
40
+ {
41
+ "epoch": 0.32,
42
+ "learning_rate": 1.932472229404356e-05,
43
+ "loss": 0.3724,
44
+ "step": 6
45
+ },
46
+ {
47
+ "epoch": 0.38,
48
+ "learning_rate": 1.8951632913550625e-05,
49
+ "loss": 0.3217,
50
+ "step": 7
51
+ },
52
+ {
53
+ "epoch": 0.43,
54
+ "learning_rate": 1.8502171357296144e-05,
55
+ "loss": 0.3093,
56
+ "step": 8
57
+ },
58
+ {
59
+ "epoch": 0.49,
60
+ "learning_rate": 1.7980172272802398e-05,
61
+ "loss": 0.3106,
62
+ "step": 9
63
+ },
64
+ {
65
+ "epoch": 0.54,
66
+ "learning_rate": 1.7390089172206594e-05,
67
+ "loss": 0.306,
68
+ "step": 10
69
+ },
70
+ {
71
+ "epoch": 0.59,
72
+ "learning_rate": 1.6736956436465573e-05,
73
+ "loss": 0.313,
74
+ "step": 11
75
+ },
76
+ {
77
+ "epoch": 0.65,
78
+ "learning_rate": 1.6026346363792565e-05,
79
+ "loss": 0.3213,
80
+ "step": 12
81
+ },
82
+ {
83
+ "epoch": 0.7,
84
+ "learning_rate": 1.526432162877356e-05,
85
+ "loss": 0.2503,
86
+ "step": 13
87
+ },
88
+ {
89
+ "epoch": 0.76,
90
+ "learning_rate": 1.4457383557765385e-05,
91
+ "loss": 0.271,
92
+ "step": 14
93
+ },
94
+ {
95
+ "epoch": 0.81,
96
+ "learning_rate": 1.3612416661871532e-05,
97
+ "loss": 0.2319,
98
+ "step": 15
99
+ },
100
+ {
101
+ "epoch": 0.86,
102
+ "learning_rate": 1.2736629900720832e-05,
103
+ "loss": 0.2549,
104
+ "step": 16
105
+ },
106
+ {
107
+ "epoch": 0.92,
108
+ "learning_rate": 1.1837495178165706e-05,
109
+ "loss": 0.2571,
110
+ "step": 17
111
+ },
112
+ {
113
+ "epoch": 0.97,
114
+ "learning_rate": 1.092268359463302e-05,
115
+ "loss": 0.2518,
116
+ "step": 18
117
+ },
118
+ {
119
+ "epoch": 1.03,
120
+ "learning_rate": 1e-05,
121
+ "loss": 0.2384,
122
+ "step": 19
123
+ },
124
+ {
125
+ "epoch": 1.08,
126
+ "learning_rate": 9.07731640536698e-06,
127
+ "loss": 0.1869,
128
+ "step": 20
129
+ },
130
+ {
131
+ "epoch": 1.14,
132
+ "learning_rate": 8.162504821834296e-06,
133
+ "loss": 0.2296,
134
+ "step": 21
135
+ },
136
+ {
137
+ "epoch": 1.19,
138
+ "learning_rate": 7.263370099279173e-06,
139
+ "loss": 0.2035,
140
+ "step": 22
141
+ },
142
+ {
143
+ "epoch": 1.24,
144
+ "learning_rate": 6.387583338128471e-06,
145
+ "loss": 0.1887,
146
+ "step": 23
147
+ },
148
+ {
149
+ "epoch": 1.3,
150
+ "learning_rate": 5.542616442234618e-06,
151
+ "loss": 0.19,
152
+ "step": 24
153
+ },
154
+ {
155
+ "epoch": 1.35,
156
+ "learning_rate": 4.7356783712264405e-06,
157
+ "loss": 0.187,
158
+ "step": 25
159
+ },
160
+ {
161
+ "epoch": 1.41,
162
+ "learning_rate": 3.973653636207437e-06,
163
+ "loss": 0.1957,
164
+ "step": 26
165
+ },
166
+ {
167
+ "epoch": 1.46,
168
+ "learning_rate": 3.2630435635344283e-06,
169
+ "loss": 0.1932,
170
+ "step": 27
171
+ },
172
+ {
173
+ "epoch": 1.51,
174
+ "learning_rate": 2.6099108277934105e-06,
175
+ "loss": 0.2026,
176
+ "step": 28
177
+ },
178
+ {
179
+ "epoch": 1.57,
180
+ "learning_rate": 2.019827727197605e-06,
181
+ "loss": 0.1922,
182
+ "step": 29
183
+ },
184
+ {
185
+ "epoch": 1.62,
186
+ "learning_rate": 1.4978286427038602e-06,
187
+ "loss": 0.1889,
188
+ "step": 30
189
+ },
190
+ {
191
+ "epoch": 1.68,
192
+ "learning_rate": 1.0483670864493777e-06,
193
+ "loss": 0.2075,
194
+ "step": 31
195
+ },
196
+ {
197
+ "epoch": 1.73,
198
+ "learning_rate": 6.752777059564431e-07,
199
+ "loss": 0.1633,
200
+ "step": 32
201
+ },
202
+ {
203
+ "epoch": 1.78,
204
+ "learning_rate": 3.817435682718096e-07,
205
+ "loss": 0.158,
206
+ "step": 33
207
+ },
208
+ {
209
+ "epoch": 1.84,
210
+ "learning_rate": 1.7026900316098217e-07,
211
+ "loss": 0.1605,
212
+ "step": 34
213
+ },
214
+ {
215
+ "epoch": 1.89,
216
+ "learning_rate": 4.2658237049655325e-08,
217
+ "loss": 0.1666,
218
+ "step": 35
219
+ },
220
+ {
221
+ "epoch": 1.95,
222
+ "learning_rate": 0.0,
223
+ "loss": 0.1882,
224
+ "step": 36
225
+ },
226
+ {
227
+ "epoch": 1.95,
228
+ "step": 36,
229
+ "total_flos": 1.8313009197744128e+17,
230
+ "train_loss": 0.26231372563375366,
231
+ "train_runtime": 5201.7559,
232
+ "train_samples_per_second": 0.899,
233
+ "train_steps_per_second": 0.007
234
+ }
235
+ ],
236
+ "max_steps": 36,
237
+ "num_train_epochs": 2,
238
+ "total_flos": 1.8313009197744128e+17,
239
+ "trial_name": null,
240
+ "trial_params": null
241
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81173250cf5970b7fdcfafca0d0252ce3ac75caacff7e168b11461dc1b571c6c
3
+ size 3771