Vihang D commited on
Commit
2023dff
1 Parent(s): 7220cc5

Initial import of tinyllama finetune

Browse files
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "PY007/TinyLlama-1.1B-intermediate-step-715k-1.5T",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 2048,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 5632,
13
+ "max_position_embeddings": 2048,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 22,
17
+ "num_key_value_heads": 4,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "rope_theta": 10000.0,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "float16",
24
+ "transformers_version": "4.35.0.dev0",
25
+ "use_cache": true,
26
+ "vocab_size": 32000
27
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "eos_token_id": 2,
4
+ "max_length": 2048,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.35.0.dev0"
7
+ }
pytorch_model-00001-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4055cef3499f62d796b53a8410bede33f9c8c9864a6453f79a91a9df329abda9
3
+ size 395347554
pytorch_model-00002-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dba8cc3fbfea5feec2159b6374fab929865953fa9461bddeba8cee0f5bec6e57
3
+ size 394311500
pytorch_model-00003-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6a7129889c65f2b372d853aaaefe15c866273d804e0382a850acf31430cde24
3
+ size 398513658
pytorch_model-00004-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6984c4c426c803eee1da43b8cd016f2d115cdfb83f7b495ab3853b810236c89
3
+ size 394311564
pytorch_model-00005-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:759126be07dc0aeeeec3732ec18f1f99c82ba0b76584457fed80583a00a219ef
3
+ size 398513658
pytorch_model-00006-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9c2778ac3abce0e6f730cd8251b91f364f4f8232b460b87048ebb6c4ecb3f67
3
+ size 219169136
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 2200096768
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.v_proj.weight": "pytorch_model-00001-of-00006.bin",
17
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
18
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
19
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
20
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
22
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
23
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
24
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
25
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
26
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
27
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
28
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
29
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
30
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
31
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
32
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
33
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
34
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
35
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
36
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
37
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
38
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
39
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
40
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
41
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
42
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
43
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
44
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
45
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
46
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
47
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
48
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
49
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
50
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
51
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
52
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
53
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
54
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
55
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
56
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
57
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
58
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
59
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
60
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
61
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
62
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
63
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
64
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
65
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
66
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
67
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
68
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
69
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
70
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
71
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
72
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
73
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
74
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
75
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
76
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
77
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
78
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
79
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
80
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
81
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
82
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
83
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
84
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
85
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
86
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
87
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
88
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
89
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
90
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
91
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
92
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
93
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
94
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
95
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
96
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
97
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
98
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
99
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
100
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
101
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
102
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
103
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
104
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
105
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
106
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
107
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
108
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
109
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
110
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
111
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
112
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
113
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
114
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
115
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
116
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
117
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
118
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
119
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
120
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
121
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
122
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
123
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
124
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
125
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
126
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
127
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
128
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
129
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
130
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
131
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
132
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
133
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
134
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
135
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
136
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
137
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
138
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
139
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
140
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
141
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
142
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
143
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
144
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
145
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
146
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
147
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
148
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
149
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
150
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
151
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
152
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
153
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
154
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
155
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
156
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
157
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
158
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
159
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
160
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
161
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
162
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
163
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
164
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
165
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
166
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
167
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
168
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
169
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
170
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
171
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
172
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
173
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
174
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
175
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
176
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
177
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
178
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
179
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
180
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
181
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
182
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
183
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
184
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
185
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
186
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
187
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
188
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
189
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
190
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
191
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
192
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
193
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
194
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
195
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
196
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
197
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
198
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
199
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
200
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
201
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
202
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
203
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
204
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
205
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
206
+ "model.norm.weight": "pytorch_model-00006-of-00006.bin"
207
+ }
208
+ }
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 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
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": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": false,
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": null,
24
+ "padding_side": "right",
25
+ "sp_model_kwargs": {},
26
+ "tokenizer_class": "LlamaTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }