benjamin commited on
Commit
83edc51
·
1 Parent(s): f9a9e4c
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 128,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 3072,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 8192,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 24,
23
+ "num_hidden_layers": 28,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 32.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": true,
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.46.0.dev0",
38
+ "use_cache": true,
39
+ "vocab_size": 128256
40
+ }
flax_model-00001-of-00002.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62c1e9d1379d50efba9c3386defb7a75eff877bd63e580a07d3e236b6b51a35a
3
+ size 9981919884
flax_model-00002-of-00002.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbc24a4f92026a8c05302730568e12be19a4cb9cea44c93da2516f03985e983c
3
+ size 2869091323
flax_model.msgpack.index.json ADDED
@@ -0,0 +1,261 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 12850999296
4
+ },
5
+ "weight_map": {
6
+ "model/embed_tokens/embedding": "flax_model-00001-of-00002.msgpack",
7
+ "model/layers/0/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
8
+ "model/layers/0/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
9
+ "model/layers/0/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
10
+ "model/layers/0/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
11
+ "model/layers/0/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
12
+ "model/layers/0/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
13
+ "model/layers/0/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
14
+ "model/layers/0/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
15
+ "model/layers/0/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
16
+ "model/layers/1/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
17
+ "model/layers/1/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
18
+ "model/layers/1/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
19
+ "model/layers/1/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
20
+ "model/layers/1/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
21
+ "model/layers/1/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
22
+ "model/layers/1/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
23
+ "model/layers/1/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
24
+ "model/layers/1/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
25
+ "model/layers/10/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
26
+ "model/layers/10/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
27
+ "model/layers/10/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
28
+ "model/layers/10/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
29
+ "model/layers/10/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
30
+ "model/layers/10/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
31
+ "model/layers/10/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
32
+ "model/layers/10/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
33
+ "model/layers/10/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
34
+ "model/layers/11/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
35
+ "model/layers/11/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
36
+ "model/layers/11/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
37
+ "model/layers/11/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
38
+ "model/layers/11/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
39
+ "model/layers/11/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
40
+ "model/layers/11/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
41
+ "model/layers/11/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
42
+ "model/layers/11/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
43
+ "model/layers/12/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
44
+ "model/layers/12/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
45
+ "model/layers/12/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
46
+ "model/layers/12/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
47
+ "model/layers/12/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
48
+ "model/layers/12/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
49
+ "model/layers/12/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
50
+ "model/layers/12/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
51
+ "model/layers/12/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
52
+ "model/layers/13/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
53
+ "model/layers/13/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
54
+ "model/layers/13/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
55
+ "model/layers/13/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
56
+ "model/layers/13/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
57
+ "model/layers/13/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
58
+ "model/layers/13/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
59
+ "model/layers/13/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
60
+ "model/layers/13/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
61
+ "model/layers/14/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
62
+ "model/layers/14/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
63
+ "model/layers/14/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
64
+ "model/layers/14/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
65
+ "model/layers/14/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
66
+ "model/layers/14/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
67
+ "model/layers/14/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
68
+ "model/layers/14/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
69
+ "model/layers/14/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
70
+ "model/layers/15/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
71
+ "model/layers/15/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
72
+ "model/layers/15/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
73
+ "model/layers/15/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
74
+ "model/layers/15/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
75
+ "model/layers/15/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
76
+ "model/layers/15/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
77
+ "model/layers/15/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
78
+ "model/layers/15/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
79
+ "model/layers/16/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
80
+ "model/layers/16/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
81
+ "model/layers/16/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
82
+ "model/layers/16/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
83
+ "model/layers/16/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
84
+ "model/layers/16/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
85
+ "model/layers/16/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
86
+ "model/layers/16/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
87
+ "model/layers/16/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
88
+ "model/layers/17/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
89
+ "model/layers/17/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
90
+ "model/layers/17/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
91
+ "model/layers/17/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
92
+ "model/layers/17/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
93
+ "model/layers/17/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
94
+ "model/layers/17/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
95
+ "model/layers/17/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
96
+ "model/layers/17/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
97
+ "model/layers/18/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
98
+ "model/layers/18/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
99
+ "model/layers/18/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
100
+ "model/layers/18/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
101
+ "model/layers/18/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
102
+ "model/layers/18/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
103
+ "model/layers/18/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
104
+ "model/layers/18/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
105
+ "model/layers/18/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
106
+ "model/layers/19/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
107
+ "model/layers/19/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
108
+ "model/layers/19/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
109
+ "model/layers/19/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
110
+ "model/layers/19/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
111
+ "model/layers/19/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
112
+ "model/layers/19/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
113
+ "model/layers/19/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
114
+ "model/layers/19/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
115
+ "model/layers/2/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
116
+ "model/layers/2/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
117
+ "model/layers/2/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
118
+ "model/layers/2/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
119
+ "model/layers/2/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
120
+ "model/layers/2/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
121
+ "model/layers/2/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
122
+ "model/layers/2/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
123
+ "model/layers/2/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
124
+ "model/layers/20/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
125
+ "model/layers/20/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
126
+ "model/layers/20/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
127
+ "model/layers/20/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
128
+ "model/layers/20/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
129
+ "model/layers/20/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
130
+ "model/layers/20/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
131
+ "model/layers/20/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
132
+ "model/layers/20/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
133
+ "model/layers/21/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
134
+ "model/layers/21/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
135
+ "model/layers/21/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
136
+ "model/layers/21/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
137
+ "model/layers/21/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
138
+ "model/layers/21/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
139
+ "model/layers/21/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
140
+ "model/layers/21/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
141
+ "model/layers/21/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
142
+ "model/layers/22/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
143
+ "model/layers/22/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
144
+ "model/layers/22/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
145
+ "model/layers/22/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
146
+ "model/layers/22/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
147
+ "model/layers/22/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
148
+ "model/layers/22/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
149
+ "model/layers/22/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
150
+ "model/layers/22/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
151
+ "model/layers/23/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
152
+ "model/layers/23/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
153
+ "model/layers/23/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
154
+ "model/layers/23/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
155
+ "model/layers/23/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
156
+ "model/layers/23/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
157
+ "model/layers/23/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
158
+ "model/layers/23/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
159
+ "model/layers/23/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
160
+ "model/layers/24/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
161
+ "model/layers/24/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
162
+ "model/layers/24/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
163
+ "model/layers/24/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
164
+ "model/layers/24/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
165
+ "model/layers/24/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
166
+ "model/layers/24/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
167
+ "model/layers/24/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
168
+ "model/layers/24/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
169
+ "model/layers/25/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
170
+ "model/layers/25/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
171
+ "model/layers/25/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
172
+ "model/layers/25/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
173
+ "model/layers/25/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
174
+ "model/layers/25/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
175
+ "model/layers/25/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
176
+ "model/layers/25/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
177
+ "model/layers/25/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
178
+ "model/layers/26/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
179
+ "model/layers/26/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
180
+ "model/layers/26/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
181
+ "model/layers/26/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
182
+ "model/layers/26/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
183
+ "model/layers/26/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
184
+ "model/layers/26/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
185
+ "model/layers/26/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
186
+ "model/layers/26/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
187
+ "model/layers/27/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
188
+ "model/layers/27/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
189
+ "model/layers/27/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
190
+ "model/layers/27/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
191
+ "model/layers/27/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
192
+ "model/layers/27/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
193
+ "model/layers/27/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
194
+ "model/layers/27/self_attn/q_proj/kernel": "flax_model-00002-of-00002.msgpack",
195
+ "model/layers/27/self_attn/v_proj/kernel": "flax_model-00002-of-00002.msgpack",
196
+ "model/layers/3/input_layernorm/weight": "flax_model-00002-of-00002.msgpack",
197
+ "model/layers/3/mlp/down_proj/kernel": "flax_model-00002-of-00002.msgpack",
198
+ "model/layers/3/mlp/gate_proj/kernel": "flax_model-00002-of-00002.msgpack",
199
+ "model/layers/3/mlp/up_proj/kernel": "flax_model-00002-of-00002.msgpack",
200
+ "model/layers/3/post_attention_layernorm/weight": "flax_model-00002-of-00002.msgpack",
201
+ "model/layers/3/self_attn/k_proj/kernel": "flax_model-00002-of-00002.msgpack",
202
+ "model/layers/3/self_attn/o_proj/kernel": "flax_model-00002-of-00002.msgpack",
203
+ "model/layers/3/self_attn/q_proj/kernel": "flax_model-00002-of-00002.msgpack",
204
+ "model/layers/3/self_attn/v_proj/kernel": "flax_model-00002-of-00002.msgpack",
205
+ "model/layers/4/input_layernorm/weight": "flax_model-00002-of-00002.msgpack",
206
+ "model/layers/4/mlp/down_proj/kernel": "flax_model-00002-of-00002.msgpack",
207
+ "model/layers/4/mlp/gate_proj/kernel": "flax_model-00002-of-00002.msgpack",
208
+ "model/layers/4/mlp/up_proj/kernel": "flax_model-00002-of-00002.msgpack",
209
+ "model/layers/4/post_attention_layernorm/weight": "flax_model-00002-of-00002.msgpack",
210
+ "model/layers/4/self_attn/k_proj/kernel": "flax_model-00002-of-00002.msgpack",
211
+ "model/layers/4/self_attn/o_proj/kernel": "flax_model-00002-of-00002.msgpack",
212
+ "model/layers/4/self_attn/q_proj/kernel": "flax_model-00002-of-00002.msgpack",
213
+ "model/layers/4/self_attn/v_proj/kernel": "flax_model-00002-of-00002.msgpack",
214
+ "model/layers/5/input_layernorm/weight": "flax_model-00002-of-00002.msgpack",
215
+ "model/layers/5/mlp/down_proj/kernel": "flax_model-00002-of-00002.msgpack",
216
+ "model/layers/5/mlp/gate_proj/kernel": "flax_model-00002-of-00002.msgpack",
217
+ "model/layers/5/mlp/up_proj/kernel": "flax_model-00002-of-00002.msgpack",
218
+ "model/layers/5/post_attention_layernorm/weight": "flax_model-00002-of-00002.msgpack",
219
+ "model/layers/5/self_attn/k_proj/kernel": "flax_model-00002-of-00002.msgpack",
220
+ "model/layers/5/self_attn/o_proj/kernel": "flax_model-00002-of-00002.msgpack",
221
+ "model/layers/5/self_attn/q_proj/kernel": "flax_model-00002-of-00002.msgpack",
222
+ "model/layers/5/self_attn/v_proj/kernel": "flax_model-00002-of-00002.msgpack",
223
+ "model/layers/6/input_layernorm/weight": "flax_model-00002-of-00002.msgpack",
224
+ "model/layers/6/mlp/down_proj/kernel": "flax_model-00002-of-00002.msgpack",
225
+ "model/layers/6/mlp/gate_proj/kernel": "flax_model-00002-of-00002.msgpack",
226
+ "model/layers/6/mlp/up_proj/kernel": "flax_model-00002-of-00002.msgpack",
227
+ "model/layers/6/post_attention_layernorm/weight": "flax_model-00002-of-00002.msgpack",
228
+ "model/layers/6/self_attn/k_proj/kernel": "flax_model-00002-of-00002.msgpack",
229
+ "model/layers/6/self_attn/o_proj/kernel": "flax_model-00002-of-00002.msgpack",
230
+ "model/layers/6/self_attn/q_proj/kernel": "flax_model-00002-of-00002.msgpack",
231
+ "model/layers/6/self_attn/v_proj/kernel": "flax_model-00002-of-00002.msgpack",
232
+ "model/layers/7/input_layernorm/weight": "flax_model-00002-of-00002.msgpack",
233
+ "model/layers/7/mlp/down_proj/kernel": "flax_model-00002-of-00002.msgpack",
234
+ "model/layers/7/mlp/gate_proj/kernel": "flax_model-00002-of-00002.msgpack",
235
+ "model/layers/7/mlp/up_proj/kernel": "flax_model-00002-of-00002.msgpack",
236
+ "model/layers/7/post_attention_layernorm/weight": "flax_model-00002-of-00002.msgpack",
237
+ "model/layers/7/self_attn/k_proj/kernel": "flax_model-00002-of-00002.msgpack",
238
+ "model/layers/7/self_attn/o_proj/kernel": "flax_model-00002-of-00002.msgpack",
239
+ "model/layers/7/self_attn/q_proj/kernel": "flax_model-00002-of-00002.msgpack",
240
+ "model/layers/7/self_attn/v_proj/kernel": "flax_model-00002-of-00002.msgpack",
241
+ "model/layers/8/input_layernorm/weight": "flax_model-00002-of-00002.msgpack",
242
+ "model/layers/8/mlp/down_proj/kernel": "flax_model-00002-of-00002.msgpack",
243
+ "model/layers/8/mlp/gate_proj/kernel": "flax_model-00002-of-00002.msgpack",
244
+ "model/layers/8/mlp/up_proj/kernel": "flax_model-00002-of-00002.msgpack",
245
+ "model/layers/8/post_attention_layernorm/weight": "flax_model-00002-of-00002.msgpack",
246
+ "model/layers/8/self_attn/k_proj/kernel": "flax_model-00002-of-00002.msgpack",
247
+ "model/layers/8/self_attn/o_proj/kernel": "flax_model-00002-of-00002.msgpack",
248
+ "model/layers/8/self_attn/q_proj/kernel": "flax_model-00002-of-00002.msgpack",
249
+ "model/layers/8/self_attn/v_proj/kernel": "flax_model-00002-of-00002.msgpack",
250
+ "model/layers/9/input_layernorm/weight": "flax_model-00002-of-00002.msgpack",
251
+ "model/layers/9/mlp/down_proj/kernel": "flax_model-00002-of-00002.msgpack",
252
+ "model/layers/9/mlp/gate_proj/kernel": "flax_model-00002-of-00002.msgpack",
253
+ "model/layers/9/mlp/up_proj/kernel": "flax_model-00002-of-00002.msgpack",
254
+ "model/layers/9/post_attention_layernorm/weight": "flax_model-00002-of-00002.msgpack",
255
+ "model/layers/9/self_attn/k_proj/kernel": "flax_model-00002-of-00002.msgpack",
256
+ "model/layers/9/self_attn/o_proj/kernel": "flax_model-00002-of-00002.msgpack",
257
+ "model/layers/9/self_attn/q_proj/kernel": "flax_model-00002-of-00002.msgpack",
258
+ "model/layers/9/self_attn/v_proj/kernel": "flax_model-00002-of-00002.msgpack",
259
+ "model/norm/weight": "flax_model-00002-of-00002.msgpack"
260
+ }
261
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.46.0.dev0"
12
+ }