yam-peleg commited on
Commit
89c7fa8
1 Parent(s): 8908526

Upload 13 files

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/yam/gemma_hebrew_session_9_instruct_session_4/checkpoint-3150",
3
+ "architectures": [
4
+ "GemmaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 2,
9
+ "eos_token_id": 1,
10
+ "head_dim": 256,
11
+ "hidden_act": "gelu",
12
+ "hidden_size": 3072,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 24576,
15
+ "max_position_embeddings": 8192,
16
+ "model_type": "gemma",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 35,
19
+ "num_key_value_heads": 16,
20
+ "pad_token_id": 0,
21
+ "rms_norm_eps": 1e-06,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.38.1",
26
+ "use_cache": false,
27
+ "vocab_size": 256000
28
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.38.1"
7
+ }
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a6f7f43f97bf3c3d7fba52c733b3d3d72d6a33d550df021a2cdf2f3ff6ef2ff
3
+ size 4995496656
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bbb97d5d635af96362983d73ad63cb8f784b9b111fd720aa3f23049f932fb88
3
+ size 4982953168
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bebb346df4983c6514261141c99995bcea8bd252ac033b8acae896654968d2eb
3
+ size 4982953200
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:001c550c687920a2331285125a4c35b7b3a3f3747c8756536ecf4c186f6ced95
3
+ size 4982953200
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f577be694f78e03ea5009fc8ec538a76b72764c39103b2dfdbe0ef2378ba1b50
3
+ size 1006665400
model.safetensors.index.json ADDED
@@ -0,0 +1,324 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 20950984704
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
12
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
13
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
14
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
15
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
16
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
17
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
18
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
19
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
20
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
21
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
22
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
23
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
24
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
25
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
26
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
27
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
28
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
29
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
30
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
31
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
32
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
33
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
34
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
35
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
36
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
37
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
38
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
39
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
40
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
41
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
42
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
43
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
44
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
45
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
46
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
47
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
48
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
49
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
50
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
51
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
52
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
53
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
54
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
55
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
56
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
57
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
58
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
59
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
60
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
61
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
62
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
63
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
64
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
65
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
66
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
67
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
68
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
69
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
70
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
71
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
72
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
73
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
74
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
75
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
76
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
77
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
78
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
79
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
80
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
81
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
82
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
83
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
84
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
85
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
86
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
87
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
88
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
89
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
90
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
91
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
92
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
93
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
94
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
95
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
96
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
97
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
98
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
99
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
100
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
101
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
102
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
103
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
104
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
105
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
106
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
107
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
108
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
109
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
110
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
111
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
112
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
113
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
114
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
115
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
116
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
117
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
118
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
119
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
120
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
121
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
122
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
123
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
124
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
125
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
126
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
127
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
128
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
129
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
130
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
131
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
132
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
133
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
134
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
135
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
136
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
137
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
138
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
139
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
140
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
141
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
142
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
143
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
144
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
145
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
146
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
147
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
148
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
149
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
150
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
151
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
152
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
153
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
154
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
155
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
156
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
157
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
158
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
159
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
160
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
161
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
162
+ "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
163
+ "model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
164
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
165
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
166
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
167
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
168
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
169
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
170
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
171
+ "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
172
+ "model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
173
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
174
+ "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
175
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
176
+ "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
177
+ "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
178
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
179
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
180
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
181
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
182
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
183
+ "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
184
+ "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
185
+ "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
186
+ "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
187
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
188
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
189
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
190
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
191
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
192
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
193
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
194
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
195
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
196
+ "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
197
+ "model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
198
+ "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
199
+ "model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
200
+ "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
201
+ "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
202
+ "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
203
+ "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
204
+ "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
205
+ "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
206
+ "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
207
+ "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
208
+ "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
209
+ "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
210
+ "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
211
+ "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
212
+ "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
213
+ "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
214
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
215
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
216
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
217
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
218
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
219
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
220
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
221
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
222
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
223
+ "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
224
+ "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
225
+ "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
226
+ "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
227
+ "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
228
+ "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
229
+ "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
230
+ "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
231
+ "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
232
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
233
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
234
+ "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
235
+ "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
236
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
237
+ "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
238
+ "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
239
+ "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
240
+ "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
241
+ "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
242
+ "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
243
+ "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
244
+ "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
245
+ "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
246
+ "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
247
+ "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
248
+ "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
249
+ "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
250
+ "model.layers.33.input_layernorm.weight": "model-00005-of-00005.safetensors",
251
+ "model.layers.33.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
252
+ "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
253
+ "model.layers.33.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
254
+ "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
255
+ "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
256
+ "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
257
+ "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
258
+ "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
259
+ "model.layers.34.input_layernorm.weight": "model-00005-of-00005.safetensors",
260
+ "model.layers.34.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
261
+ "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
262
+ "model.layers.34.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
263
+ "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
264
+ "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
265
+ "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
266
+ "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
267
+ "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
268
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
269
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
270
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
271
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
272
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
273
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
274
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
275
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
276
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
277
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
278
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
279
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
280
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
281
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
282
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
283
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
284
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
285
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
286
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
287
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
288
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
289
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
290
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
291
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
292
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
293
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
294
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
295
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
296
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
297
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
298
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
299
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
300
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
301
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
302
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
303
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
304
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
305
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
306
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
307
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
308
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
309
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
310
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
311
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
312
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
313
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
314
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
315
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
316
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
317
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
318
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
319
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
320
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
321
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
322
+ "model.norm.weight": "model-00005-of-00005.safetensors"
323
+ }
324
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<start_of_turn>",
4
+ "<end_of_turn>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<bos>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<pad>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05e97791a5e007260de1db7e1692e53150e08cea481e2bf25435553380c147ee
3
+ size 17477929
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6969e64047744a44bb3abfb5c50f8de0f7ed8b571d5444426ef931f651d1a0ef
3
+ size 4241111
tokenizer_config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<bos>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "106": {
38
+ "content": "<start_of_turn>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "107": {
46
+ "content": "<end_of_turn>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ }
53
+ },
54
+ "additional_special_tokens": [
55
+ "<start_of_turn>",
56
+ "<end_of_turn>"
57
+ ],
58
+ "bos_token": "<bos>",
59
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
60
+ "clean_up_tokenization_spaces": false,
61
+ "eos_token": "<eos>",
62
+ "legacy": null,
63
+ "model_max_length": 1000000000000000019884624838656,
64
+ "pad_token": "<pad>",
65
+ "sp_model_kwargs": {},
66
+ "spaces_between_special_tokens": false,
67
+ "tokenizer_class": "GemmaTokenizer",
68
+ "unk_token": "<unk>",
69
+ "use_default_system_prompt": false
70
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff