ntvcie commited on
Commit
23102ea
1 Parent(s): 049b0c6

(Trained with Unsloth)

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 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/gemma-2b-bnb-4bit",
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_activation": null,
13
+ "hidden_size": 2048,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 16384,
16
+ "max_position_embeddings": 8192,
17
+ "model_type": "gemma",
18
+ "num_attention_heads": 8,
19
+ "num_hidden_layers": 18,
20
+ "num_key_value_heads": 1,
21
+ "pad_token_id": 0,
22
+ "rms_norm_eps": 1e-06,
23
+ "rope_scaling": null,
24
+ "rope_theta": 10000.0,
25
+ "torch_dtype": "float16",
26
+ "transformers_version": "4.39.3",
27
+ "unsloth_version": "2024.4",
28
+ "use_cache": true,
29
+ "vocab_size": 256000
30
+ }
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": "4.39.3"
7
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f211d14acc04977297fc9d3c949dffd13332cb79a68174596e22eefa0ab31c9
3
+ size 4945280638
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7e755856f229ef1111277f8cf837b4f2915390fb19fd11c0b3a42e26bc0c914
3
+ size 67123512
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5012344832
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
7
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
8
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
9
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
10
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
11
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
12
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
13
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
14
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
15
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
16
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
17
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
18
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
19
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
20
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
21
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
22
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
23
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
24
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
25
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
26
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
27
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
28
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
29
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
30
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
31
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
32
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
33
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
34
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
35
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
36
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
37
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
38
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
39
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
40
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
41
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
42
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
43
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
44
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
45
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
46
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
47
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
48
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
49
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
50
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
51
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
52
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
53
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
54
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
55
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
56
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
57
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
58
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
59
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
60
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
61
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
62
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
63
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
64
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
65
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
66
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
67
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
68
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
69
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
70
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
71
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
72
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
73
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
74
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
75
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
76
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
77
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
78
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
79
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
80
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
81
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
82
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
83
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
84
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
85
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
86
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
87
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
88
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
89
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
90
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
91
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
92
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
93
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
94
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
95
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
96
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
97
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
98
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
99
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
100
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
101
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
102
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
103
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
104
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
105
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
106
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
107
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
108
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
109
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
110
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
111
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
112
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
113
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
114
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
115
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
116
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
117
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
118
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
119
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
120
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
121
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
122
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
123
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
124
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
125
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
126
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
127
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
128
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
129
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
130
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
131
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
132
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
133
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
134
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
135
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
136
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
137
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
138
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
139
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
140
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
141
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
142
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
143
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
144
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
145
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
146
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
147
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
148
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
149
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
150
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
151
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
152
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
153
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
154
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
155
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
156
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
157
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
158
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
159
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
160
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
161
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
162
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
163
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
164
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
165
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
166
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
167
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
168
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
169
+ "model.norm.weight": "pytorch_model-00002-of-00002.bin"
170
+ }
171
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<eos>",
21
+ "unk_token": {
22
+ "content": "<unk>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ }
28
+ }
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 sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
3
+ size 4241003
tokenizer_config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "{{ bos_token }}{% 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": 8192,
64
+ "pad_token": "<eos>",
65
+ "padding_side": "left",
66
+ "sp_model_kwargs": {},
67
+ "spaces_between_special_tokens": false,
68
+ "tokenizer_class": "GemmaTokenizer",
69
+ "unk_token": "<unk>",
70
+ "use_default_system_prompt": false
71
+ }