Siddartha10 commited on
Commit
c84c66d
1 Parent(s): 6fa5ff4

Upload folder using huggingface_hub

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
README.md CHANGED
@@ -1,3 +1,40 @@
1
  ---
2
- license: apache-2.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: other
3
+ library_name: transformers
4
+ tags:
5
+ - mlx
6
+ widget:
7
+ - text: '<start_of_turn>user
8
+
9
+ How does the brain work?<end_of_turn>
10
+
11
+ <start_of_turn>model
12
+
13
+ '
14
+ inference:
15
+ parameters:
16
+ max_new_tokens: 200
17
+ extra_gated_heading: Access Gemma on Hugging Face
18
+ extra_gated_prompt: To access Gemma on Hugging Face, you’re required to review and
19
+ agree to Google’s usage license. To do this, please ensure you’re logged-in to Hugging
20
+ Face and click below. Requests are processed immediately.
21
+ extra_gated_button_content: Acknowledge license
22
+ license_name: gemma-terms-of-use
23
+ license_link: https://ai.google.dev/gemma/terms
24
  ---
25
+
26
+ # Siddartha10/gemma-2b-it_sarvam_ai_dataset
27
+ This model was converted to MLX format from [`google/gemma-2b-it`]().
28
+ Refer to the [original model card](https://huggingface.co/google/gemma-2b-it) for more details on the model.
29
+ ## Use with mlx
30
+
31
+ ```bash
32
+ pip install mlx-lm
33
+ ```
34
+
35
+ ```python
36
+ from mlx_lm import load, generate
37
+
38
+ model, tokenizer = load("Siddartha10/gemma-2b-it_sarvam_ai_dataset")
39
+ response = generate(model, tokenizer, prompt="hello", verbose=True)
40
+ ```
config.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 256000,
3
+ "max_position_embeddings": 8192,
4
+ "hidden_size": 2048,
5
+ "intermediate_size": 16384,
6
+ "num_hidden_layers": 18,
7
+ "num_attention_heads": 8,
8
+ "head_dim": 256,
9
+ "num_key_value_heads": 1,
10
+ "hidden_act": "gelu",
11
+ "initializer_range": 0.02,
12
+ "rms_norm_eps": 1e-06,
13
+ "use_cache": true,
14
+ "rope_theta": 10000.0,
15
+ "attention_bias": false,
16
+ "attention_dropout": 0.0,
17
+ "return_dict": true,
18
+ "output_hidden_states": false,
19
+ "output_attentions": false,
20
+ "torchscript": false,
21
+ "torch_dtype": "bfloat16",
22
+ "use_bfloat16": false,
23
+ "tf_legacy_loss": false,
24
+ "pruned_heads": {},
25
+ "tie_word_embeddings": true,
26
+ "chunk_size_feed_forward": 0,
27
+ "is_encoder_decoder": false,
28
+ "is_decoder": false,
29
+ "cross_attention_hidden_size": null,
30
+ "add_cross_attention": false,
31
+ "tie_encoder_decoder": false,
32
+ "max_length": 20,
33
+ "min_length": 0,
34
+ "do_sample": false,
35
+ "early_stopping": false,
36
+ "num_beams": 1,
37
+ "num_beam_groups": 1,
38
+ "diversity_penalty": 0.0,
39
+ "temperature": 1.0,
40
+ "top_k": 50,
41
+ "top_p": 1.0,
42
+ "typical_p": 1.0,
43
+ "repetition_penalty": 1.0,
44
+ "length_penalty": 1.0,
45
+ "no_repeat_ngram_size": 0,
46
+ "encoder_no_repeat_ngram_size": 0,
47
+ "bad_words_ids": null,
48
+ "num_return_sequences": 1,
49
+ "output_scores": false,
50
+ "return_dict_in_generate": false,
51
+ "forced_bos_token_id": null,
52
+ "forced_eos_token_id": null,
53
+ "remove_invalid_values": false,
54
+ "exponential_decay_length_penalty": null,
55
+ "suppress_tokens": null,
56
+ "begin_suppress_tokens": null,
57
+ "architectures": [
58
+ "GemmaForCausalLM"
59
+ ],
60
+ "finetuning_task": null,
61
+ "id2label": {
62
+ "0": "LABEL_0",
63
+ "1": "LABEL_1"
64
+ },
65
+ "label2id": {
66
+ "LABEL_0": 0,
67
+ "LABEL_1": 1
68
+ },
69
+ "tokenizer_class": null,
70
+ "prefix": null,
71
+ "bos_token_id": 2,
72
+ "pad_token_id": 0,
73
+ "eos_token_id": 1,
74
+ "sep_token_id": null,
75
+ "decoder_start_token_id": null,
76
+ "task_specific_params": null,
77
+ "problem_type": null,
78
+ "_name_or_path": "/Users/siddartha/.cache/huggingface/hub/models--google--gemma-2b-it/snapshots/9f5abd187467338b36f75c06bf2bda7b2e7eb404",
79
+ "transformers_version": "4.38.0",
80
+ "model_type": "gemma",
81
+ "rope_scaling": null
82
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:234ced923631ef456cad78d0e7d0ebe479d26f0d8652f131477473263720e462
3
+ size 5012363747
model.safetensors.index.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5012344832
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
12
+ "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
13
+ "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
14
+ "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
15
+ "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
16
+ "model.layers.1.input_layernorm.weight": "model.safetensors",
17
+ "model.layers.1.mlp.down_proj.weight": "model.safetensors",
18
+ "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
19
+ "model.layers.1.mlp.up_proj.weight": "model.safetensors",
20
+ "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
21
+ "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
22
+ "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
23
+ "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
24
+ "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
25
+ "model.layers.10.input_layernorm.weight": "model.safetensors",
26
+ "model.layers.10.mlp.down_proj.weight": "model.safetensors",
27
+ "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
28
+ "model.layers.10.mlp.up_proj.weight": "model.safetensors",
29
+ "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
30
+ "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
31
+ "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
32
+ "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
33
+ "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
34
+ "model.layers.11.input_layernorm.weight": "model.safetensors",
35
+ "model.layers.11.mlp.down_proj.weight": "model.safetensors",
36
+ "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
37
+ "model.layers.11.mlp.up_proj.weight": "model.safetensors",
38
+ "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
39
+ "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
40
+ "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
41
+ "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
42
+ "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
43
+ "model.layers.12.input_layernorm.weight": "model.safetensors",
44
+ "model.layers.12.mlp.down_proj.weight": "model.safetensors",
45
+ "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
46
+ "model.layers.12.mlp.up_proj.weight": "model.safetensors",
47
+ "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
48
+ "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
49
+ "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
50
+ "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
51
+ "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
52
+ "model.layers.13.input_layernorm.weight": "model.safetensors",
53
+ "model.layers.13.mlp.down_proj.weight": "model.safetensors",
54
+ "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
55
+ "model.layers.13.mlp.up_proj.weight": "model.safetensors",
56
+ "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
57
+ "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
58
+ "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
59
+ "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
60
+ "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
61
+ "model.layers.14.input_layernorm.weight": "model.safetensors",
62
+ "model.layers.14.mlp.down_proj.weight": "model.safetensors",
63
+ "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
64
+ "model.layers.14.mlp.up_proj.weight": "model.safetensors",
65
+ "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
66
+ "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
67
+ "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
68
+ "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
69
+ "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
70
+ "model.layers.15.input_layernorm.weight": "model.safetensors",
71
+ "model.layers.15.mlp.down_proj.weight": "model.safetensors",
72
+ "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
73
+ "model.layers.15.mlp.up_proj.weight": "model.safetensors",
74
+ "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
75
+ "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
76
+ "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
77
+ "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
78
+ "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
79
+ "model.layers.16.input_layernorm.weight": "model.safetensors",
80
+ "model.layers.16.mlp.down_proj.weight": "model.safetensors",
81
+ "model.layers.16.mlp.gate_proj.weight": "model.safetensors",
82
+ "model.layers.16.mlp.up_proj.weight": "model.safetensors",
83
+ "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
84
+ "model.layers.16.self_attn.k_proj.weight": "model.safetensors",
85
+ "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
86
+ "model.layers.16.self_attn.q_proj.weight": "model.safetensors",
87
+ "model.layers.16.self_attn.v_proj.weight": "model.safetensors",
88
+ "model.layers.17.input_layernorm.weight": "model.safetensors",
89
+ "model.layers.17.mlp.down_proj.weight": "model.safetensors",
90
+ "model.layers.17.mlp.gate_proj.weight": "model.safetensors",
91
+ "model.layers.17.mlp.up_proj.weight": "model.safetensors",
92
+ "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
93
+ "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
94
+ "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
95
+ "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
96
+ "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
97
+ "model.layers.2.input_layernorm.weight": "model.safetensors",
98
+ "model.layers.2.mlp.down_proj.weight": "model.safetensors",
99
+ "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
100
+ "model.layers.2.mlp.up_proj.weight": "model.safetensors",
101
+ "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
102
+ "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
103
+ "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
104
+ "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
105
+ "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
106
+ "model.layers.3.input_layernorm.weight": "model.safetensors",
107
+ "model.layers.3.mlp.down_proj.weight": "model.safetensors",
108
+ "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
109
+ "model.layers.3.mlp.up_proj.weight": "model.safetensors",
110
+ "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
111
+ "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
112
+ "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
113
+ "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
114
+ "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
115
+ "model.layers.4.input_layernorm.weight": "model.safetensors",
116
+ "model.layers.4.mlp.down_proj.weight": "model.safetensors",
117
+ "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
118
+ "model.layers.4.mlp.up_proj.weight": "model.safetensors",
119
+ "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
120
+ "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
121
+ "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
122
+ "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
123
+ "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
124
+ "model.layers.5.input_layernorm.weight": "model.safetensors",
125
+ "model.layers.5.mlp.down_proj.weight": "model.safetensors",
126
+ "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
127
+ "model.layers.5.mlp.up_proj.weight": "model.safetensors",
128
+ "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
129
+ "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
130
+ "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
131
+ "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
132
+ "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
133
+ "model.layers.6.input_layernorm.weight": "model.safetensors",
134
+ "model.layers.6.mlp.down_proj.weight": "model.safetensors",
135
+ "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
136
+ "model.layers.6.mlp.up_proj.weight": "model.safetensors",
137
+ "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
138
+ "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
139
+ "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
140
+ "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
141
+ "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
142
+ "model.layers.7.input_layernorm.weight": "model.safetensors",
143
+ "model.layers.7.mlp.down_proj.weight": "model.safetensors",
144
+ "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
145
+ "model.layers.7.mlp.up_proj.weight": "model.safetensors",
146
+ "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
147
+ "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
148
+ "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
149
+ "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
150
+ "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
151
+ "model.layers.8.input_layernorm.weight": "model.safetensors",
152
+ "model.layers.8.mlp.down_proj.weight": "model.safetensors",
153
+ "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
154
+ "model.layers.8.mlp.up_proj.weight": "model.safetensors",
155
+ "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
156
+ "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
157
+ "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
158
+ "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
159
+ "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
160
+ "model.layers.9.input_layernorm.weight": "model.safetensors",
161
+ "model.layers.9.mlp.down_proj.weight": "model.safetensors",
162
+ "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
163
+ "model.layers.9.mlp.up_proj.weight": "model.safetensors",
164
+ "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
165
+ "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
166
+ "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
167
+ "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
168
+ "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
169
+ "model.norm.weight": "model.safetensors"
170
+ }
171
+ }
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 sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
3
+ size 4241003
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": "{{ 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": 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
+ }