(Trained with Unsloth)
Browse files- .gitattributes +1 -0
- chat_template.jinja +88 -0
- config.json +193 -0
- processor_config.json +75 -0
- tokenizer.json +3 -0
- tokenizer_config.json +96 -0
.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
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{ bos_token }}{%- if messages[0]['role'] == 'system' -%}
|
| 2 |
+
{%- set first_user_prefix = messages[0]['content'] + '
|
| 3 |
+
|
| 4 |
+
' -%}
|
| 5 |
+
{%- set loop_messages = messages[1:] -%}
|
| 6 |
+
{%- else -%}
|
| 7 |
+
{%- set first_user_prefix = "" -%}
|
| 8 |
+
{%- set loop_messages = messages -%}
|
| 9 |
+
{%- endif -%}
|
| 10 |
+
{%- for message in loop_messages -%}
|
| 11 |
+
{%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
|
| 12 |
+
{{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
|
| 13 |
+
{%- endif -%}
|
| 14 |
+
{%- if (message['role'] == 'assistant') -%}
|
| 15 |
+
{%- set role = "model" -%}
|
| 16 |
+
{%- else -%}
|
| 17 |
+
{%- set role = message['role'] -%}
|
| 18 |
+
{%- endif -%}
|
| 19 |
+
{%- if message['content'] is string -%}
|
| 20 |
+
{%- set content = message['content'] | trim -%}
|
| 21 |
+
{%- else -%}
|
| 22 |
+
{%- set content = '' -%}
|
| 23 |
+
{%- endif -%}
|
| 24 |
+
{%- if role == "model" -%}
|
| 25 |
+
{%- set reasoning_content = '' -%}
|
| 26 |
+
{%- if message['reasoning_content'] is defined and message['reasoning_content'] is string -%}
|
| 27 |
+
{%- set reasoning_content = message['reasoning_content'] | trim -%}
|
| 28 |
+
{%- elif message['thinking'] is defined and message['thinking'] is string -%}
|
| 29 |
+
{%- set reasoning_content = message['thinking'] | trim -%}
|
| 30 |
+
{%- elif message['reasoning'] is defined and message['reasoning'] is string -%}
|
| 31 |
+
{%- set reasoning_content = message['reasoning'] | trim -%}
|
| 32 |
+
{%- endif -%}
|
| 33 |
+
{%- if reasoning_content == '' and message['content'] is string and '<|channel>thought' in content and '<channel|>' in content -%}
|
| 34 |
+
{%- set reasoning_content = content.split('<|channel>thought', 1)[1].split('<channel|>', 1)[0].strip('
|
| 35 |
+
') -%}
|
| 36 |
+
{%- set content = content.split('<channel|>', 1)[1].lstrip('
|
| 37 |
+
') -%}
|
| 38 |
+
{%- endif -%}
|
| 39 |
+
{%- if reasoning_content == '' and message['content'] is string and '<think>' in content and '</think>' in content -%}
|
| 40 |
+
{%- set reasoning_content = content.split('</think>', 1)[0].rstrip('
|
| 41 |
+
').split('<think>', 1)[-1].lstrip('
|
| 42 |
+
') -%}
|
| 43 |
+
{%- set content = content.split('</think>', 1)[1].lstrip('
|
| 44 |
+
') -%}
|
| 45 |
+
{%- endif -%}
|
| 46 |
+
{%- endif -%}
|
| 47 |
+
{{ '<|turn>' + role + '
|
| 48 |
+
' + (first_user_prefix if loop.first else "") }}
|
| 49 |
+
{%- if role == "model" -%}
|
| 50 |
+
{%- if reasoning_content -%}
|
| 51 |
+
{{ '<|channel>thought
|
| 52 |
+
' + reasoning_content + '<channel|>' }}
|
| 53 |
+
{%- else -%}
|
| 54 |
+
{{ '<|channel>thought
|
| 55 |
+
<channel|>' }}
|
| 56 |
+
{%- endif -%}
|
| 57 |
+
{%- endif -%}
|
| 58 |
+
{%- if message['content'] is string -%}
|
| 59 |
+
{{ content }}
|
| 60 |
+
{%- elif message['content'] is iterable -%}
|
| 61 |
+
{%- for item in message['content'] -%}
|
| 62 |
+
{%- if item['type'] == 'audio' -%}
|
| 63 |
+
{{ '<|audio|>' }}
|
| 64 |
+
{%- elif item['type'] == 'image' -%}
|
| 65 |
+
{{ '<|image|>' }}
|
| 66 |
+
{%- elif item['type'] == 'video' -%}
|
| 67 |
+
{{ '<|video|>' }}
|
| 68 |
+
{%- elif item['type'] == 'text' -%}
|
| 69 |
+
{{ item['text'] | trim }}
|
| 70 |
+
{%- endif -%}
|
| 71 |
+
{%- endfor -%}
|
| 72 |
+
{%- else -%}
|
| 73 |
+
{{ raise_exception("Invalid content type") }}
|
| 74 |
+
{%- endif -%}
|
| 75 |
+
{{ '<turn|>
|
| 76 |
+
' }}
|
| 77 |
+
{%- endfor -%}
|
| 78 |
+
{%- if add_generation_prompt -%}
|
| 79 |
+
{{ '<|turn>model
|
| 80 |
+
' }}
|
| 81 |
+
{%- if enable_thinking | default(true) -%}
|
| 82 |
+
{{ '<|channel>thought
|
| 83 |
+
' }}
|
| 84 |
+
{%- else -%}
|
| 85 |
+
{{ '<|channel>thought
|
| 86 |
+
<channel|>' }}
|
| 87 |
+
{%- endif -%}
|
| 88 |
+
{%- endif -%}
|
config.json
ADDED
|
@@ -0,0 +1,193 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Gemma4ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"audio_config": {
|
| 6 |
+
"_name_or_path": "",
|
| 7 |
+
"architectures": null,
|
| 8 |
+
"attention_chunk_size": 12,
|
| 9 |
+
"attention_context_left": 13,
|
| 10 |
+
"attention_context_right": 0,
|
| 11 |
+
"attention_invalid_logits_value": -1000000000.0,
|
| 12 |
+
"attention_logit_cap": 50.0,
|
| 13 |
+
"chunk_size_feed_forward": 0,
|
| 14 |
+
"conv_kernel_size": 5,
|
| 15 |
+
"torch_dtype": "bfloat16",
|
| 16 |
+
"gradient_clipping": 10000000000.0,
|
| 17 |
+
"hidden_act": "silu",
|
| 18 |
+
"hidden_size": 1024,
|
| 19 |
+
"id2label": {
|
| 20 |
+
"0": "LABEL_0",
|
| 21 |
+
"1": "LABEL_1"
|
| 22 |
+
},
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"is_encoder_decoder": false,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"LABEL_0": 0,
|
| 27 |
+
"LABEL_1": 1
|
| 28 |
+
},
|
| 29 |
+
"model_type": "gemma4_audio",
|
| 30 |
+
"num_attention_heads": 8,
|
| 31 |
+
"num_hidden_layers": 12,
|
| 32 |
+
"output_attentions": false,
|
| 33 |
+
"output_hidden_states": false,
|
| 34 |
+
"output_proj_dims": 1536,
|
| 35 |
+
"problem_type": null,
|
| 36 |
+
"residual_weight": 0.5,
|
| 37 |
+
"return_dict": true,
|
| 38 |
+
"rms_norm_eps": 1e-06,
|
| 39 |
+
"subsampling_conv_channels": [
|
| 40 |
+
128,
|
| 41 |
+
32
|
| 42 |
+
],
|
| 43 |
+
"use_clipped_linears": true
|
| 44 |
+
},
|
| 45 |
+
"audio_token_id": 258881,
|
| 46 |
+
"boa_token_id": 256000,
|
| 47 |
+
"boi_token_id": 255999,
|
| 48 |
+
"bos_token_id": 2,
|
| 49 |
+
"torch_dtype": "bfloat16",
|
| 50 |
+
"eoa_token_id": 258883,
|
| 51 |
+
"eoa_token_index": 258883,
|
| 52 |
+
"eoi_token_id": 258882,
|
| 53 |
+
"eos_token_id": 106,
|
| 54 |
+
"image_token_id": 258880,
|
| 55 |
+
"initializer_range": 0.02,
|
| 56 |
+
"model_name": "unsloth/gemma-4-E2B-it",
|
| 57 |
+
"model_type": "gemma4",
|
| 58 |
+
"pad_token_id": 0,
|
| 59 |
+
"text_config": {
|
| 60 |
+
"attention_bias": false,
|
| 61 |
+
"attention_dropout": 0.0,
|
| 62 |
+
"attention_k_eq_v": false,
|
| 63 |
+
"bos_token_id": 2,
|
| 64 |
+
"torch_dtype": "bfloat16",
|
| 65 |
+
"enable_moe_block": false,
|
| 66 |
+
"eos_token_id": 1,
|
| 67 |
+
"expert_intermediate_size": null,
|
| 68 |
+
"final_logit_softcapping": 30.0,
|
| 69 |
+
"global_head_dim": 512,
|
| 70 |
+
"head_dim": 256,
|
| 71 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 72 |
+
"hidden_size": 1536,
|
| 73 |
+
"hidden_size_per_layer_input": 256,
|
| 74 |
+
"initializer_range": 0.02,
|
| 75 |
+
"intermediate_size": 6144,
|
| 76 |
+
"layer_types": [
|
| 77 |
+
"sliding_attention",
|
| 78 |
+
"sliding_attention",
|
| 79 |
+
"sliding_attention",
|
| 80 |
+
"sliding_attention",
|
| 81 |
+
"full_attention",
|
| 82 |
+
"sliding_attention",
|
| 83 |
+
"sliding_attention",
|
| 84 |
+
"sliding_attention",
|
| 85 |
+
"sliding_attention",
|
| 86 |
+
"full_attention",
|
| 87 |
+
"sliding_attention",
|
| 88 |
+
"sliding_attention",
|
| 89 |
+
"sliding_attention",
|
| 90 |
+
"sliding_attention",
|
| 91 |
+
"full_attention",
|
| 92 |
+
"sliding_attention",
|
| 93 |
+
"sliding_attention",
|
| 94 |
+
"sliding_attention",
|
| 95 |
+
"sliding_attention",
|
| 96 |
+
"full_attention",
|
| 97 |
+
"sliding_attention",
|
| 98 |
+
"sliding_attention",
|
| 99 |
+
"sliding_attention",
|
| 100 |
+
"sliding_attention",
|
| 101 |
+
"full_attention",
|
| 102 |
+
"sliding_attention",
|
| 103 |
+
"sliding_attention",
|
| 104 |
+
"sliding_attention",
|
| 105 |
+
"sliding_attention",
|
| 106 |
+
"full_attention",
|
| 107 |
+
"sliding_attention",
|
| 108 |
+
"sliding_attention",
|
| 109 |
+
"sliding_attention",
|
| 110 |
+
"sliding_attention",
|
| 111 |
+
"full_attention"
|
| 112 |
+
],
|
| 113 |
+
"max_position_embeddings": 131072,
|
| 114 |
+
"model_type": "gemma4_text",
|
| 115 |
+
"moe_intermediate_size": null,
|
| 116 |
+
"num_attention_heads": 8,
|
| 117 |
+
"num_experts": null,
|
| 118 |
+
"num_global_key_value_heads": null,
|
| 119 |
+
"num_hidden_layers": 35,
|
| 120 |
+
"num_key_value_heads": 1,
|
| 121 |
+
"num_kv_shared_layers": 20,
|
| 122 |
+
"pad_token_id": 0,
|
| 123 |
+
"rms_norm_eps": 1e-06,
|
| 124 |
+
"rope_parameters": {
|
| 125 |
+
"full_attention": {
|
| 126 |
+
"partial_rotary_factor": 0.25,
|
| 127 |
+
"rope_theta": 1000000.0,
|
| 128 |
+
"rope_type": "proportional"
|
| 129 |
+
},
|
| 130 |
+
"sliding_attention": {
|
| 131 |
+
"rope_theta": 10000.0,
|
| 132 |
+
"rope_type": "default"
|
| 133 |
+
}
|
| 134 |
+
},
|
| 135 |
+
"sliding_window": 512,
|
| 136 |
+
"tie_word_embeddings": true,
|
| 137 |
+
"top_k_experts": null,
|
| 138 |
+
"use_bidirectional_attention": null,
|
| 139 |
+
"use_cache": true,
|
| 140 |
+
"use_double_wide_mlp": true,
|
| 141 |
+
"vocab_size": 262144,
|
| 142 |
+
"vocab_size_per_layer_input": 262144
|
| 143 |
+
},
|
| 144 |
+
"tie_word_embeddings": true,
|
| 145 |
+
"unsloth_fixed": true,
|
| 146 |
+
"unsloth_version": "2026.4.2",
|
| 147 |
+
"use_cache": false,
|
| 148 |
+
"video_token_id": 258884,
|
| 149 |
+
"vision_config": {
|
| 150 |
+
"_name_or_path": "",
|
| 151 |
+
"architectures": null,
|
| 152 |
+
"attention_bias": false,
|
| 153 |
+
"attention_dropout": 0.0,
|
| 154 |
+
"chunk_size_feed_forward": 0,
|
| 155 |
+
"default_output_length": 280,
|
| 156 |
+
"torch_dtype": "bfloat16",
|
| 157 |
+
"global_head_dim": 64,
|
| 158 |
+
"head_dim": 64,
|
| 159 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 160 |
+
"hidden_size": 768,
|
| 161 |
+
"id2label": {
|
| 162 |
+
"0": "LABEL_0",
|
| 163 |
+
"1": "LABEL_1"
|
| 164 |
+
},
|
| 165 |
+
"initializer_range": 0.02,
|
| 166 |
+
"intermediate_size": 3072,
|
| 167 |
+
"is_encoder_decoder": false,
|
| 168 |
+
"label2id": {
|
| 169 |
+
"LABEL_0": 0,
|
| 170 |
+
"LABEL_1": 1
|
| 171 |
+
},
|
| 172 |
+
"max_position_embeddings": 131072,
|
| 173 |
+
"model_type": "gemma4_vision",
|
| 174 |
+
"num_attention_heads": 12,
|
| 175 |
+
"num_hidden_layers": 16,
|
| 176 |
+
"num_key_value_heads": 12,
|
| 177 |
+
"output_attentions": false,
|
| 178 |
+
"output_hidden_states": false,
|
| 179 |
+
"patch_size": 16,
|
| 180 |
+
"pooling_kernel_size": 3,
|
| 181 |
+
"position_embedding_size": 10240,
|
| 182 |
+
"problem_type": null,
|
| 183 |
+
"return_dict": true,
|
| 184 |
+
"rms_norm_eps": 1e-06,
|
| 185 |
+
"rope_parameters": {
|
| 186 |
+
"rope_theta": 100.0,
|
| 187 |
+
"rope_type": "default"
|
| 188 |
+
},
|
| 189 |
+
"standardize": false,
|
| 190 |
+
"use_clipped_linears": true
|
| 191 |
+
},
|
| 192 |
+
"vision_soft_tokens_per_image": 280
|
| 193 |
+
}
|
processor_config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"audio_ms_per_token": 40,
|
| 3 |
+
"audio_seq_length": 750,
|
| 4 |
+
"feature_extractor": {
|
| 5 |
+
"dither": 0.0,
|
| 6 |
+
"feature_extractor_type": "Gemma4AudioFeatureExtractor",
|
| 7 |
+
"feature_size": 128,
|
| 8 |
+
"fft_length": 512,
|
| 9 |
+
"fft_overdrive": false,
|
| 10 |
+
"frame_length": 320,
|
| 11 |
+
"hop_length": 160,
|
| 12 |
+
"input_scale_factor": 1.0,
|
| 13 |
+
"max_frequency": 8000.0,
|
| 14 |
+
"mel_floor": 0.001,
|
| 15 |
+
"min_frequency": 0.0,
|
| 16 |
+
"padding_side": "left",
|
| 17 |
+
"padding_value": 0.0,
|
| 18 |
+
"per_bin_mean": null,
|
| 19 |
+
"per_bin_stddev": null,
|
| 20 |
+
"preemphasis": 0.0,
|
| 21 |
+
"preemphasis_htk_flavor": true,
|
| 22 |
+
"return_attention_mask": true,
|
| 23 |
+
"sampling_rate": 16000
|
| 24 |
+
},
|
| 25 |
+
"image_processor": {
|
| 26 |
+
"do_convert_rgb": true,
|
| 27 |
+
"do_normalize": false,
|
| 28 |
+
"do_rescale": true,
|
| 29 |
+
"do_resize": true,
|
| 30 |
+
"image_mean": [
|
| 31 |
+
0.0,
|
| 32 |
+
0.0,
|
| 33 |
+
0.0
|
| 34 |
+
],
|
| 35 |
+
"image_processor_type": "Gemma4ImageProcessor",
|
| 36 |
+
"image_seq_length": 280,
|
| 37 |
+
"image_std": [
|
| 38 |
+
1.0,
|
| 39 |
+
1.0,
|
| 40 |
+
1.0
|
| 41 |
+
],
|
| 42 |
+
"max_soft_tokens": 280,
|
| 43 |
+
"patch_size": 16,
|
| 44 |
+
"pooling_kernel_size": 3,
|
| 45 |
+
"resample": 3,
|
| 46 |
+
"rescale_factor": 0.00392156862745098
|
| 47 |
+
},
|
| 48 |
+
"image_seq_length": 280,
|
| 49 |
+
"processor_class": "Gemma4Processor",
|
| 50 |
+
"video_processor": {
|
| 51 |
+
"do_convert_rgb": true,
|
| 52 |
+
"do_normalize": true,
|
| 53 |
+
"do_rescale": true,
|
| 54 |
+
"do_resize": true,
|
| 55 |
+
"do_sample_frames": true,
|
| 56 |
+
"image_mean": [
|
| 57 |
+
0.0,
|
| 58 |
+
0.0,
|
| 59 |
+
0.0
|
| 60 |
+
],
|
| 61 |
+
"image_std": [
|
| 62 |
+
1.0,
|
| 63 |
+
1.0,
|
| 64 |
+
1.0
|
| 65 |
+
],
|
| 66 |
+
"max_soft_tokens": 70,
|
| 67 |
+
"num_frames": 32,
|
| 68 |
+
"patch_size": 16,
|
| 69 |
+
"pooling_kernel_size": 3,
|
| 70 |
+
"resample": 3,
|
| 71 |
+
"rescale_factor": 0.00392156862745098,
|
| 72 |
+
"return_metadata": false,
|
| 73 |
+
"video_processor_type": "Gemma4VideoProcessor"
|
| 74 |
+
}
|
| 75 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
|
| 3 |
+
size 32169626
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"audio_token": "<|audio|>",
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"boa_token": "<|audio>",
|
| 5 |
+
"boi_token": "<|image>",
|
| 6 |
+
"bos_token": "<bos>",
|
| 7 |
+
"eoa_token": "<audio|>",
|
| 8 |
+
"eoc_token": "<channel|>",
|
| 9 |
+
"eoi_token": "<image|>",
|
| 10 |
+
"eos_token": "<turn|>",
|
| 11 |
+
"eot_token": "<turn|>",
|
| 12 |
+
"escape_token": "<|\"|>",
|
| 13 |
+
"etc_token": "<tool_call|>",
|
| 14 |
+
"etd_token": "<tool|>",
|
| 15 |
+
"etr_token": "<tool_response|>",
|
| 16 |
+
"extra_special_tokens": [
|
| 17 |
+
"<|video|>"
|
| 18 |
+
],
|
| 19 |
+
"image_token": "<|image|>",
|
| 20 |
+
"is_local": false,
|
| 21 |
+
"mask_token": "<mask>",
|
| 22 |
+
"model_max_length": 131072,
|
| 23 |
+
"model_specific_special_tokens": {
|
| 24 |
+
"audio_token": "<|audio|>",
|
| 25 |
+
"boa_token": "<|audio>",
|
| 26 |
+
"boi_token": "<|image>",
|
| 27 |
+
"eoa_token": "<audio|>",
|
| 28 |
+
"eoc_token": "<channel|>",
|
| 29 |
+
"eoi_token": "<image|>",
|
| 30 |
+
"eot_token": "<turn|>",
|
| 31 |
+
"escape_token": "<|\"|>",
|
| 32 |
+
"etc_token": "<tool_call|>",
|
| 33 |
+
"etd_token": "<tool|>",
|
| 34 |
+
"etr_token": "<tool_response|>",
|
| 35 |
+
"image_token": "<|image|>",
|
| 36 |
+
"soc_token": "<|channel>",
|
| 37 |
+
"sot_token": "<|turn>",
|
| 38 |
+
"stc_token": "<|tool_call>",
|
| 39 |
+
"std_token": "<|tool>",
|
| 40 |
+
"str_token": "<|tool_response>",
|
| 41 |
+
"think_token": "<|think|>"
|
| 42 |
+
},
|
| 43 |
+
"pad_token": "<pad>",
|
| 44 |
+
"padding_side": "right",
|
| 45 |
+
"processor_class": "Gemma4Processor",
|
| 46 |
+
"response_schema": {
|
| 47 |
+
"properties": {
|
| 48 |
+
"content": {
|
| 49 |
+
"type": "string"
|
| 50 |
+
},
|
| 51 |
+
"role": {
|
| 52 |
+
"const": "assistant"
|
| 53 |
+
},
|
| 54 |
+
"thinking": {
|
| 55 |
+
"type": "string"
|
| 56 |
+
},
|
| 57 |
+
"tool_calls": {
|
| 58 |
+
"items": {
|
| 59 |
+
"properties": {
|
| 60 |
+
"function": {
|
| 61 |
+
"properties": {
|
| 62 |
+
"arguments": {
|
| 63 |
+
"additionalProperties": {},
|
| 64 |
+
"type": "object",
|
| 65 |
+
"x-parser": "gemma4-tool-call"
|
| 66 |
+
},
|
| 67 |
+
"name": {
|
| 68 |
+
"type": "string"
|
| 69 |
+
}
|
| 70 |
+
},
|
| 71 |
+
"type": "object",
|
| 72 |
+
"x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
|
| 73 |
+
},
|
| 74 |
+
"type": {
|
| 75 |
+
"const": "function"
|
| 76 |
+
}
|
| 77 |
+
},
|
| 78 |
+
"type": "object"
|
| 79 |
+
},
|
| 80 |
+
"type": "array",
|
| 81 |
+
"x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
|
| 82 |
+
}
|
| 83 |
+
},
|
| 84 |
+
"type": "object",
|
| 85 |
+
"x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<content>(?:(?!\\<\\|tool_call\\>)(?!\\<turn\\|\\>).)+)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?:\\<turn\\|\\>)?"
|
| 86 |
+
},
|
| 87 |
+
"soc_token": "<|channel>",
|
| 88 |
+
"sot_token": "<|turn>",
|
| 89 |
+
"stc_token": "<|tool_call>",
|
| 90 |
+
"std_token": "<|tool>",
|
| 91 |
+
"str_token": "<|tool_response>",
|
| 92 |
+
"think_token": "<|think|>",
|
| 93 |
+
"tokenizer_class": "GemmaTokenizer",
|
| 94 |
+
"unk_token": "<unk>",
|
| 95 |
+
"chat_template": "{{ bos_token }}{%- if messages[0]['role'] == 'system' -%}\n {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n {%- set first_user_prefix = \"\" -%}\n {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif -%}\n {%- if (message['role'] == 'assistant') -%}\n {%- set role = \"model\" -%}\n {%- else -%}\n {%- set role = message['role'] -%}\n {%- endif -%}\n {%- if message['content'] is string -%}\n {%- set content = message['content'] | trim -%}\n {%- else -%}\n {%- set content = '' -%}\n {%- endif -%}\n {%- if role == \"model\" -%}\n {%- set reasoning_content = '' -%}\n {%- if message['reasoning_content'] is defined and message['reasoning_content'] is string -%}\n {%- set reasoning_content = message['reasoning_content'] | trim -%}\n {%- elif message['thinking'] is defined and message['thinking'] is string -%}\n {%- set reasoning_content = message['thinking'] | trim -%}\n {%- elif message['reasoning'] is defined and message['reasoning'] is string -%}\n {%- set reasoning_content = message['reasoning'] | trim -%}\n {%- endif -%}\n {%- if reasoning_content == '' and message['content'] is string and '<|channel>thought' in content and '<channel|>' in content -%}\n {%- set reasoning_content = content.split('<|channel>thought', 1)[1].split('<channel|>', 1)[0].strip('\n') -%}\n {%- set content = content.split('<channel|>', 1)[1].lstrip('\n') -%}\n {%- endif -%}\n {%- if reasoning_content == '' and message['content'] is string and '<think>' in content and '</think>' in content -%}\n {%- set reasoning_content = content.split('</think>', 1)[0].rstrip('\n').split('<think>', 1)[-1].lstrip('\n') -%}\n {%- set content = content.split('</think>', 1)[1].lstrip('\n') -%}\n {%- endif -%}\n {%- endif -%}\n {{ '<|turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n {%- if role == \"model\" -%}\n {%- if reasoning_content -%}\n {{ '<|channel>thought\n' + reasoning_content + '<channel|>' }}\n {%- else -%}\n {{ '<|channel>thought\n<channel|>' }}\n {%- endif -%}\n {%- endif -%}\n {%- if message['content'] is string -%}\n {{ content }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'audio' -%}\n {{ '<|audio|>' }}\n {%- elif item['type'] == 'image' -%}\n {{ '<|image|>' }}\n {%- elif item['type'] == 'video' -%}\n {{ '<|video|>' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '<turn|>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{ '<|turn>model\n' }}\n {%- if enable_thinking | default(true) -%}\n {{ '<|channel>thought\n' }}\n {%- else -%}\n {{ '<|channel>thought\n<channel|>' }}\n {%- endif -%}\n{%- endif -%}\n"
|
| 96 |
+
}
|