(Trained with Unsloth)
Browse files- config.json +101 -0
- tokenizer_config.json +3 -2
config.json
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Gemma3ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"boi_token_index": 255999,
|
| 6 |
+
"bos_token_id": 2,
|
| 7 |
+
"torch_dtype": "float16",
|
| 8 |
+
"eoi_token_index": 256000,
|
| 9 |
+
"eos_token_id": 106,
|
| 10 |
+
"image_token_index": 262144,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"mm_tokens_per_image": 256,
|
| 13 |
+
"model_type": "gemma3",
|
| 14 |
+
"pad_token_id": 0,
|
| 15 |
+
"text_config": {
|
| 16 |
+
"_sliding_window_pattern": 6,
|
| 17 |
+
"attention_bias": false,
|
| 18 |
+
"attention_dropout": 0.0,
|
| 19 |
+
"attn_logit_softcapping": null,
|
| 20 |
+
"cache_implementation": "hybrid",
|
| 21 |
+
"torch_dtype": "float16",
|
| 22 |
+
"final_logit_softcapping": null,
|
| 23 |
+
"head_dim": 256,
|
| 24 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 25 |
+
"hidden_size": 2560,
|
| 26 |
+
"initializer_range": 0.02,
|
| 27 |
+
"intermediate_size": 10240,
|
| 28 |
+
"layer_types": [
|
| 29 |
+
"sliding_attention",
|
| 30 |
+
"sliding_attention",
|
| 31 |
+
"sliding_attention",
|
| 32 |
+
"sliding_attention",
|
| 33 |
+
"sliding_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"sliding_attention",
|
| 36 |
+
"sliding_attention",
|
| 37 |
+
"sliding_attention",
|
| 38 |
+
"sliding_attention",
|
| 39 |
+
"sliding_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"sliding_attention",
|
| 42 |
+
"sliding_attention",
|
| 43 |
+
"sliding_attention",
|
| 44 |
+
"sliding_attention",
|
| 45 |
+
"sliding_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"sliding_attention",
|
| 48 |
+
"sliding_attention",
|
| 49 |
+
"sliding_attention",
|
| 50 |
+
"sliding_attention",
|
| 51 |
+
"sliding_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"sliding_attention",
|
| 54 |
+
"sliding_attention",
|
| 55 |
+
"sliding_attention",
|
| 56 |
+
"sliding_attention",
|
| 57 |
+
"sliding_attention",
|
| 58 |
+
"full_attention",
|
| 59 |
+
"sliding_attention",
|
| 60 |
+
"sliding_attention",
|
| 61 |
+
"sliding_attention",
|
| 62 |
+
"sliding_attention"
|
| 63 |
+
],
|
| 64 |
+
"max_position_embeddings": 131072,
|
| 65 |
+
"model_type": "gemma3_text",
|
| 66 |
+
"num_attention_heads": 8,
|
| 67 |
+
"num_hidden_layers": 34,
|
| 68 |
+
"num_key_value_heads": 4,
|
| 69 |
+
"query_pre_attn_scalar": 256,
|
| 70 |
+
"rms_norm_eps": 1e-06,
|
| 71 |
+
"rope_local_base_freq": 10000,
|
| 72 |
+
"rope_scaling": {
|
| 73 |
+
"factor": 8.0,
|
| 74 |
+
"rope_type": "linear"
|
| 75 |
+
},
|
| 76 |
+
"rope_theta": 1000000,
|
| 77 |
+
"sliding_window": 1024,
|
| 78 |
+
"sliding_window_pattern": 6,
|
| 79 |
+
"use_bidirectional_attention": false,
|
| 80 |
+
"use_cache": true,
|
| 81 |
+
"vocab_size": 262208
|
| 82 |
+
},
|
| 83 |
+
"transformers_version": "4.57.2",
|
| 84 |
+
"unsloth_fixed": true,
|
| 85 |
+
"unsloth_version": "2025.11.4",
|
| 86 |
+
"vision_config": {
|
| 87 |
+
"attention_dropout": 0.0,
|
| 88 |
+
"torch_dtype": "float16",
|
| 89 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 90 |
+
"hidden_size": 1152,
|
| 91 |
+
"image_size": 896,
|
| 92 |
+
"intermediate_size": 4304,
|
| 93 |
+
"layer_norm_eps": 1e-06,
|
| 94 |
+
"model_type": "siglip_vision_model",
|
| 95 |
+
"num_attention_heads": 16,
|
| 96 |
+
"num_channels": 3,
|
| 97 |
+
"num_hidden_layers": 27,
|
| 98 |
+
"patch_size": 14,
|
| 99 |
+
"vision_use_head": false
|
| 100 |
+
}
|
| 101 |
+
}
|
tokenizer_config.json
CHANGED
|
@@ -51342,5 +51342,6 @@
|
|
| 51342 |
"spaces_between_special_tokens": false,
|
| 51343 |
"tokenizer_class": "GemmaTokenizer",
|
| 51344 |
"unk_token": "<unk>",
|
| 51345 |
-
"use_default_system_prompt": false
|
| 51346 |
-
}
|
|
|
|
|
|
| 51342 |
"spaces_between_special_tokens": false,
|
| 51343 |
"tokenizer_class": "GemmaTokenizer",
|
| 51344 |
"unk_token": "<unk>",
|
| 51345 |
+
"use_default_system_prompt": false,
|
| 51346 |
+
"chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n {%- if messages[0]['content'] is string -%}\n {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n {%- else -%}\n {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n {%- endif -%}\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 {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n {%- if message['content'] is string -%}\n {{ message['content'] | trim }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'image' -%}\n {{ '<start_of_image>' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{'<start_of_turn>model\n'}}\n{%- endif -%}\n"
|
| 51347 |
+
}
|