Add tiny processor fixture for testing (qwen3_vl)
Browse files- chat_template.json +4 -0
- config.json +69 -0
- generation_config.json +14 -0
- preprocessor_config.json +21 -0
- tokenizer.json +1032 -0
- tokenizer_config.json +239 -0
- video_preprocessor_config.json +21 -0
chat_template.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content_item in message.content %}\n {%- if 'text' in content_item %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and message.content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
|
| 3 |
+
}
|
| 4 |
+
|
config.json
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3VLMoeForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"image_token_id": 151655,
|
| 6 |
+
"model_type": "qwen3_vl_moe",
|
| 7 |
+
"text_config": {
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"bos_token_id": 151643,
|
| 11 |
+
"decoder_sparse_step": 1,
|
| 12 |
+
"dtype": "bfloat16",
|
| 13 |
+
"eos_token_id": 151645,
|
| 14 |
+
"head_dim": 128,
|
| 15 |
+
"hidden_act": "silu",
|
| 16 |
+
"hidden_size": 4096,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 12288,
|
| 19 |
+
"max_position_embeddings": 262144,
|
| 20 |
+
"mlp_only_layers": [],
|
| 21 |
+
"model_type": "qwen3_vl_moe_text",
|
| 22 |
+
"moe_intermediate_size": 1536,
|
| 23 |
+
"norm_topk_prob": true,
|
| 24 |
+
"num_attention_heads": 64,
|
| 25 |
+
"num_experts": 128,
|
| 26 |
+
"num_experts_per_tok": 8,
|
| 27 |
+
"num_hidden_layers": 94,
|
| 28 |
+
"num_key_value_heads": 4,
|
| 29 |
+
"rms_norm_eps": 1e-06,
|
| 30 |
+
"rope_scaling": {
|
| 31 |
+
"mrope_interleaved": true,
|
| 32 |
+
"mrope_section": [
|
| 33 |
+
24,
|
| 34 |
+
20,
|
| 35 |
+
20
|
| 36 |
+
],
|
| 37 |
+
"rope_type": "default"
|
| 38 |
+
},
|
| 39 |
+
"rope_theta": 5000000,
|
| 40 |
+
"use_cache": true,
|
| 41 |
+
"vocab_size": 151936
|
| 42 |
+
},
|
| 43 |
+
"tie_word_embeddings": false,
|
| 44 |
+
"transformers_version": "4.57.0.dev0",
|
| 45 |
+
"video_token_id": 151656,
|
| 46 |
+
"vision_config": {
|
| 47 |
+
"deepstack_visual_indexes": [
|
| 48 |
+
8,
|
| 49 |
+
16,
|
| 50 |
+
24
|
| 51 |
+
],
|
| 52 |
+
"depth": 27,
|
| 53 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 54 |
+
"hidden_size": 1152,
|
| 55 |
+
"in_channels": 3,
|
| 56 |
+
"initializer_range": 0.02,
|
| 57 |
+
"intermediate_size": 4304,
|
| 58 |
+
"model_type": "qwen3_vl_moe",
|
| 59 |
+
"num_heads": 16,
|
| 60 |
+
"num_position_embeddings": 2304,
|
| 61 |
+
"out_hidden_size": 4096,
|
| 62 |
+
"patch_size": 16,
|
| 63 |
+
"spatial_merge_size": 2,
|
| 64 |
+
"temporal_patch_size": 2
|
| 65 |
+
},
|
| 66 |
+
"vision_end_token_id": 151653,
|
| 67 |
+
"vision_start_token_id": 151652,
|
| 68 |
+
"vocab_size": 500
|
| 69 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"pad_token_id": 151643,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
151645,
|
| 7 |
+
151643
|
| 8 |
+
],
|
| 9 |
+
"top_p": 0.8,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"temperature": 0.7,
|
| 12 |
+
"repetition_penalty": 1.0,
|
| 13 |
+
"transformers_version": "4.56.0"
|
| 14 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 3136,
|
| 4 |
+
"shortest_edge": 784
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 4,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"image_processor_type": "Qwen2VLImageProcessorFast"
|
| 21 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,1032 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 500,
|
| 8 |
+
"content": "<|endoftext|>",
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"special": true
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"id": 501,
|
| 17 |
+
"content": "<|im_start|>",
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"special": true
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"id": 502,
|
| 26 |
+
"content": "<|im_end|>",
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"special": true
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 503,
|
| 35 |
+
"content": "<|object_ref_start|>",
|
| 36 |
+
"normalized": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"single_word": false,
|
| 40 |
+
"special": true
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"id": 504,
|
| 44 |
+
"content": "<|object_ref_end|>",
|
| 45 |
+
"normalized": false,
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"id": 505,
|
| 53 |
+
"content": "<|box_start|>",
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"id": 506,
|
| 62 |
+
"content": "<|box_end|>",
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"id": 507,
|
| 71 |
+
"content": "<|quad_start|>",
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"lstrip": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"id": 508,
|
| 80 |
+
"content": "<|quad_end|>",
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"lstrip": false,
|
| 83 |
+
"rstrip": false,
|
| 84 |
+
"single_word": false,
|
| 85 |
+
"special": true
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"id": 509,
|
| 89 |
+
"content": "<|vision_start|>",
|
| 90 |
+
"normalized": false,
|
| 91 |
+
"lstrip": false,
|
| 92 |
+
"rstrip": false,
|
| 93 |
+
"single_word": false,
|
| 94 |
+
"special": true
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"id": 510,
|
| 98 |
+
"content": "<|vision_end|>",
|
| 99 |
+
"normalized": false,
|
| 100 |
+
"lstrip": false,
|
| 101 |
+
"rstrip": false,
|
| 102 |
+
"single_word": false,
|
| 103 |
+
"special": true
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"id": 511,
|
| 107 |
+
"content": "<|vision_pad|>",
|
| 108 |
+
"normalized": false,
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"rstrip": false,
|
| 111 |
+
"single_word": false,
|
| 112 |
+
"special": true
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"id": 512,
|
| 116 |
+
"content": "<|image_pad|>",
|
| 117 |
+
"normalized": false,
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"id": 513,
|
| 125 |
+
"content": "<|video_pad|>",
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"id": 514,
|
| 134 |
+
"content": "<tool_call>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"id": 515,
|
| 143 |
+
"content": "</tool_call>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"id": 516,
|
| 152 |
+
"content": "<|fim_prefix|>",
|
| 153 |
+
"lstrip": false,
|
| 154 |
+
"normalized": false,
|
| 155 |
+
"rstrip": false,
|
| 156 |
+
"single_word": false,
|
| 157 |
+
"special": false
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"id": 517,
|
| 161 |
+
"content": "<|fim_middle|>",
|
| 162 |
+
"lstrip": false,
|
| 163 |
+
"normalized": false,
|
| 164 |
+
"rstrip": false,
|
| 165 |
+
"single_word": false,
|
| 166 |
+
"special": false
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"id": 518,
|
| 170 |
+
"content": "<|fim_suffix|>",
|
| 171 |
+
"lstrip": false,
|
| 172 |
+
"normalized": false,
|
| 173 |
+
"rstrip": false,
|
| 174 |
+
"single_word": false,
|
| 175 |
+
"special": false
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"id": 519,
|
| 179 |
+
"content": "<|fim_pad|>",
|
| 180 |
+
"lstrip": false,
|
| 181 |
+
"normalized": false,
|
| 182 |
+
"rstrip": false,
|
| 183 |
+
"single_word": false,
|
| 184 |
+
"special": false
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"id": 520,
|
| 188 |
+
"content": "<|repo_name|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": false
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"id": 521,
|
| 197 |
+
"content": "<|file_sep|>",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": false
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"id": 522,
|
| 206 |
+
"content": "<tool_response>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"id": 523,
|
| 215 |
+
"content": "</tool_response>",
|
| 216 |
+
"lstrip": false,
|
| 217 |
+
"normalized": false,
|
| 218 |
+
"rstrip": false,
|
| 219 |
+
"single_word": false,
|
| 220 |
+
"special": false
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"id": 524,
|
| 224 |
+
"content": "<think>",
|
| 225 |
+
"lstrip": false,
|
| 226 |
+
"normalized": false,
|
| 227 |
+
"rstrip": false,
|
| 228 |
+
"single_word": false,
|
| 229 |
+
"special": false
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"id": 525,
|
| 233 |
+
"content": "</think>",
|
| 234 |
+
"lstrip": false,
|
| 235 |
+
"normalized": false,
|
| 236 |
+
"rstrip": false,
|
| 237 |
+
"single_word": false,
|
| 238 |
+
"special": false
|
| 239 |
+
}
|
| 240 |
+
],
|
| 241 |
+
"normalizer": {
|
| 242 |
+
"type": "NFC"
|
| 243 |
+
},
|
| 244 |
+
"pre_tokenizer": {
|
| 245 |
+
"type": "Sequence",
|
| 246 |
+
"pretokenizers": [
|
| 247 |
+
{
|
| 248 |
+
"type": "Split",
|
| 249 |
+
"pattern": {
|
| 250 |
+
"Regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
|
| 251 |
+
},
|
| 252 |
+
"behavior": "Isolated",
|
| 253 |
+
"invert": false
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"type": "ByteLevel",
|
| 257 |
+
"add_prefix_space": false,
|
| 258 |
+
"trim_offsets": false,
|
| 259 |
+
"use_regex": false
|
| 260 |
+
}
|
| 261 |
+
]
|
| 262 |
+
},
|
| 263 |
+
"post_processor": {
|
| 264 |
+
"type": "ByteLevel",
|
| 265 |
+
"add_prefix_space": false,
|
| 266 |
+
"trim_offsets": false,
|
| 267 |
+
"use_regex": false
|
| 268 |
+
},
|
| 269 |
+
"decoder": {
|
| 270 |
+
"type": "ByteLevel",
|
| 271 |
+
"add_prefix_space": false,
|
| 272 |
+
"trim_offsets": false,
|
| 273 |
+
"use_regex": false
|
| 274 |
+
},
|
| 275 |
+
"model": {
|
| 276 |
+
"type": "BPE",
|
| 277 |
+
"dropout": null,
|
| 278 |
+
"unk_token": null,
|
| 279 |
+
"continuing_subword_prefix": "",
|
| 280 |
+
"end_of_word_suffix": "",
|
| 281 |
+
"fuse_unk": false,
|
| 282 |
+
"byte_fallback": false,
|
| 283 |
+
"vocab": {
|
| 284 |
+
"!": 0,
|
| 285 |
+
"\"": 1,
|
| 286 |
+
"#": 2,
|
| 287 |
+
"$": 3,
|
| 288 |
+
"%": 4,
|
| 289 |
+
"&": 5,
|
| 290 |
+
"'": 6,
|
| 291 |
+
"(": 7,
|
| 292 |
+
")": 8,
|
| 293 |
+
"*": 9,
|
| 294 |
+
"+": 10,
|
| 295 |
+
",": 11,
|
| 296 |
+
"-": 12,
|
| 297 |
+
".": 13,
|
| 298 |
+
"/": 14,
|
| 299 |
+
"0": 15,
|
| 300 |
+
"1": 16,
|
| 301 |
+
"2": 17,
|
| 302 |
+
"3": 18,
|
| 303 |
+
"4": 19,
|
| 304 |
+
"5": 20,
|
| 305 |
+
"6": 21,
|
| 306 |
+
"7": 22,
|
| 307 |
+
"8": 23,
|
| 308 |
+
"9": 24,
|
| 309 |
+
":": 25,
|
| 310 |
+
";": 26,
|
| 311 |
+
"<": 27,
|
| 312 |
+
"=": 28,
|
| 313 |
+
">": 29,
|
| 314 |
+
"?": 30,
|
| 315 |
+
"@": 31,
|
| 316 |
+
"A": 32,
|
| 317 |
+
"B": 33,
|
| 318 |
+
"C": 34,
|
| 319 |
+
"D": 35,
|
| 320 |
+
"E": 36,
|
| 321 |
+
"F": 37,
|
| 322 |
+
"G": 38,
|
| 323 |
+
"H": 39,
|
| 324 |
+
"I": 40,
|
| 325 |
+
"J": 41,
|
| 326 |
+
"K": 42,
|
| 327 |
+
"L": 43,
|
| 328 |
+
"M": 44,
|
| 329 |
+
"N": 45,
|
| 330 |
+
"O": 46,
|
| 331 |
+
"P": 47,
|
| 332 |
+
"Q": 48,
|
| 333 |
+
"R": 49,
|
| 334 |
+
"S": 50,
|
| 335 |
+
"T": 51,
|
| 336 |
+
"U": 52,
|
| 337 |
+
"V": 53,
|
| 338 |
+
"W": 54,
|
| 339 |
+
"X": 55,
|
| 340 |
+
"Y": 56,
|
| 341 |
+
"Z": 57,
|
| 342 |
+
"[": 58,
|
| 343 |
+
"\\": 59,
|
| 344 |
+
"]": 60,
|
| 345 |
+
"^": 61,
|
| 346 |
+
"_": 62,
|
| 347 |
+
"`": 63,
|
| 348 |
+
"a": 64,
|
| 349 |
+
"b": 65,
|
| 350 |
+
"c": 66,
|
| 351 |
+
"d": 67,
|
| 352 |
+
"e": 68,
|
| 353 |
+
"f": 69,
|
| 354 |
+
"g": 70,
|
| 355 |
+
"h": 71,
|
| 356 |
+
"i": 72,
|
| 357 |
+
"j": 73,
|
| 358 |
+
"k": 74,
|
| 359 |
+
"l": 75,
|
| 360 |
+
"m": 76,
|
| 361 |
+
"n": 77,
|
| 362 |
+
"o": 78,
|
| 363 |
+
"p": 79,
|
| 364 |
+
"q": 80,
|
| 365 |
+
"r": 81,
|
| 366 |
+
"s": 82,
|
| 367 |
+
"t": 83,
|
| 368 |
+
"u": 84,
|
| 369 |
+
"v": 85,
|
| 370 |
+
"w": 86,
|
| 371 |
+
"x": 87,
|
| 372 |
+
"y": 88,
|
| 373 |
+
"z": 89,
|
| 374 |
+
"{": 90,
|
| 375 |
+
"|": 91,
|
| 376 |
+
"}": 92,
|
| 377 |
+
"~": 93,
|
| 378 |
+
"¡": 94,
|
| 379 |
+
"¢": 95,
|
| 380 |
+
"£": 96,
|
| 381 |
+
"¤": 97,
|
| 382 |
+
"¥": 98,
|
| 383 |
+
"¦": 99,
|
| 384 |
+
"§": 100,
|
| 385 |
+
"¨": 101,
|
| 386 |
+
"©": 102,
|
| 387 |
+
"ª": 103,
|
| 388 |
+
"«": 104,
|
| 389 |
+
"¬": 105,
|
| 390 |
+
"®": 106,
|
| 391 |
+
"¯": 107,
|
| 392 |
+
"°": 108,
|
| 393 |
+
"±": 109,
|
| 394 |
+
"²": 110,
|
| 395 |
+
"³": 111,
|
| 396 |
+
"´": 112,
|
| 397 |
+
"µ": 113,
|
| 398 |
+
"¶": 114,
|
| 399 |
+
"·": 115,
|
| 400 |
+
"¸": 116,
|
| 401 |
+
"¹": 117,
|
| 402 |
+
"º": 118,
|
| 403 |
+
"»": 119,
|
| 404 |
+
"¼": 120,
|
| 405 |
+
"½": 121,
|
| 406 |
+
"¾": 122,
|
| 407 |
+
"¿": 123,
|
| 408 |
+
"À": 124,
|
| 409 |
+
"Á": 125,
|
| 410 |
+
"Â": 126,
|
| 411 |
+
"Ã": 127,
|
| 412 |
+
"Ä": 128,
|
| 413 |
+
"Å": 129,
|
| 414 |
+
"Æ": 130,
|
| 415 |
+
"Ç": 131,
|
| 416 |
+
"È": 132,
|
| 417 |
+
"É": 133,
|
| 418 |
+
"Ê": 134,
|
| 419 |
+
"Ë": 135,
|
| 420 |
+
"Ì": 136,
|
| 421 |
+
"Í": 137,
|
| 422 |
+
"Î": 138,
|
| 423 |
+
"Ï": 139,
|
| 424 |
+
"Ð": 140,
|
| 425 |
+
"Ñ": 141,
|
| 426 |
+
"Ò": 142,
|
| 427 |
+
"Ó": 143,
|
| 428 |
+
"Ô": 144,
|
| 429 |
+
"Õ": 145,
|
| 430 |
+
"Ö": 146,
|
| 431 |
+
"×": 147,
|
| 432 |
+
"Ø": 148,
|
| 433 |
+
"Ù": 149,
|
| 434 |
+
"Ú": 150,
|
| 435 |
+
"Û": 151,
|
| 436 |
+
"Ü": 152,
|
| 437 |
+
"Ý": 153,
|
| 438 |
+
"Þ": 154,
|
| 439 |
+
"ß": 155,
|
| 440 |
+
"à": 156,
|
| 441 |
+
"á": 157,
|
| 442 |
+
"â": 158,
|
| 443 |
+
"ã": 159,
|
| 444 |
+
"ä": 160,
|
| 445 |
+
"å": 161,
|
| 446 |
+
"æ": 162,
|
| 447 |
+
"ç": 163,
|
| 448 |
+
"è": 164,
|
| 449 |
+
"é": 165,
|
| 450 |
+
"ê": 166,
|
| 451 |
+
"ë": 167,
|
| 452 |
+
"ì": 168,
|
| 453 |
+
"í": 169,
|
| 454 |
+
"î": 170,
|
| 455 |
+
"ï": 171,
|
| 456 |
+
"ð": 172,
|
| 457 |
+
"ñ": 173,
|
| 458 |
+
"ò": 174,
|
| 459 |
+
"ó": 175,
|
| 460 |
+
"ô": 176,
|
| 461 |
+
"õ": 177,
|
| 462 |
+
"ö": 178,
|
| 463 |
+
"÷": 179,
|
| 464 |
+
"ø": 180,
|
| 465 |
+
"ù": 181,
|
| 466 |
+
"ú": 182,
|
| 467 |
+
"û": 183,
|
| 468 |
+
"ü": 184,
|
| 469 |
+
"ý": 185,
|
| 470 |
+
"þ": 186,
|
| 471 |
+
"ÿ": 187,
|
| 472 |
+
"Ā": 188,
|
| 473 |
+
"ā": 189,
|
| 474 |
+
"Ă": 190,
|
| 475 |
+
"ă": 191,
|
| 476 |
+
"Ą": 192,
|
| 477 |
+
"ą": 193,
|
| 478 |
+
"Ć": 194,
|
| 479 |
+
"ć": 195,
|
| 480 |
+
"Ĉ": 196,
|
| 481 |
+
"ĉ": 197,
|
| 482 |
+
"Ċ": 198,
|
| 483 |
+
"ċ": 199,
|
| 484 |
+
"Č": 200,
|
| 485 |
+
"č": 201,
|
| 486 |
+
"Ď": 202,
|
| 487 |
+
"ď": 203,
|
| 488 |
+
"Đ": 204,
|
| 489 |
+
"đ": 205,
|
| 490 |
+
"Ē": 206,
|
| 491 |
+
"ē": 207,
|
| 492 |
+
"Ĕ": 208,
|
| 493 |
+
"ĕ": 209,
|
| 494 |
+
"Ė": 210,
|
| 495 |
+
"ė": 211,
|
| 496 |
+
"Ę": 212,
|
| 497 |
+
"ę": 213,
|
| 498 |
+
"Ě": 214,
|
| 499 |
+
"ě": 215,
|
| 500 |
+
"Ĝ": 216,
|
| 501 |
+
"ĝ": 217,
|
| 502 |
+
"Ğ": 218,
|
| 503 |
+
"ğ": 219,
|
| 504 |
+
"Ġ": 220,
|
| 505 |
+
"ġ": 221,
|
| 506 |
+
"Ģ": 222,
|
| 507 |
+
"ģ": 223,
|
| 508 |
+
"Ĥ": 224,
|
| 509 |
+
"ĥ": 225,
|
| 510 |
+
"Ħ": 226,
|
| 511 |
+
"ħ": 227,
|
| 512 |
+
"Ĩ": 228,
|
| 513 |
+
"ĩ": 229,
|
| 514 |
+
"Ī": 230,
|
| 515 |
+
"ī": 231,
|
| 516 |
+
"Ĭ": 232,
|
| 517 |
+
"ĭ": 233,
|
| 518 |
+
"Į": 234,
|
| 519 |
+
"į": 235,
|
| 520 |
+
"İ": 236,
|
| 521 |
+
"ı": 237,
|
| 522 |
+
"IJ": 238,
|
| 523 |
+
"ij": 239,
|
| 524 |
+
"Ĵ": 240,
|
| 525 |
+
"ĵ": 241,
|
| 526 |
+
"Ķ": 242,
|
| 527 |
+
"ķ": 243,
|
| 528 |
+
"ĸ": 244,
|
| 529 |
+
"Ĺ": 245,
|
| 530 |
+
"ĺ": 246,
|
| 531 |
+
"Ļ": 247,
|
| 532 |
+
"ļ": 248,
|
| 533 |
+
"Ľ": 249,
|
| 534 |
+
"ľ": 250,
|
| 535 |
+
"Ŀ": 251,
|
| 536 |
+
"ŀ": 252,
|
| 537 |
+
"Ł": 253,
|
| 538 |
+
"ł": 254,
|
| 539 |
+
"Ń": 255,
|
| 540 |
+
"ĠĠ": 256,
|
| 541 |
+
"ĠĠĠĠ": 257,
|
| 542 |
+
"in": 258,
|
| 543 |
+
"Ġt": 259,
|
| 544 |
+
"ĠĠĠĠĠĠĠĠ": 260,
|
| 545 |
+
"er": 261,
|
| 546 |
+
"ĠĠĠ": 262,
|
| 547 |
+
"on": 263,
|
| 548 |
+
"Ġa": 264,
|
| 549 |
+
"re": 265,
|
| 550 |
+
"at": 266,
|
| 551 |
+
"st": 267,
|
| 552 |
+
"en": 268,
|
| 553 |
+
"or": 269,
|
| 554 |
+
"Ġth": 270,
|
| 555 |
+
"ĊĊ": 271,
|
| 556 |
+
"Ġc": 272,
|
| 557 |
+
"le": 273,
|
| 558 |
+
"Ġs": 274,
|
| 559 |
+
"it": 275,
|
| 560 |
+
"an": 276,
|
| 561 |
+
"ar": 277,
|
| 562 |
+
"al": 278,
|
| 563 |
+
"Ġthe": 279,
|
| 564 |
+
";Ċ": 280,
|
| 565 |
+
"Ġp": 281,
|
| 566 |
+
"Ġf": 282,
|
| 567 |
+
"ou": 283,
|
| 568 |
+
"Ġ=": 284,
|
| 569 |
+
"is": 285,
|
| 570 |
+
"ĠĠĠĠĠĠĠ": 286,
|
| 571 |
+
"ing": 287,
|
| 572 |
+
"es": 288,
|
| 573 |
+
"Ġw": 289,
|
| 574 |
+
"ion": 290,
|
| 575 |
+
"ed": 291,
|
| 576 |
+
"ic": 292,
|
| 577 |
+
"Ġb": 293,
|
| 578 |
+
"Ġd": 294,
|
| 579 |
+
"et": 295,
|
| 580 |
+
"Ġm": 296,
|
| 581 |
+
"Ġo": 297,
|
| 582 |
+
"ĉĉ": 298,
|
| 583 |
+
"ro": 299,
|
| 584 |
+
"as": 300,
|
| 585 |
+
"el": 301,
|
| 586 |
+
"ct": 302,
|
| 587 |
+
"nd": 303,
|
| 588 |
+
"Ġin": 304,
|
| 589 |
+
"Ġh": 305,
|
| 590 |
+
"ent": 306,
|
| 591 |
+
"id": 307,
|
| 592 |
+
"Ġn": 308,
|
| 593 |
+
"am": 309,
|
| 594 |
+
"ĠĠĠĠĠĠĠĠĠĠĠ": 310,
|
| 595 |
+
"Ġto": 311,
|
| 596 |
+
"Ġre": 312,
|
| 597 |
+
"--": 313,
|
| 598 |
+
"Ġ{": 314,
|
| 599 |
+
"Ġof": 315,
|
| 600 |
+
"om": 316,
|
| 601 |
+
");Ċ": 317,
|
| 602 |
+
"im": 318,
|
| 603 |
+
"čĊ": 319,
|
| 604 |
+
"Ġ(": 320,
|
| 605 |
+
"il": 321,
|
| 606 |
+
"//": 322,
|
| 607 |
+
"Ġand": 323,
|
| 608 |
+
"ur": 324,
|
| 609 |
+
"se": 325,
|
| 610 |
+
"Ġl": 326,
|
| 611 |
+
"ex": 327,
|
| 612 |
+
"ĠS": 328,
|
| 613 |
+
"ad": 329,
|
| 614 |
+
"Ġ\"": 330,
|
| 615 |
+
"ch": 331,
|
| 616 |
+
"ut": 332,
|
| 617 |
+
"if": 333,
|
| 618 |
+
"**": 334,
|
| 619 |
+
"Ġ}": 335,
|
| 620 |
+
"em": 336,
|
| 621 |
+
"ol": 337,
|
| 622 |
+
"ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ": 338,
|
| 623 |
+
"th": 339,
|
| 624 |
+
")Ċ": 340,
|
| 625 |
+
"Ġ{Ċ": 341,
|
| 626 |
+
"Ġg": 342,
|
| 627 |
+
"ig": 343,
|
| 628 |
+
"iv": 344,
|
| 629 |
+
",Ċ": 345,
|
| 630 |
+
"ce": 346,
|
| 631 |
+
"od": 347,
|
| 632 |
+
"Ġv": 348,
|
| 633 |
+
"ate": 349,
|
| 634 |
+
"ĠT": 350,
|
| 635 |
+
"ag": 351,
|
| 636 |
+
"ay": 352,
|
| 637 |
+
"Ġ*": 353,
|
| 638 |
+
"ot": 354,
|
| 639 |
+
"us": 355,
|
| 640 |
+
"ĠC": 356,
|
| 641 |
+
"Ġst": 357,
|
| 642 |
+
"ĠI": 358,
|
| 643 |
+
"un": 359,
|
| 644 |
+
"ul": 360,
|
| 645 |
+
"ue": 361,
|
| 646 |
+
"ĠA": 362,
|
| 647 |
+
"ow": 363,
|
| 648 |
+
"Ġ'": 364,
|
| 649 |
+
"ew": 365,
|
| 650 |
+
"Ġ<": 366,
|
| 651 |
+
"ation": 367,
|
| 652 |
+
"()": 368,
|
| 653 |
+
"Ġfor": 369,
|
| 654 |
+
"ab": 370,
|
| 655 |
+
"ort": 371,
|
| 656 |
+
"um": 372,
|
| 657 |
+
"ame": 373,
|
| 658 |
+
"Ġis": 374,
|
| 659 |
+
"pe": 375,
|
| 660 |
+
"tr": 376,
|
| 661 |
+
"ck": 377,
|
| 662 |
+
"âĢ": 378,
|
| 663 |
+
"Ġy": 379,
|
| 664 |
+
"ist": 380,
|
| 665 |
+
"----": 381,
|
| 666 |
+
".ĊĊ": 382,
|
| 667 |
+
"he": 383,
|
| 668 |
+
"Ġe": 384,
|
| 669 |
+
"lo": 385,
|
| 670 |
+
"ĠM": 386,
|
| 671 |
+
"Ġbe": 387,
|
| 672 |
+
"ers": 388,
|
| 673 |
+
"Ġon": 389,
|
| 674 |
+
"Ġcon": 390,
|
| 675 |
+
"ap": 391,
|
| 676 |
+
"ub": 392,
|
| 677 |
+
"ĠP": 393,
|
| 678 |
+
"ĠĠĠĠĠĠĠĠĠĠĠĠĠĠĠ": 394,
|
| 679 |
+
"ass": 395,
|
| 680 |
+
"int": 396,
|
| 681 |
+
">Ċ": 397,
|
| 682 |
+
"ly": 398,
|
| 683 |
+
"urn": 399,
|
| 684 |
+
"Ġ$": 400,
|
| 685 |
+
";ĊĊ": 401,
|
| 686 |
+
"av": 402,
|
| 687 |
+
"port": 403,
|
| 688 |
+
"ir": 404,
|
| 689 |
+
"->": 405,
|
| 690 |
+
"nt": 406,
|
| 691 |
+
"ction": 407,
|
| 692 |
+
"end": 408,
|
| 693 |
+
"Ġde": 409,
|
| 694 |
+
"ith": 410,
|
| 695 |
+
"out": 411,
|
| 696 |
+
"turn": 412,
|
| 697 |
+
"our": 413,
|
| 698 |
+
"ĠĠĠĠĠ": 414,
|
| 699 |
+
"lic": 415,
|
| 700 |
+
"res": 416,
|
| 701 |
+
"pt": 417,
|
| 702 |
+
"==": 418,
|
| 703 |
+
"Ġthis": 419,
|
| 704 |
+
"Ġwh": 420,
|
| 705 |
+
"Ġif": 421,
|
| 706 |
+
"ĠD": 422,
|
| 707 |
+
"ver": 423,
|
| 708 |
+
"age": 424,
|
| 709 |
+
"ĠB": 425,
|
| 710 |
+
"ht": 426,
|
| 711 |
+
"ext": 427,
|
| 712 |
+
"=\"": 428,
|
| 713 |
+
"Ġthat": 429,
|
| 714 |
+
"****": 430,
|
| 715 |
+
"ĠR": 431,
|
| 716 |
+
"Ġit": 432,
|
| 717 |
+
"ess": 433,
|
| 718 |
+
"ĠF": 434,
|
| 719 |
+
"Ġr": 435,
|
| 720 |
+
"os": 436,
|
| 721 |
+
"and": 437,
|
| 722 |
+
"Ġas": 438,
|
| 723 |
+
"ect": 439,
|
| 724 |
+
"ke": 440,
|
| 725 |
+
"rom": 441,
|
| 726 |
+
"Ġ//": 442,
|
| 727 |
+
"con": 443,
|
| 728 |
+
"ĠL": 444,
|
| 729 |
+
"(\"": 445,
|
| 730 |
+
"qu": 446,
|
| 731 |
+
"lass": 447,
|
| 732 |
+
"Ġwith": 448,
|
| 733 |
+
"iz": 449,
|
| 734 |
+
"de": 450,
|
| 735 |
+
"ĠN": 451,
|
| 736 |
+
"Ġal": 452,
|
| 737 |
+
"op": 453,
|
| 738 |
+
"up": 454,
|
| 739 |
+
"get": 455,
|
| 740 |
+
"Ġ}Ċ": 456,
|
| 741 |
+
"ile": 457,
|
| 742 |
+
"Ġan": 458,
|
| 743 |
+
"ata": 459,
|
| 744 |
+
"ore": 460,
|
| 745 |
+
"ri": 461,
|
| 746 |
+
"Ġpro": 462,
|
| 747 |
+
";čĊ": 463,
|
| 748 |
+
"ĉĉĉĉ": 464,
|
| 749 |
+
"ter": 465,
|
| 750 |
+
"ain": 466,
|
| 751 |
+
"ĠW": 467,
|
| 752 |
+
"ĠE": 468,
|
| 753 |
+
"Ġcom": 469,
|
| 754 |
+
"Ġreturn": 470,
|
| 755 |
+
"art": 471,
|
| 756 |
+
"ĠH": 472,
|
| 757 |
+
"ack": 473,
|
| 758 |
+
"import": 474,
|
| 759 |
+
"ublic": 475,
|
| 760 |
+
"Ġor": 476,
|
| 761 |
+
"est": 477,
|
| 762 |
+
"ment": 478,
|
| 763 |
+
"ĠG": 479,
|
| 764 |
+
"able": 480,
|
| 765 |
+
"Ġ-": 481,
|
| 766 |
+
"ine": 482,
|
| 767 |
+
"ill": 483,
|
| 768 |
+
"ind": 484,
|
| 769 |
+
"ere": 485,
|
| 770 |
+
"::": 486,
|
| 771 |
+
"ity": 487,
|
| 772 |
+
"Ġ+": 488,
|
| 773 |
+
"Ġtr": 489,
|
| 774 |
+
"elf": 490,
|
| 775 |
+
"ight": 491,
|
| 776 |
+
"('": 492,
|
| 777 |
+
"orm": 493,
|
| 778 |
+
"ult": 494,
|
| 779 |
+
"str": 495,
|
| 780 |
+
"..": 496,
|
| 781 |
+
"\",": 497,
|
| 782 |
+
"Ġyou": 498,
|
| 783 |
+
"ype": 499
|
| 784 |
+
},
|
| 785 |
+
"merges": [
|
| 786 |
+
"Ġ Ġ",
|
| 787 |
+
"ĠĠ ĠĠ",
|
| 788 |
+
"i n",
|
| 789 |
+
"Ġ t",
|
| 790 |
+
"ĠĠĠĠ ĠĠĠĠ",
|
| 791 |
+
"e r",
|
| 792 |
+
"ĠĠ Ġ",
|
| 793 |
+
"o n",
|
| 794 |
+
"Ġ a",
|
| 795 |
+
"r e",
|
| 796 |
+
"a t",
|
| 797 |
+
"s t",
|
| 798 |
+
"e n",
|
| 799 |
+
"o r",
|
| 800 |
+
"Ġt h",
|
| 801 |
+
"Ċ Ċ",
|
| 802 |
+
"Ġ c",
|
| 803 |
+
"l e",
|
| 804 |
+
"Ġ s",
|
| 805 |
+
"i t",
|
| 806 |
+
"a n",
|
| 807 |
+
"a r",
|
| 808 |
+
"a l",
|
| 809 |
+
"Ġth e",
|
| 810 |
+
"; Ċ",
|
| 811 |
+
"Ġ p",
|
| 812 |
+
"Ġ f",
|
| 813 |
+
"o u",
|
| 814 |
+
"Ġ =",
|
| 815 |
+
"i s",
|
| 816 |
+
"ĠĠĠĠ ĠĠĠ",
|
| 817 |
+
"in g",
|
| 818 |
+
"e s",
|
| 819 |
+
"Ġ w",
|
| 820 |
+
"i on",
|
| 821 |
+
"e d",
|
| 822 |
+
"i c",
|
| 823 |
+
"Ġ b",
|
| 824 |
+
"Ġ d",
|
| 825 |
+
"e t",
|
| 826 |
+
"Ġ m",
|
| 827 |
+
"Ġ o",
|
| 828 |
+
"ĉ ĉ",
|
| 829 |
+
"r o",
|
| 830 |
+
"a s",
|
| 831 |
+
"e l",
|
| 832 |
+
"c t",
|
| 833 |
+
"n d",
|
| 834 |
+
"Ġ in",
|
| 835 |
+
"Ġ h",
|
| 836 |
+
"en t",
|
| 837 |
+
"i d",
|
| 838 |
+
"Ġ n",
|
| 839 |
+
"a m",
|
| 840 |
+
"ĠĠĠĠĠĠĠĠ ĠĠĠ",
|
| 841 |
+
"Ġt o",
|
| 842 |
+
"Ġ re",
|
| 843 |
+
"- -",
|
| 844 |
+
"Ġ {",
|
| 845 |
+
"Ġo f",
|
| 846 |
+
"o m",
|
| 847 |
+
") ;Ċ",
|
| 848 |
+
"i m",
|
| 849 |
+
"č Ċ",
|
| 850 |
+
"Ġ (",
|
| 851 |
+
"i l",
|
| 852 |
+
"/ /",
|
| 853 |
+
"Ġa nd",
|
| 854 |
+
"u r",
|
| 855 |
+
"s e",
|
| 856 |
+
"Ġ l",
|
| 857 |
+
"e x",
|
| 858 |
+
"Ġ S",
|
| 859 |
+
"a d",
|
| 860 |
+
"Ġ \"",
|
| 861 |
+
"c h",
|
| 862 |
+
"u t",
|
| 863 |
+
"i f",
|
| 864 |
+
"* *",
|
| 865 |
+
"Ġ }",
|
| 866 |
+
"e m",
|
| 867 |
+
"o l",
|
| 868 |
+
"ĠĠĠĠĠĠĠĠ ĠĠĠĠĠĠĠĠ",
|
| 869 |
+
"t h",
|
| 870 |
+
") Ċ",
|
| 871 |
+
"Ġ{ Ċ",
|
| 872 |
+
"Ġ g",
|
| 873 |
+
"i g",
|
| 874 |
+
"i v",
|
| 875 |
+
", Ċ",
|
| 876 |
+
"c e",
|
| 877 |
+
"o d",
|
| 878 |
+
"Ġ v",
|
| 879 |
+
"at e",
|
| 880 |
+
"Ġ T",
|
| 881 |
+
"a g",
|
| 882 |
+
"a y",
|
| 883 |
+
"Ġ *",
|
| 884 |
+
"o t",
|
| 885 |
+
"u s",
|
| 886 |
+
"Ġ C",
|
| 887 |
+
"Ġ st",
|
| 888 |
+
"Ġ I",
|
| 889 |
+
"u n",
|
| 890 |
+
"u l",
|
| 891 |
+
"u e",
|
| 892 |
+
"Ġ A",
|
| 893 |
+
"o w",
|
| 894 |
+
"Ġ '",
|
| 895 |
+
"e w",
|
| 896 |
+
"Ġ <",
|
| 897 |
+
"at ion",
|
| 898 |
+
"( )",
|
| 899 |
+
"Ġf or",
|
| 900 |
+
"a b",
|
| 901 |
+
"or t",
|
| 902 |
+
"u m",
|
| 903 |
+
"am e",
|
| 904 |
+
"Ġ is",
|
| 905 |
+
"p e",
|
| 906 |
+
"t r",
|
| 907 |
+
"c k",
|
| 908 |
+
"â Ģ",
|
| 909 |
+
"Ġ y",
|
| 910 |
+
"i st",
|
| 911 |
+
"-- --",
|
| 912 |
+
". ĊĊ",
|
| 913 |
+
"h e",
|
| 914 |
+
"Ġ e",
|
| 915 |
+
"l o",
|
| 916 |
+
"Ġ M",
|
| 917 |
+
"Ġb e",
|
| 918 |
+
"er s",
|
| 919 |
+
"Ġ on",
|
| 920 |
+
"Ġc on",
|
| 921 |
+
"a p",
|
| 922 |
+
"u b",
|
| 923 |
+
"Ġ P",
|
| 924 |
+
"ĠĠĠĠĠĠĠĠ ĠĠĠĠĠĠĠ",
|
| 925 |
+
"as s",
|
| 926 |
+
"in t",
|
| 927 |
+
"> Ċ",
|
| 928 |
+
"l y",
|
| 929 |
+
"ur n",
|
| 930 |
+
"Ġ $",
|
| 931 |
+
"; ĊĊ",
|
| 932 |
+
"a v",
|
| 933 |
+
"p ort",
|
| 934 |
+
"i r",
|
| 935 |
+
"- >",
|
| 936 |
+
"n t",
|
| 937 |
+
"ct ion",
|
| 938 |
+
"en d",
|
| 939 |
+
"Ġd e",
|
| 940 |
+
"it h",
|
| 941 |
+
"ou t",
|
| 942 |
+
"t urn",
|
| 943 |
+
"ou r",
|
| 944 |
+
"ĠĠĠĠ Ġ",
|
| 945 |
+
"l ic",
|
| 946 |
+
"re s",
|
| 947 |
+
"p t",
|
| 948 |
+
"= =",
|
| 949 |
+
"Ġth is",
|
| 950 |
+
"Ġw h",
|
| 951 |
+
"Ġ if",
|
| 952 |
+
"Ġ D",
|
| 953 |
+
"v er",
|
| 954 |
+
"ag e",
|
| 955 |
+
"Ġ B",
|
| 956 |
+
"h t",
|
| 957 |
+
"ex t",
|
| 958 |
+
"= \"",
|
| 959 |
+
"Ġth at",
|
| 960 |
+
"** **",
|
| 961 |
+
"Ġ R",
|
| 962 |
+
"Ġ it",
|
| 963 |
+
"es s",
|
| 964 |
+
"Ġ F",
|
| 965 |
+
"Ġ r",
|
| 966 |
+
"o s",
|
| 967 |
+
"an d",
|
| 968 |
+
"Ġa s",
|
| 969 |
+
"e ct",
|
| 970 |
+
"k e",
|
| 971 |
+
"ro m",
|
| 972 |
+
"Ġ //",
|
| 973 |
+
"c on",
|
| 974 |
+
"Ġ L",
|
| 975 |
+
"( \"",
|
| 976 |
+
"q u",
|
| 977 |
+
"l ass",
|
| 978 |
+
"Ġw ith",
|
| 979 |
+
"i z",
|
| 980 |
+
"d e",
|
| 981 |
+
"Ġ N",
|
| 982 |
+
"Ġa l",
|
| 983 |
+
"o p",
|
| 984 |
+
"u p",
|
| 985 |
+
"g et",
|
| 986 |
+
"Ġ} Ċ",
|
| 987 |
+
"i le",
|
| 988 |
+
"Ġa n",
|
| 989 |
+
"at a",
|
| 990 |
+
"o re",
|
| 991 |
+
"r i",
|
| 992 |
+
"Ġp ro",
|
| 993 |
+
"; čĊ",
|
| 994 |
+
"ĉĉ ĉĉ",
|
| 995 |
+
"t er",
|
| 996 |
+
"a in",
|
| 997 |
+
"Ġ W",
|
| 998 |
+
"Ġ E",
|
| 999 |
+
"Ġc om",
|
| 1000 |
+
"Ġre turn",
|
| 1001 |
+
"ar t",
|
| 1002 |
+
"Ġ H",
|
| 1003 |
+
"a ck",
|
| 1004 |
+
"im port",
|
| 1005 |
+
"ub lic",
|
| 1006 |
+
"Ġ or",
|
| 1007 |
+
"e st",
|
| 1008 |
+
"m ent",
|
| 1009 |
+
"Ġ G",
|
| 1010 |
+
"ab le",
|
| 1011 |
+
"Ġ -",
|
| 1012 |
+
"in e",
|
| 1013 |
+
"il l",
|
| 1014 |
+
"in d",
|
| 1015 |
+
"er e",
|
| 1016 |
+
": :",
|
| 1017 |
+
"it y",
|
| 1018 |
+
"Ġ +",
|
| 1019 |
+
"Ġt r",
|
| 1020 |
+
"el f",
|
| 1021 |
+
"ig ht",
|
| 1022 |
+
"( '",
|
| 1023 |
+
"or m",
|
| 1024 |
+
"ul t",
|
| 1025 |
+
"st r",
|
| 1026 |
+
". .",
|
| 1027 |
+
"\" ,",
|
| 1028 |
+
"Ġy ou",
|
| 1029 |
+
"y pe"
|
| 1030 |
+
]
|
| 1031 |
+
}
|
| 1032 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content_item in message.content %}\n {%- if 'text' in content_item %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and message.content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 231 |
+
"clean_up_tokenization_spaces": false,
|
| 232 |
+
"eos_token": "<|im_end|>",
|
| 233 |
+
"errors": "replace",
|
| 234 |
+
"model_max_length": 262144,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"split_special_tokens": false,
|
| 237 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 238 |
+
"unk_token": null
|
| 239 |
+
}
|
video_preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 3136,
|
| 4 |
+
"shortest_edge": 784
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 4,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 21 |
+
}
|