SeeWye commited on
Commit
dd2d530
·
verified ·
1 Parent(s): 9f094ca

Training in progress, step 100

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 ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: SeeWye/qwen3_5_TM_ocr_merged2
3
+ library_name: transformers
4
+ model_name: outputs
5
+ tags:
6
+ - generated_from_trainer
7
+ - trl
8
+ - grpo
9
+ - unsloth
10
+ licence: license
11
+ ---
12
+
13
+ # Model Card for outputs
14
+
15
+ This model is a fine-tuned version of [SeeWye/qwen3_5_TM_ocr_merged2](https://huggingface.co/SeeWye/qwen3_5_TM_ocr_merged2).
16
+ It has been trained using [TRL](https://github.com/huggingface/trl).
17
+
18
+ ## Quick start
19
+
20
+ ```python
21
+ from transformers import pipeline
22
+
23
+ question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
24
+ generator = pipeline("text-generation", model="SeeWye/outputs", device="cuda")
25
+ output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
26
+ print(output["generated_text"])
27
+ ```
28
+
29
+ ## Training procedure
30
+
31
+
32
+
33
+
34
+ This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
35
+
36
+ ### Framework versions
37
+
38
+ - TRL: 0.22.2
39
+ - Transformers: 5.2.0
40
+ - Pytorch: 2.8.0
41
+ - Datasets: 4.3.0
42
+ - Tokenizers: 0.22.2
43
+
44
+ ## Citations
45
+
46
+ Cite GRPO as:
47
+
48
+ ```bibtex
49
+ @article{shao2024deepseekmath,
50
+ title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
51
+ author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
52
+ year = 2024,
53
+ eprint = {arXiv:2402.03300},
54
+ }
55
+
56
+ ```
57
+
58
+ Cite TRL as:
59
+
60
+ ```bibtex
61
+ @misc{vonwerra2022trl,
62
+ title = {{TRL: Transformer Reinforcement Learning}},
63
+ author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
64
+ year = 2020,
65
+ journal = {GitHub repository},
66
+ publisher = {GitHub},
67
+ howpublished = {\url{https://github.com/huggingface/trl}}
68
+ }
69
+ ```
adapter_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "Qwen3_5ForConditionalGeneration",
7
+ "parent_library": "transformers.models.qwen3_5.modeling_qwen3_5",
8
+ "unsloth_fixed": true
9
+ },
10
+ "base_model_name_or_path": "SeeWye/qwen3_5_TM_ocr_merged2",
11
+ "bias": "none",
12
+ "corda_config": null,
13
+ "ensure_weight_tying": false,
14
+ "eva_config": null,
15
+ "exclude_modules": null,
16
+ "fan_in_fan_out": false,
17
+ "inference_mode": true,
18
+ "init_lora_weights": true,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 32,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0,
26
+ "lora_ga_config": null,
27
+ "megatron_config": null,
28
+ "megatron_core": "megatron.core",
29
+ "modules_to_save": null,
30
+ "monteclora_config": null,
31
+ "peft_type": "LORA",
32
+ "peft_version": "0.20.0",
33
+ "qalora_group_size": 16,
34
+ "r": 32,
35
+ "rank_pattern": {},
36
+ "revision": null,
37
+ "target_modules": "(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer).*?(?:qkv|proj|linear_fc1|linear_fc2|out_proj|in_proj_qkv|in_proj_z|in_proj_b|in_proj_a|gate_proj|up_proj|down_proj|q_proj|k_proj|v_proj|o_proj))|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer)\\.(?:(?:qkv|proj|linear_fc1|linear_fc2|out_proj|in_proj_qkv|in_proj_z|in_proj_b|in_proj_a|gate_proj|up_proj|down_proj|q_proj|k_proj|v_proj|o_proj)))",
38
+ "target_parameters": null,
39
+ "task_type": "CAUSAL_LM",
40
+ "trainable_token_indices": null,
41
+ "use_bdlora": null,
42
+ "use_dora": false,
43
+ "use_qalora": false,
44
+ "use_rslora": false,
45
+ "velora_config": null
46
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fab877a20aec2dc28251b15239564c0ad317f1b512801dcaf17cf8cee7a808bc
3
+ size 310152752
chat_template.jinja ADDED
@@ -0,0 +1,158 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set image_count = namespace(value=0) %}
2
+ {%- set video_count = namespace(value=0) %}
3
+ {%- macro render_content(content, do_vision_count, is_system_content=false) %}
4
+ {%- if content is string %}
5
+ {{- content }}
6
+ {%- elif content is iterable and content is not mapping %}
7
+ {%- for item in content %}
8
+ {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
+ {%- if is_system_content %}
10
+ {{- raise_exception('System message cannot contain images.') }}
11
+ {%- endif %}
12
+ {%- if do_vision_count %}
13
+ {%- set image_count.value = image_count.value + 1 %}
14
+ {%- endif %}
15
+ {%- if add_vision_id %}
16
+ {{- 'Picture ' ~ image_count.value ~ ': ' }}
17
+ {%- endif %}
18
+ {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
19
+ {%- elif 'video' in item or item.type == 'video' %}
20
+ {%- if is_system_content %}
21
+ {{- raise_exception('System message cannot contain videos.') }}
22
+ {%- endif %}
23
+ {%- if do_vision_count %}
24
+ {%- set video_count.value = video_count.value + 1 %}
25
+ {%- endif %}
26
+ {%- if add_vision_id %}
27
+ {{- 'Video ' ~ video_count.value ~ ': ' }}
28
+ {%- endif %}
29
+ {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
30
+ {%- elif 'text' in item %}
31
+ {{- item.text }}
32
+ {%- else %}
33
+ {{- raise_exception('Unexpected item type in content.') }}
34
+ {%- endif %}
35
+ {%- endfor %}
36
+ {%- elif content is none or content is undefined %}
37
+ {{- '' }}
38
+ {%- else %}
39
+ {{- raise_exception('Unexpected content type.') }}
40
+ {%- endif %}
41
+ {%- endmacro %}
42
+ {%- if not messages %}
43
+ {{- raise_exception('No messages provided.') }}
44
+ {%- endif %}
45
+ {%- set num_sys = 0 %}
46
+ {%- set merged_system = '' %}
47
+ {%- if messages[0].role == 'system' or messages[0].role == 'developer' %}
48
+ {%- set first = render_content(messages[0].content, false, true)|trim %}
49
+ {%- if messages|length > 1 and (messages[1].role == 'system' or messages[1].role == 'developer') %}
50
+ {%- set second = render_content(messages[1].content, false, true)|trim %}
51
+ {%- set merged_system = first + '\n' + second %}
52
+ {%- set num_sys = 2 %}
53
+ {%- else %}
54
+ {%- set merged_system = first %}
55
+ {%- set num_sys = 1 %}
56
+ {%- endif %}
57
+ {%- endif %}
58
+ {%- if tools and tools is iterable and tools is not mapping %}
59
+ {{- '<|im_start|>system\n' }}
60
+ {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
61
+ {%- for tool in tools %}
62
+ {{- "\n" }}
63
+ {{- tool | tojson }}
64
+ {%- endfor %}
65
+ {{- "\n</tools>" }}
66
+ {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
67
+ {%- if merged_system %}
68
+ {{- '\n\n' + merged_system }}
69
+ {%- endif %}
70
+ {{- '<|im_end|>\n' }}
71
+ {%- else %}
72
+ {%- if merged_system %}
73
+ {{- '<|im_start|>system\n' + merged_system + '<|im_end|>\n' }}
74
+ {%- endif %}
75
+ {%- endif %}
76
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
77
+ {%- for message in messages[::-1] %}
78
+ {%- set index = (messages|length - 1) - loop.index0 %}
79
+ {%- if ns.multi_step_tool and message.role == "user" %}
80
+ {%- set content = render_content(message.content, false)|trim %}
81
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
82
+ {%- set ns.multi_step_tool = false %}
83
+ {%- set ns.last_query_index = index %}
84
+ {%- endif %}
85
+ {%- endif %}
86
+ {%- endfor %}
87
+ {%- for message in messages %}
88
+ {%- if loop.index0 >= num_sys and message.role != "system" and message.role != "developer" %}
89
+ {%- set content = render_content(message.content, true)|trim %}
90
+ {%- if message.role == "user" %}
91
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
92
+ {%- elif message.role == "assistant" %}
93
+ {%- set reasoning_content = '' %}
94
+ {%- if message.reasoning_content is string %}
95
+ {%- set reasoning_content = message.reasoning_content %}
96
+ {%- else %}
97
+ {%- if '</think>' in content %}
98
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
99
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
100
+ {%- endif %}
101
+ {%- endif %}
102
+ {%- set reasoning_content = reasoning_content|trim %}
103
+ {%- if loop.index0 > ns.last_query_index %}
104
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
105
+ {%- else %}
106
+ {{- '<|im_start|>' + message.role + '\n' + content }}
107
+ {%- endif %}
108
+ {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
109
+ {%- for tool_call in message.tool_calls %}
110
+ {%- if tool_call.function is defined %}
111
+ {%- set tool_call = tool_call.function %}
112
+ {%- endif %}
113
+ {%- if loop.first %}
114
+ {%- if content|trim %}
115
+ {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
116
+ {%- else %}
117
+ {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
118
+ {%- endif %}
119
+ {%- else %}
120
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
121
+ {%- endif %}
122
+ {%- if tool_call.arguments is mapping %}
123
+ {%- for args_name in tool_call.arguments %}
124
+ {%- set args_value = tool_call.arguments[args_name] %}
125
+ {{- '<parameter=' + args_name + '>\n' }}
126
+ {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
127
+ {{- args_value }}
128
+ {{- '\n</parameter>\n' }}
129
+ {%- endfor %}
130
+ {%- endif %}
131
+ {{- '</function>\n</tool_call>' }}
132
+ {%- endfor %}
133
+ {%- endif %}
134
+ {{- '<|im_end|>\n' }}
135
+ {%- elif message.role == "tool" %}
136
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
137
+ {{- '<|im_start|>user' }}
138
+ {%- endif %}
139
+ {{- '\n<tool_response>\n' }}
140
+ {{- content }}
141
+ {{- '\n</tool_response>' }}
142
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
143
+ {{- '<|im_end|>\n' }}
144
+ {%- elif loop.last %}
145
+ {{- '<|im_end|>\n' }}
146
+ {%- endif %}
147
+ {%- endif %}
148
+ {%- endif %}
149
+ {%- endfor %}
150
+ {%- if add_generation_prompt %}
151
+ {{- '<|im_start|>assistant\n' }}
152
+ {%- if enable_thinking is defined and enable_thinking is false %}
153
+ {{- '<think>\n\n</think>\n\n' }}
154
+ {%- else %}
155
+ {{- '<think>\n' }}
156
+ {%- endif %}
157
+ {%- endif %}
158
+ {#- Unsloth fixes - developer role, tool calling #}
processor_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "data_format": "channels_first",
4
+ "do_convert_rgb": true,
5
+ "do_normalize": true,
6
+ "do_rescale": true,
7
+ "do_resize": true,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_processor_type": "Qwen2VLImageProcessorFast",
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "merge_size": 2,
20
+ "patch_size": 16,
21
+ "resample": 3,
22
+ "rescale_factor": 0.00392156862745098,
23
+ "size": {
24
+ "longest_edge": 16777216,
25
+ "shortest_edge": 65536
26
+ },
27
+ "temporal_patch_size": 2
28
+ },
29
+ "processor_class": "Qwen3VLProcessor",
30
+ "video_processor": {
31
+ "data_format": "channels_first",
32
+ "default_to_square": true,
33
+ "do_convert_rgb": true,
34
+ "do_normalize": true,
35
+ "do_rescale": true,
36
+ "do_resize": true,
37
+ "do_sample_frames": true,
38
+ "fps": 2,
39
+ "image_mean": [
40
+ 0.5,
41
+ 0.5,
42
+ 0.5
43
+ ],
44
+ "image_std": [
45
+ 0.5,
46
+ 0.5,
47
+ 0.5
48
+ ],
49
+ "max_frames": 768,
50
+ "merge_size": 2,
51
+ "min_frames": 4,
52
+ "patch_size": 16,
53
+ "resample": 3,
54
+ "rescale_factor": 0.00392156862745098,
55
+ "return_metadata": false,
56
+ "size": {
57
+ "longest_edge": 25165824,
58
+ "shortest_edge": 4096
59
+ },
60
+ "temporal_patch_size": 2,
61
+ "video_processor_type": "Qwen3VLVideoProcessor"
62
+ }
63
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd1ed2db726bd54c518f2f92d5b0e64e74da888bd8ddcd3003e4b650182892dd
3
+ size 19989511
tokenizer_config.json ADDED
@@ -0,0 +1,305 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "audio_bos_token": "<|audio_start|>",
4
+ "audio_eos_token": "<|audio_end|>",
5
+ "audio_token": "<|audio_pad|>",
6
+ "backend": "tokenizers",
7
+ "bos_token": null,
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": "<|im_end|>",
10
+ "errors": "replace",
11
+ "image_token": "<|image_pad|>",
12
+ "is_local": false,
13
+ "max_length": 2048,
14
+ "model_max_length": 262144,
15
+ "model_specific_special_tokens": {
16
+ "audio_bos_token": "<|audio_start|>",
17
+ "audio_eos_token": "<|audio_end|>",
18
+ "audio_token": "<|audio_pad|>",
19
+ "image_token": "<|image_pad|>",
20
+ "video_token": "<|video_pad|>",
21
+ "vision_bos_token": "<|vision_start|>",
22
+ "vision_eos_token": "<|vision_end|>"
23
+ },
24
+ "pad_to_multiple_of": null,
25
+ "pad_token": "<|vision_pad|>",
26
+ "pad_token_type_id": 0,
27
+ "padding_side": "right",
28
+ "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
29
+ "processor_class": "Qwen3VLProcessor",
30
+ "split_special_tokens": false,
31
+ "stride": 0,
32
+ "tokenizer_class": "TokenizersBackend",
33
+ "truncation_side": "right",
34
+ "truncation_strategy": "longest_first",
35
+ "unk_token": null,
36
+ "video_token": "<|video_pad|>",
37
+ "vision_bos_token": "<|vision_start|>",
38
+ "vision_eos_token": "<|vision_end|>",
39
+ "added_tokens_decoder": {
40
+ "248044": {
41
+ "content": "<|endoftext|>",
42
+ "single_word": false,
43
+ "lstrip": false,
44
+ "rstrip": false,
45
+ "normalized": false,
46
+ "special": true
47
+ },
48
+ "248045": {
49
+ "content": "<|im_start|>",
50
+ "single_word": false,
51
+ "lstrip": false,
52
+ "rstrip": false,
53
+ "normalized": false,
54
+ "special": true
55
+ },
56
+ "248046": {
57
+ "content": "<|im_end|>",
58
+ "single_word": false,
59
+ "lstrip": false,
60
+ "rstrip": false,
61
+ "normalized": false,
62
+ "special": true
63
+ },
64
+ "248047": {
65
+ "content": "<|object_ref_start|>",
66
+ "single_word": false,
67
+ "lstrip": false,
68
+ "rstrip": false,
69
+ "normalized": false,
70
+ "special": true
71
+ },
72
+ "248048": {
73
+ "content": "<|object_ref_end|>",
74
+ "single_word": false,
75
+ "lstrip": false,
76
+ "rstrip": false,
77
+ "normalized": false,
78
+ "special": true
79
+ },
80
+ "248049": {
81
+ "content": "<|box_start|>",
82
+ "single_word": false,
83
+ "lstrip": false,
84
+ "rstrip": false,
85
+ "normalized": false,
86
+ "special": true
87
+ },
88
+ "248050": {
89
+ "content": "<|box_end|>",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": false,
94
+ "special": true
95
+ },
96
+ "248051": {
97
+ "content": "<|quad_start|>",
98
+ "single_word": false,
99
+ "lstrip": false,
100
+ "rstrip": false,
101
+ "normalized": false,
102
+ "special": true
103
+ },
104
+ "248052": {
105
+ "content": "<|quad_end|>",
106
+ "single_word": false,
107
+ "lstrip": false,
108
+ "rstrip": false,
109
+ "normalized": false,
110
+ "special": true
111
+ },
112
+ "248053": {
113
+ "content": "<|vision_start|>",
114
+ "single_word": false,
115
+ "lstrip": false,
116
+ "rstrip": false,
117
+ "normalized": false,
118
+ "special": true
119
+ },
120
+ "248054": {
121
+ "content": "<|vision_end|>",
122
+ "single_word": false,
123
+ "lstrip": false,
124
+ "rstrip": false,
125
+ "normalized": false,
126
+ "special": true
127
+ },
128
+ "248055": {
129
+ "content": "<|vision_pad|>",
130
+ "single_word": false,
131
+ "lstrip": false,
132
+ "rstrip": false,
133
+ "normalized": false,
134
+ "special": true
135
+ },
136
+ "248056": {
137
+ "content": "<|image_pad|>",
138
+ "single_word": false,
139
+ "lstrip": false,
140
+ "rstrip": false,
141
+ "normalized": false,
142
+ "special": true
143
+ },
144
+ "248057": {
145
+ "content": "<|video_pad|>",
146
+ "single_word": false,
147
+ "lstrip": false,
148
+ "rstrip": false,
149
+ "normalized": false,
150
+ "special": true
151
+ },
152
+ "248058": {
153
+ "content": "<tool_call>",
154
+ "single_word": false,
155
+ "lstrip": false,
156
+ "rstrip": false,
157
+ "normalized": false,
158
+ "special": false
159
+ },
160
+ "248059": {
161
+ "content": "</tool_call>",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": false,
166
+ "special": false
167
+ },
168
+ "248060": {
169
+ "content": "<|fim_prefix|>",
170
+ "single_word": false,
171
+ "lstrip": false,
172
+ "rstrip": false,
173
+ "normalized": false,
174
+ "special": false
175
+ },
176
+ "248061": {
177
+ "content": "<|fim_middle|>",
178
+ "single_word": false,
179
+ "lstrip": false,
180
+ "rstrip": false,
181
+ "normalized": false,
182
+ "special": false
183
+ },
184
+ "248062": {
185
+ "content": "<|fim_suffix|>",
186
+ "single_word": false,
187
+ "lstrip": false,
188
+ "rstrip": false,
189
+ "normalized": false,
190
+ "special": false
191
+ },
192
+ "248063": {
193
+ "content": "<|fim_pad|>",
194
+ "single_word": false,
195
+ "lstrip": false,
196
+ "rstrip": false,
197
+ "normalized": false,
198
+ "special": false
199
+ },
200
+ "248064": {
201
+ "content": "<|repo_name|>",
202
+ "single_word": false,
203
+ "lstrip": false,
204
+ "rstrip": false,
205
+ "normalized": false,
206
+ "special": false
207
+ },
208
+ "248065": {
209
+ "content": "<|file_sep|>",
210
+ "single_word": false,
211
+ "lstrip": false,
212
+ "rstrip": false,
213
+ "normalized": false,
214
+ "special": false
215
+ },
216
+ "248066": {
217
+ "content": "<tool_response>",
218
+ "single_word": false,
219
+ "lstrip": false,
220
+ "rstrip": false,
221
+ "normalized": false,
222
+ "special": false
223
+ },
224
+ "248067": {
225
+ "content": "</tool_response>",
226
+ "single_word": false,
227
+ "lstrip": false,
228
+ "rstrip": false,
229
+ "normalized": false,
230
+ "special": false
231
+ },
232
+ "248068": {
233
+ "content": "<think>",
234
+ "single_word": false,
235
+ "lstrip": false,
236
+ "rstrip": false,
237
+ "normalized": false,
238
+ "special": false
239
+ },
240
+ "248069": {
241
+ "content": "</think>",
242
+ "single_word": false,
243
+ "lstrip": false,
244
+ "rstrip": false,
245
+ "normalized": false,
246
+ "special": false
247
+ },
248
+ "248070": {
249
+ "content": "<|audio_start|>",
250
+ "single_word": false,
251
+ "lstrip": false,
252
+ "rstrip": false,
253
+ "normalized": false,
254
+ "special": true
255
+ },
256
+ "248071": {
257
+ "content": "<|audio_end|>",
258
+ "single_word": false,
259
+ "lstrip": false,
260
+ "rstrip": false,
261
+ "normalized": false,
262
+ "special": true
263
+ },
264
+ "248072": {
265
+ "content": "<tts_pad>",
266
+ "single_word": false,
267
+ "lstrip": false,
268
+ "rstrip": false,
269
+ "normalized": false,
270
+ "special": true
271
+ },
272
+ "248073": {
273
+ "content": "<tts_text_bos>",
274
+ "single_word": false,
275
+ "lstrip": false,
276
+ "rstrip": false,
277
+ "normalized": false,
278
+ "special": true
279
+ },
280
+ "248074": {
281
+ "content": "<tts_text_eod>",
282
+ "single_word": false,
283
+ "lstrip": false,
284
+ "rstrip": false,
285
+ "normalized": false,
286
+ "special": true
287
+ },
288
+ "248075": {
289
+ "content": "<tts_text_bos_single>",
290
+ "single_word": false,
291
+ "lstrip": false,
292
+ "rstrip": false,
293
+ "normalized": false,
294
+ "special": true
295
+ },
296
+ "248076": {
297
+ "content": "<|audio_pad|>",
298
+ "single_word": false,
299
+ "lstrip": false,
300
+ "rstrip": false,
301
+ "normalized": false,
302
+ "special": true
303
+ }
304
+ }
305
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:979a08b994c28dbdd20b1a388b517fa189ea8809c24a2c4073b66cba41590995
3
+ size 6609