Hugging Face's logo

voidful
/
desta25_4b_R1_lean

Safetensors
desta25
Model card Files
xet
 Community
voidful commited on
Commit
2a499e0
·
verified ·
1 Parent(s): bbf1902

Upload trained Struct-ORCA model

Browse files
Files changed (17) hide show
  1. .gitattributes +2 -0
  2. added_tokens.json +29 -0
  3. chat_template.jinja +61 -0
  4. config.json +179 -0
  5. merges.txt +0 -0
  6. model.safetensors +3 -0
  7. optimizer.pt +3 -0
  8. rng_state_0.pth +3 -0
  9. rng_state_1.pth +3 -0
  10. rng_state_2.pth +3 -0
  11. scheduler.pt +3 -0
  12. special_tokens_map.json +25 -0
  13. tokenizer.json +3 -0
  14. tokenizer_config.json +247 -0
  15. trainer_state.json +3 -0
  16. training_args.bin +3 -0
  17. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ 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
37
+ trainer_state.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|AUDIO|>": 151669,
9
+ "<|box_end|>": 151649,
10
+ "<|box_start|>": 151648,
11
+ "<|endoftext|>": 151643,
12
+ "<|file_sep|>": 151664,
13
+ "<|fim_middle|>": 151660,
14
+ "<|fim_pad|>": 151662,
15
+ "<|fim_prefix|>": 151659,
16
+ "<|fim_suffix|>": 151661,
17
+ "<|im_end|>": 151645,
18
+ "<|im_start|>": 151644,
19
+ "<|image_pad|>": 151655,
20
+ "<|object_ref_end|>": 151647,
21
+ "<|object_ref_start|>": 151646,
22
+ "<|quad_end|>": 151651,
23
+ "<|quad_start|>": 151650,
24
+ "<|repo_name|>": 151663,
25
+ "<|video_pad|>": 151656,
26
+ "<|vision_end|>": 151653,
27
+ "<|vision_pad|>": 151654,
28
+ "<|vision_start|>": 151652
29
+ }
chat_template.jinja ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# 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>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\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" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- for message in messages %}
18
+ {%- if message.content is string %}
19
+ {%- set content = message.content %}
20
+ {%- else %}
21
+ {%- set content = '' %}
22
+ {%- endif %}
23
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
24
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
25
+ {%- elif message.role == "assistant" %}
26
+ {{- '<|im_start|>' + message.role + '\n' + content }}
27
+ {%- if message.tool_calls %}
28
+ {%- for tool_call in message.tool_calls %}
29
+ {%- if (loop.first and content) or (not loop.first) %}
30
+ {{- '\n' }}
31
+ {%- endif %}
32
+ {%- if tool_call.function %}
33
+ {%- set tool_call = tool_call.function %}
34
+ {%- endif %}
35
+ {{- '<tool_call>\n{"name": "' }}
36
+ {{- tool_call.name }}
37
+ {{- '", "arguments": ' }}
38
+ {%- if tool_call.arguments is string %}
39
+ {{- tool_call.arguments }}
40
+ {%- else %}
41
+ {{- tool_call.arguments | tojson }}
42
+ {%- endif %}
43
+ {{- '}\n</tool_call>' }}
44
+ {%- endfor %}
45
+ {%- endif %}
46
+ {{- '<|im_end|>\n' }}
47
+ {%- elif message.role == "tool" %}
48
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
49
+ {{- '<|im_start|>user' }}
50
+ {%- endif %}
51
+ {{- '\n<tool_response>\n' }}
52
+ {{- content }}
53
+ {{- '\n</tool_response>' }}
54
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
55
+ {{- '<|im_end|>\n' }}
56
+ {%- endif %}
57
+ {%- endif %}
58
+ {%- endfor %}
59
+ {%- if add_generation_prompt %}
60
+ {{- '<|im_start|>assistant\n' }}
61
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,179 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DeSTA25AudioModel"
4
+ ],
5
+ "asr_dropout_prob": 0.0,
6
+ "asr_noise_augment_enabled": false,
7
+ "asr_noise_prob": 0.0,
8
+ "audio_locator": "<|AUDIO|>",
9
+ "audio_question_contrastive_enabled": false,
10
+ "audio_question_contrastive_weight": 0.1,
11
+ "connector_mode": "struct_orca",
12
+ "dtype": "bfloat16",
13
+ "encoder_config": {
14
+ "_name_or_path": "openai/whisper-large-v3",
15
+ "activation_dropout": 0.0,
16
+ "activation_function": "gelu",
17
+ "apply_spec_augment": false,
18
+ "architectures": [
19
+ "WhisperForConditionalGeneration"
20
+ ],
21
+ "attention_dropout": 0.0,
22
+ "begin_suppress_tokens": [
23
+ 220,
24
+ 50257
25
+ ],
26
+ "bos_token_id": 50257,
27
+ "classifier_proj_size": 256,
28
+ "d_model": 1280,
29
+ "decoder_attention_heads": 20,
30
+ "decoder_ffn_dim": 5120,
31
+ "decoder_layerdrop": 0.0,
32
+ "decoder_layers": 32,
33
+ "decoder_start_token_id": 50258,
34
+ "dropout": 0.0,
35
+ "dtype": "float16",
36
+ "encoder_attention_heads": 20,
37
+ "encoder_ffn_dim": 5120,
38
+ "encoder_layerdrop": 0.0,
39
+ "encoder_layers": 32,
40
+ "eos_token_id": 50257,
41
+ "init_std": 0.02,
42
+ "mask_feature_length": 10,
43
+ "mask_feature_min_masks": 0,
44
+ "mask_feature_prob": 0.0,
45
+ "mask_time_length": 10,
46
+ "mask_time_min_masks": 2,
47
+ "mask_time_prob": 0.05,
48
+ "max_length": 448,
49
+ "max_source_positions": 1500,
50
+ "max_target_positions": 448,
51
+ "median_filter_width": 7,
52
+ "model_type": "whisper",
53
+ "num_hidden_layers": 32,
54
+ "num_mel_bins": 128,
55
+ "scale_embedding": false,
56
+ "use_cache": true,
57
+ "use_weighted_layer_sum": false,
58
+ "vocab_size": 51866
59
+ },
60
+ "encoder_model_id": "openai/whisper-large-v3",
61
+ "eos_token_id": 151645,
62
+ "focal_loss_enabled": false,
63
+ "focal_loss_gamma": 2.0,
64
+ "info": "\uff24\uff45\uff53\uff54\uff41\uff12\u3002\uff15 \uff21\uff55\uff44\uff49\uff4f",
65
+ "layer_weighted_learnable": true,
66
+ "layer_weighted_sum_enabled": false,
67
+ "llm_config": {
68
+ "_name_or_path": "Qwen/Qwen3-4B-Instruct-2507",
69
+ "architectures": [
70
+ "Qwen3ForCausalLM"
71
+ ],
72
+ "attention_bias": false,
73
+ "attention_dropout": 0.0,
74
+ "bos_token_id": 151643,
75
+ "dtype": "bfloat16",
76
+ "eos_token_id": 151645,
77
+ "head_dim": 128,
78
+ "hidden_act": "silu",
79
+ "hidden_size": 2560,
80
+ "initializer_range": 0.02,
81
+ "intermediate_size": 9728,
82
+ "layer_types": [
83
+ "full_attention",
84
+ "full_attention",
85
+ "full_attention",
86
+ "full_attention",
87
+ "full_attention",
88
+ "full_attention",
89
+ "full_attention",
90
+ "full_attention",
91
+ "full_attention",
92
+ "full_attention",
93
+ "full_attention",
94
+ "full_attention",
95
+ "full_attention",
96
+ "full_attention",
97
+ "full_attention",
98
+ "full_attention",
99
+ "full_attention",
100
+ "full_attention",
101
+ "full_attention",
102
+ "full_attention",
103
+ "full_attention",
104
+ "full_attention",
105
+ "full_attention",
106
+ "full_attention",
107
+ "full_attention",
108
+ "full_attention",
109
+ "full_attention",
110
+ "full_attention",
111
+ "full_attention",
112
+ "full_attention",
113
+ "full_attention",
114
+ "full_attention",
115
+ "full_attention",
116
+ "full_attention",
117
+ "full_attention",
118
+ "full_attention"
119
+ ],
120
+ "max_position_embeddings": 262144,
121
+ "max_window_layers": 36,
122
+ "model_type": "qwen3",
123
+ "num_attention_heads": 32,
124
+ "num_hidden_layers": 36,
125
+ "num_key_value_heads": 8,
126
+ "rms_norm_eps": 1e-06,
127
+ "rope_scaling": null,
128
+ "rope_theta": 5000000,
129
+ "sliding_window": null,
130
+ "tie_word_embeddings": true,
131
+ "use_cache": true,
132
+ "use_sliding_window": false,
133
+ "vocab_size": 151936
134
+ },
135
+ "llm_model_id": "Qwen/Qwen3-4B-Instruct-2507",
136
+ "modality_dpo_beta": 0.1,
137
+ "modality_dpo_enabled": false,
138
+ "model_type": "desta25",
139
+ "multi_scale_local_enabled": false,
140
+ "orca_adversarial_erasure": false,
141
+ "orca_adversarial_weight": 0.0,
142
+ "orca_align_weight_local": 0.0,
143
+ "orca_audio_position_scale": 5.0,
144
+ "orca_deep_injection_enabled": true,
145
+ "orca_deep_injection_stride": 1,
146
+ "orca_enabled": false,
147
+ "orca_gate_init": 0.1,
148
+ "orca_global_cross_attn": false,
149
+ "orca_global_num_tokens": 4,
150
+ "orca_local_branch_true": false,
151
+ "orca_local_downsample": 4,
152
+ "orca_local_enabled": true,
153
+ "orca_local_kernel_size": 7,
154
+ "orca_local_ortho_weight": 0.0,
155
+ "orca_ortho_diversity_weight": 0.01,
156
+ "orca_ortho_weight_global": 0.01,
157
+ "orca_ortho_weight_qformer_local": 0.01,
158
+ "orca_orthogonal_projection": false,
159
+ "orca_use_all_layers": false,
160
+ "pad_token_id": 151645,
161
+ "placeholder_token": "<|video_pad|>",
162
+ "prompt_size": 64,
163
+ "qformer_num_hidden_layers": 6,
164
+ "scene_prior_enabled": false,
165
+ "scene_prior_num_classes": 10,
166
+ "struct_orca_acd_alpha": 0.5,
167
+ "struct_orca_inter_group_weight": 0.1,
168
+ "struct_orca_intra_group_weight": 0.03,
169
+ "struct_orca_iv_weight": 0,
170
+ "struct_orca_num_groups": 8,
171
+ "struct_orca_queries_per_group": 8,
172
+ "task_aware_routing_enabled": false,
173
+ "temporal_attention_enabled": false,
174
+ "train_id": 30678,
175
+ "transformers_version": "4.57.3",
176
+ "use_lora": false,
177
+ "variational_grouping_enabled": false,
178
+ "variational_kl_weight": 0.01
179
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5ce9525d982ce3653fe33c8035957fea73756e6000867cb134565b552bdfe65
3
+ size 518316536
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e26323ad82eddd19e7463db3c5ebd34f9f080ed35aa0e534c5c74a69daa8d2ae
3
+ size 1577146
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4db36c14e0d8a7cf991414bf40b3e4a01764bc4265b034ddd30fbfe4494c14b5
3
+ size 14768
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f7ce0ba7f460f615bb10709794a12a0f599b24ac3e559a5e7e4e651cfec6188
3
+ size 14768
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21cf00a1c9029122b17d9ce2ea7d6ea9d5fbe12086c302b22c86b4a4697075c7
3
+ size 14768
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98afbeed7aa7042bf035cb6af01fb18af5cc8d1ac93a13aa2342faf55dd1742c
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": "<|im_end|>"
25
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17d941882646cfd2a31864ba206c898f38680933f47da169539bf82983ea05af
3
+ size 11422840
tokenizer_config.json ADDED
@@ -0,0 +1,247 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "151669": {
214
+ "content": "<|AUDIO|>",
215
+ "lstrip": false,
216
+ "normalized": true,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": false
220
+ }
221
+ },
222
+ "additional_special_tokens": [
223
+ "<|im_start|>",
224
+ "<|im_end|>",
225
+ "<|object_ref_start|>",
226
+ "<|object_ref_end|>",
227
+ "<|box_start|>",
228
+ "<|box_end|>",
229
+ "<|quad_start|>",
230
+ "<|quad_end|>",
231
+ "<|vision_start|>",
232
+ "<|vision_end|>",
233
+ "<|vision_pad|>",
234
+ "<|image_pad|>",
235
+ "<|video_pad|>"
236
+ ],
237
+ "bos_token": null,
238
+ "clean_up_tokenization_spaces": false,
239
+ "eos_token": "<|im_end|>",
240
+ "errors": "replace",
241
+ "extra_special_tokens": {},
242
+ "model_max_length": 1010000,
243
+ "pad_token": "<|im_end|>",
244
+ "split_special_tokens": false,
245
+ "tokenizer_class": "Qwen2Tokenizer",
246
+ "unk_token": null
247
+ }
trainer_state.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:355e382facd008b4dd140a1e26355530283f60af3bdcdbe134dbcad563152e44
3
+ size 12775475
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59299ba336ad593d17d8a51d58820c440b5192024bf1d52bcd247ef21700539c
3
+ size 5496
vocab.json ADDED
The diff for this file is too large to render. See raw diff