Hugging Face's logo

KENIC-1
/
white

Model card Files
xet
Community
KENIC-1 commited on
Commit
41bb236
·
verified ·
1 Parent(s): 8be49ed

Delete folder: models

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. models/DreamOmni2/README.md +0 -3
  2. models/DreamOmni2/edit_lora/pytorch_lora_weights.safetensors.url +0 -1
  3. models/DreamOmni2/gen_lora/pytorch_lora_weights.safetensors.url +0 -1
  4. models/DreamOmni2/vlm-model/added_tokens.json +0 -24
  5. models/DreamOmni2/vlm-model/chat_template.jinja +0 -7
  6. models/DreamOmni2/vlm-model/config.json +0 -135
  7. models/DreamOmni2/vlm-model/generation_config.json +0 -12
  8. models/DreamOmni2/vlm-model/merges.txt +0 -0
  9. models/DreamOmni2/vlm-model/model-00001-of-00004.safetensors.url +0 -1
  10. models/DreamOmni2/vlm-model/model-00002-of-00004.safetensors.url +0 -1
  11. models/DreamOmni2/vlm-model/model-00003-of-00004.safetensors.url +0 -1
  12. models/DreamOmni2/vlm-model/model-00004-of-00004.safetensors.url +0 -1
  13. models/DreamOmni2/vlm-model/model.safetensors.index.json +0 -737
  14. models/DreamOmni2/vlm-model/preprocessor_config.json +0 -37
  15. models/DreamOmni2/vlm-model/special_tokens_map.json +0 -31
  16. models/DreamOmni2/vlm-model/tokenizer.json +0 -3
  17. models/DreamOmni2/vlm-model/tokenizer_config.json +0 -209
  18. models/DreamOmni2/vlm-model/video_preprocessor_config.json +0 -43
  19. models/DreamOmni2/vlm-model/vocab.json +0 -0
  20. models/IndexTTS-1.5/bigvgan_discriminator.pth.url +0 -1
  21. models/IndexTTS-1.5/bigvgan_generator.pth.url +0 -1
  22. models/IndexTTS-1.5/bpe.model +0 -3
  23. models/IndexTTS-1.5/config.yaml +0 -113
  24. models/IndexTTS-1.5/dvae.pth.url +0 -1
  25. models/IndexTTS-1.5/gpt.pth.url +0 -1
  26. models/IndexTTS-1.5/unigram_12000.vocab +0 -0
  27. models/IndexTTS-2/README.md +0 -74
  28. models/IndexTTS-2/bigvgan/bigvgan_v2_22khz_80band_256x/bigvgan_generator.pt.url +0 -1
  29. models/IndexTTS-2/bigvgan/bigvgan_v2_22khz_80band_256x/config.json +0 -63
  30. models/IndexTTS-2/checkpoints/bigvgan/bigvgan_generator.pt.url +0 -1
  31. models/IndexTTS-2/checkpoints/bigvgan/config.json +0 -63
  32. models/IndexTTS-2/checkpoints/bpe.model +0 -3
  33. models/IndexTTS-2/checkpoints/campplus_cn_common.bin copy.url +0 -1
  34. models/IndexTTS-2/checkpoints/campplus_cn_common.bin.url +0 -1
  35. models/IndexTTS-2/checkpoints/config.yaml +0 -120
  36. models/IndexTTS-2/checkpoints/feat1.pt.url +0 -1
  37. models/IndexTTS-2/checkpoints/feat2.pt.url +0 -1
  38. models/IndexTTS-2/checkpoints/gpt.pth.url +0 -1
  39. models/IndexTTS-2/checkpoints/qwen0.6bemo4-merge/Modelfile +0 -11
  40. models/IndexTTS-2/checkpoints/qwen0.6bemo4-merge/added_tokens.json +0 -28
  41. models/IndexTTS-2/checkpoints/qwen0.6bemo4-merge/chat_template.jinja +0 -4
  42. models/IndexTTS-2/checkpoints/qwen0.6bemo4-merge/config.json +0 -30
  43. models/IndexTTS-2/checkpoints/qwen0.6bemo4-merge/generation_config.json +0 -6
  44. models/IndexTTS-2/checkpoints/qwen0.6bemo4-merge/merges.txt +0 -0
  45. models/IndexTTS-2/checkpoints/qwen0.6bemo4-merge/model.safetensors.url +0 -1
  46. models/IndexTTS-2/checkpoints/qwen0.6bemo4-merge/special_tokens_map.json +0 -31
  47. models/IndexTTS-2/checkpoints/qwen0.6bemo4-merge/tokenizer.json +0 -3
  48. models/IndexTTS-2/checkpoints/qwen0.6bemo4-merge/tokenizer_config.json +0 -240
  49. models/IndexTTS-2/checkpoints/qwen0.6bemo4-merge/vocab.json +0 -0
  50. models/IndexTTS-2/checkpoints/s2mel.pth.url +0 -1
models/DreamOmni2/README.md DELETED
@@ -1,3 +0,0 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
models/DreamOmni2/edit_lora/pytorch_lora_weights.safetensors.url DELETED
@@ -1 +0,0 @@
1
- https://cnb.cool/W3C/33095019/1018DreamOmni2/-/lfs/c61b22f6488c893ab3d1d8ef5744daa2fc7696b2cefcbd55d6731f6f55fd474a?name=pytorch_lora_weights.safetensors
 
 
models/DreamOmni2/gen_lora/pytorch_lora_weights.safetensors.url DELETED
@@ -1 +0,0 @@
1
- https://cnb.cool/W3C/33095019/1018DreamOmni2/-/lfs/1146cddc48545c79ad871bc6b0ae3fca0aaaa5c61ea5ce29629c0405af095e2a?name=pytorch_lora_weights.safetensors
 
 
models/DreamOmni2/vlm-model/added_tokens.json DELETED
@@ -1,24 +0,0 @@
1
- {
2
- "</tool_call>": 151658,
3
- "<tool_call>": 151657,
4
- "<|box_end|>": 151649,
5
- "<|box_start|>": 151648,
6
- "<|endoftext|>": 151643,
7
- "<|file_sep|>": 151664,
8
- "<|fim_middle|>": 151660,
9
- "<|fim_pad|>": 151662,
10
- "<|fim_prefix|>": 151659,
11
- "<|fim_suffix|>": 151661,
12
- "<|im_end|>": 151645,
13
- "<|im_start|>": 151644,
14
- "<|image_pad|>": 151655,
15
- "<|object_ref_end|>": 151647,
16
- "<|object_ref_start|>": 151646,
17
- "<|quad_end|>": 151651,
18
- "<|quad_start|>": 151650,
19
- "<|repo_name|>": 151663,
20
- "<|video_pad|>": 151656,
21
- "<|vision_end|>": 151653,
22
- "<|vision_pad|>": 151654,
23
- "<|vision_start|>": 151652
24
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
models/DreamOmni2/vlm-model/chat_template.jinja DELETED
@@ -1,7 +0,0 @@
1
- {% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
2
- You are a helpful assistant.<|im_end|>
3
- {% endif %}<|im_start|>{{ message['role'] }}
4
- {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
- {% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
6
- {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
- {% endif %}
 
 
 
 
 
 
 
 
models/DreamOmni2/vlm-model/config.json DELETED
@@ -1,135 +0,0 @@
1
- {
2
- "architectures": [
3
- "Qwen2_5_VLForConditionalGeneration"
4
- ],
5
- "attention_dropout": 0.0,
6
- "bos_token_id": 151643,
7
- "eos_token_id": 151645,
8
- "hidden_act": "silu",
9
- "hidden_size": 3584,
10
- "image_token_id": 151655,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 18944,
13
- "max_position_embeddings": 128000,
14
- "max_window_layers": 28,
15
- "model_type": "qwen2_5_vl",
16
- "num_attention_heads": 28,
17
- "num_hidden_layers": 28,
18
- "num_key_value_heads": 4,
19
- "rms_norm_eps": 1e-06,
20
- "rope_scaling": {
21
- "mrope_section": [
22
- 16,
23
- 24,
24
- 24
25
- ],
26
- "rope_type": "default",
27
- "type": "default"
28
- },
29
- "rope_theta": 1000000.0,
30
- "sliding_window": 32768,
31
- "text_config": {
32
- "architectures": [
33
- "Qwen2_5_VLForConditionalGeneration"
34
- ],
35
- "attention_dropout": 0.0,
36
- "bos_token_id": 151643,
37
- "eos_token_id": 151645,
38
- "hidden_act": "silu",
39
- "hidden_size": 3584,
40
- "image_token_id": null,
41
- "initializer_range": 0.02,
42
- "intermediate_size": 18944,
43
- "layer_types": [
44
- "full_attention",
45
- "full_attention",
46
- "full_attention",
47
- "full_attention",
48
- "full_attention",
49
- "full_attention",
50
- "full_attention",
51
- "full_attention",
52
- "full_attention",
53
- "full_attention",
54
- "full_attention",
55
- "full_attention",
56
- "full_attention",
57
- "full_attention",
58
- "full_attention",
59
- "full_attention",
60
- "full_attention",
61
- "full_attention",
62
- "full_attention",
63
- "full_attention",
64
- "full_attention",
65
- "full_attention",
66
- "full_attention",
67
- "full_attention",
68
- "full_attention",
69
- "full_attention",
70
- "full_attention",
71
- "full_attention"
72
- ],
73
- "max_position_embeddings": 128000,
74
- "max_window_layers": 28,
75
- "model_type": "qwen2_5_vl_text",
76
- "num_attention_heads": 28,
77
- "num_hidden_layers": 28,
78
- "num_key_value_heads": 4,
79
- "rms_norm_eps": 1e-06,
80
- "rope_scaling": {
81
- "mrope_section": [
82
- 16,
83
- 24,
84
- 24
85
- ],
86
- "rope_type": "default",
87
- "type": "default"
88
- },
89
- "rope_theta": 1000000.0,
90
- "sliding_window": null,
91
- "torch_dtype": "float32",
92
- "use_cache": false,
93
- "use_sliding_window": false,
94
- "video_token_id": null,
95
- "vision_end_token_id": 151653,
96
- "vision_start_token_id": 151652,
97
- "vision_token_id": 151654,
98
- "vocab_size": 152064
99
- },
100
- "tie_word_embeddings": false,
101
- "torch_dtype": "bfloat16",
102
- "transformers_version": "4.55.0",
103
- "use_cache": false,
104
- "use_sliding_window": false,
105
- "video_token_id": 151656,
106
- "vision_config": {
107
- "depth": 32,
108
- "fullatt_block_indexes": [
109
- 7,
110
- 15,
111
- 23,
112
- 31
113
- ],
114
- "hidden_act": "silu",
115
- "hidden_size": 1280,
116
- "in_channels": 3,
117
- "in_chans": 3,
118
- "initializer_range": 0.02,
119
- "intermediate_size": 3420,
120
- "model_type": "qwen2_5_vl",
121
- "num_heads": 16,
122
- "out_hidden_size": 3584,
123
- "patch_size": 14,
124
- "spatial_merge_size": 2,
125
- "spatial_patch_size": 14,
126
- "temporal_patch_size": 2,
127
- "tokens_per_second": 2,
128
- "torch_dtype": "float32",
129
- "window_size": 112
130
- },
131
- "vision_end_token_id": 151653,
132
- "vision_start_token_id": 151652,
133
- "vision_token_id": 151654,
134
- "vocab_size": 152064
135
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
models/DreamOmni2/vlm-model/generation_config.json DELETED
@@ -1,12 +0,0 @@
1
- {
2
- "bos_token_id": 151643,
3
- "do_sample": true,
4
- "eos_token_id": [
5
- 151645,
6
- 151643
7
- ],
8
- "pad_token_id": 151643,
9
- "repetition_penalty": 1.05,
10
- "temperature": 1e-06,
11
- "transformers_version": "4.55.0"
12
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
models/DreamOmni2/vlm-model/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
models/DreamOmni2/vlm-model/model-00001-of-00004.safetensors.url DELETED
@@ -1 +0,0 @@
1
- https://cnb.cool/W3C/33095019/1018DreamOmni2/-/lfs/4b7f1009a55769b8597aa2fb8ead5011d9221449faad44c55acfa68e5c56411d?name=model-00001-of-00004.safetensors
 
 
models/DreamOmni2/vlm-model/model-00002-of-00004.safetensors.url DELETED
@@ -1 +0,0 @@
1
- https://cnb.cool/W3C/33095019/1018DreamOmni2/-/lfs/9f04f503bd8d75ce8eef5d8738569be3dc305850f498beffda6d8b29000c9e1a?name=model-00002-of-00004.safetensors
 
 
models/DreamOmni2/vlm-model/model-00003-of-00004.safetensors.url DELETED
@@ -1 +0,0 @@
1
- https://cnb.cool/W3C/33095019/1018DreamOmni2/-/lfs/efbdac5e078267f8e13af626302b6ea5354ce46817b9785ebff3bf628d8c4552?name=model-00003-of-00004.safetensors
 
 
models/DreamOmni2/vlm-model/model-00004-of-00004.safetensors.url DELETED
@@ -1 +0,0 @@
1
- https://cnb.cool/W3C/33095019/1018DreamOmni2/-/lfs/39b7803a1283c97e4cc8dfc31c74fd48bc77780c7ce751f3e335b3f16273544e?name=model-00004-of-00004.safetensors
 
 
models/DreamOmni2/vlm-model/model.safetensors.index.json DELETED
@@ -1,737 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_parameters": 848896,
4
- "total_size": 16584333312
5
- },
6
- "weight_map": {
7
- "lm_head.weight": "model-00004-of-00004.safetensors",
8
- "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
- "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
- "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
15
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
16
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
17
- "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
18
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
19
- "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
20
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
21
- "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
22
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
23
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
24
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
25
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
26
- "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
27
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
28
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
29
- "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
30
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
31
- "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
32
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
33
- "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
34
- "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
35
- "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
36
- "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
37
- "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
38
- "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
39
- "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
40
- "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
41
- "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
42
- "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
- "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
44
- "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
45
- "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
46
- "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
47
- "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
48
- "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
49
- "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
50
- "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
51
- "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
52
- "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
53
- "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
54
- "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
55
- "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
56
- "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
57
- "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
58
- "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
59
- "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
60
- "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
61
- "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
62
- "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
63
- "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
64
- "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
65
- "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
66
- "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
67
- "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
68
- "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
69
- "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
70
- "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
71
- "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
72
- "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
73
- "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
74
- "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
75
- "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
76
- "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
77
- "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
78
- "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
- "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
80
- "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
81
- "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
82
- "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
83
- "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
84
- "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
85
- "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
86
- "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
87
- "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
88
- "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
89
- "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
90
- "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
91
- "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
92
- "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
93
- "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
94
- "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
95
- "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
96
- "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
97
- "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
98
- "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
99
- "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
100
- "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
101
- "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
102
- "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
103
- "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
104
- "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
105
- "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
106
- "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
107
- "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
108
- "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
109
- "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
110
- "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
111
- "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
112
- "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
113
- "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
114
- "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
- "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
116
- "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
- "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
118
- "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
119
- "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
120
- "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
121
- "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
122
- "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
123
- "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
124
- "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
125
- "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
126
- "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
127
- "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
128
- "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
129
- "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
130
- "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
131
- "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
132
- "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
133
- "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
134
- "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
135
- "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
136
- "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
137
- "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
138
- "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
139
- "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
140
- "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
141
- "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
142
- "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
143
- "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
144
- "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
145
- "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
146
- "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
147
- "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
148
- "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
149
- "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
150
- "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
- "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
152
- "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
153
- "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
154
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
155
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
156
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
157
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
158
- "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
159
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
160
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
161
- "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
162
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
163
- "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
164
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
165
- "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
166
- "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
167
- "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
168
- "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
169
- "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
170
- "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
171
- "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
172
- "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
173
- "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
174
- "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
175
- "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
176
- "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
177
- "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
178
- "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
179
- "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
180
- "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
181
- "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
182
- "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
183
- "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
184
- "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
185
- "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
186
- "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
- "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
188
- "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
189
- "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
190
- "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
191
- "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
192
- "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
193
- "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
194
- "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
195
- "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
196
- "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
197
- "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
198
- "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
199
- "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
200
- "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
201
- "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
202
- "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
203
- "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
204
- "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
205
- "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
206
- "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
207
- "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
208
- "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
209
- "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
210
- "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
211
- "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
212
- "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
213
- "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
214
- "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
215
- "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
216
- "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
217
- "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
218
- "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
219
- "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
220
- "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
221
- "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
222
- "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
223
- "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
224
- "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
225
- "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
226
- "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
227
- "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
228
- "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
229
- "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
230
- "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
231
- "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
232
- "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
233
- "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
234
- "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
235
- "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
236
- "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
237
- "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
238
- "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
239
- "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
240
- "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
241
- "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
242
- "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
243
- "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
244
- "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
245
- "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
246
- "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
247
- "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
248
- "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
249
- "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
250
- "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
251
- "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
252
- "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
253
- "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
254
- "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
255
- "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
256
- "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
257
- "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
258
- "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
259
- "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
260
- "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
261
- "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
262
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
263
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
264
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
265
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
266
- "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
267
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
268
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
269
- "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
270
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
271
- "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
272
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
273
- "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
274
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
275
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
276
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
277
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
278
- "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
279
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
280
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
281
- "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
282
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
283
- "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
284
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
285
- "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
286
- "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
287
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
288
- "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
289
- "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
290
- "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
291
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
292
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
293
- "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
294
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
295
- "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
296
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
297
- "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
298
- "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
299
- "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
300
- "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
301
- "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
302
- "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
303
- "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
304
- "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
305
- "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
306
- "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
307
- "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
308
- "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
309
- "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
310
- "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
311
- "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
312
- "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
313
- "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
314
- "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
315
- "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
316
- "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
317
- "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
318
- "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
319
- "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
320
- "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
321
- "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
322
- "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
323
- "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
324
- "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
325
- "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
326
- "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
327
- "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
328
- "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
329
- "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
330
- "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
331
- "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
332
- "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
333
- "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
334
- "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
335
- "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
336
- "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
337
- "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
338
- "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
339
- "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
340
- "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
341
- "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
342
- "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
343
- "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
344
- "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
345
- "model.norm.weight": "model-00004-of-00004.safetensors",
346
- "visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
347
- "visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
348
- "visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
349
- "visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
350
- "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
351
- "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
352
- "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
353
- "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
354
- "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
355
- "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
356
- "visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
357
- "visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
358
- "visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
359
- "visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
360
- "visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
361
- "visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
362
- "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
363
- "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
364
- "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
365
- "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
366
- "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
367
- "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
368
- "visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
369
- "visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
370
- "visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
371
- "visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
372
- "visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
373
- "visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
374
- "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
375
- "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
376
- "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
377
- "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
378
- "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
379
- "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
380
- "visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
381
- "visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
382
- "visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
383
- "visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
384
- "visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
385
- "visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
386
- "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
387
- "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
388
- "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
389
- "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
390
- "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
391
- "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
392
- "visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
393
- "visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
394
- "visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
395
- "visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
396
- "visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
397
- "visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
398
- "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
399
- "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
400
- "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
401
- "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
402
- "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
403
- "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
404
- "visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
405
- "visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
406
- "visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
407
- "visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
408
- "visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
409
- "visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
410
- "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
411
- "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
412
- "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
413
- "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
414
- "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
415
- "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
416
- "visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
417
- "visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
418
- "visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
419
- "visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
420
- "visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
421
- "visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
422
- "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
423
- "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
424
- "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
425
- "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
426
- "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
427
- "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
428
- "visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
429
- "visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
430
- "visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
431
- "visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
432
- "visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
433
- "visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
434
- "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
435
- "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
436
- "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
437
- "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
438
- "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
439
- "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
440
- "visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
441
- "visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
442
- "visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
443
- "visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
444
- "visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
445
- "visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
446
- "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
447
- "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
448
- "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
449
- "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
450
- "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
451
- "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
452
- "visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
453
- "visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
454
- "visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
455
- "visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
456
- "visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
457
- "visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
458
- "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
459
- "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
460
- "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
461
- "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
462
- "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
463
- "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
464
- "visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
465
- "visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
466
- "visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
467
- "visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
468
- "visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
469
- "visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
470
- "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
471
- "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
472
- "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
473
- "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
474
- "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
475
- "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
476
- "visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
477
- "visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
478
- "visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
479
- "visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
480
- "visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
481
- "visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
482
- "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
483
- "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
484
- "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
485
- "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
486
- "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
487
- "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
488
- "visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
489
- "visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
490
- "visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
491
- "visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
492
- "visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
493
- "visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
494
- "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
495
- "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
496
- "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
497
- "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
498
- "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
499
- "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
500
- "visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
501
- "visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
502
- "visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
503
- "visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
504
- "visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
505
- "visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
506
- "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
507
- "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
508
- "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
509
- "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
510
- "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
511
- "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
512
- "visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
513
- "visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
514
- "visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
515
- "visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
516
- "visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
517
- "visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
518
- "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
519
- "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
520
- "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
521
- "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
522
- "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
523
- "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
524
- "visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
525
- "visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
526
- "visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
527
- "visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
528
- "visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
529
- "visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
530
- "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
531
- "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
532
- "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
533
- "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
534
- "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
535
- "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
536
- "visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
537
- "visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
538
- "visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
539
- "visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
540
- "visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
541
- "visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
542
- "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
543
- "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
544
- "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
545
- "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
546
- "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
547
- "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
548
- "visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
549
- "visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
550
- "visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
551
- "visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
552
- "visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
553
- "visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
554
- "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
555
- "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
556
- "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
557
- "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
558
- "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
559
- "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
560
- "visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
561
- "visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
562
- "visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
563
- "visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
564
- "visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
565
- "visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
566
- "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
567
- "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
568
- "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
569
- "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
570
- "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
571
- "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
572
- "visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
573
- "visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
574
- "visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
575
- "visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
576
- "visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
577
- "visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
578
- "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
579
- "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
580
- "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
581
- "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
582
- "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
583
- "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
584
- "visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
585
- "visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
586
- "visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
587
- "visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
588
- "visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
589
- "visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
590
- "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
591
- "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
592
- "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
593
- "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
594
- "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
595
- "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
596
- "visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
597
- "visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
598
- "visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
599
- "visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
600
- "visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
601
- "visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
602
- "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
603
- "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
604
- "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
605
- "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
606
- "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
607
- "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
608
- "visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
609
- "visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
610
- "visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
611
- "visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
612
- "visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
613
- "visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
614
- "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
615
- "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
616
- "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
617
- "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
618
- "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
619
- "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
620
- "visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
621
- "visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
622
- "visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
623
- "visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
624
- "visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
625
- "visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
626
- "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
627
- "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
628
- "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
629
- "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
630
- "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
631
- "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
632
- "visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
633
- "visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
634
- "visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
635
- "visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
636
- "visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
637
- "visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
638
- "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
639
- "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
640
- "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
641
- "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
642
- "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
643
- "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
644
- "visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
645
- "visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
646
- "visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
647
- "visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
648
- "visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
649
- "visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
650
- "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
651
- "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
652
- "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
653
- "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
654
- "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
655
- "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
656
- "visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
657
- "visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
658
- "visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
659
- "visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
660
- "visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
661
- "visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
662
- "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
663
- "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
664
- "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
665
- "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
666
- "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
667
- "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
668
- "visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
669
- "visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
670
- "visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
671
- "visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
672
- "visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
673
- "visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
674
- "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
675
- "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
676
- "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
677
- "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
678
- "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
679
- "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
680
- "visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
681
- "visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
682
- "visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
683
- "visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
684
- "visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
685
- "visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
686
- "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
687
- "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
688
- "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
689
- "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
690
- "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
691
- "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
692
- "visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
693
- "visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
694
- "visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
695
- "visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
696
- "visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
697
- "visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
698
- "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
699
- "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
700
- "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
701
- "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
702
- "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
703
- "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
704
- "visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
705
- "visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
706
- "visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
707
- "visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
708
- "visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
709
- "visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
710
- "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
711
- "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
712
- "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
713
- "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
714
- "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
715
- "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
716
- "visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
717
- "visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
718
- "visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
719
- "visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
720
- "visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
721
- "visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
722
- "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
723
- "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
724
- "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
725
- "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
726
- "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
727
- "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
728
- "visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
729
- "visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
730
- "visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
731
- "visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
732
- "visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
733
- "visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
734
- "visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
735
- "visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
736
- }
737
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
models/DreamOmni2/vlm-model/preprocessor_config.json DELETED
@@ -1,37 +0,0 @@
1
- {
2
- "crop_size": null,
3
- "data_format": "channels_first",
4
- "default_to_square": true,
5
- "device": null,
6
- "disable_grouping": null,
7
- "do_center_crop": null,
8
- "do_convert_rgb": true,
9
- "do_normalize": true,
10
- "do_rescale": true,
11
- "do_resize": true,
12
- "image_mean": [
13
- 0.48145466,
14
- 0.4578275,
15
- 0.40821073
16
- ],
17
- "image_processor_type": "Qwen2VLImageProcessorFast",
18
- "image_std": [
19
- 0.26862954,
20
- 0.26130258,
21
- 0.27577711
22
- ],
23
- "input_data_format": null,
24
- "max_pixels": 12845056,
25
- "merge_size": 2,
26
- "min_pixels": 3136,
27
- "patch_size": 14,
28
- "processor_class": "Qwen2_5_VLProcessor",
29
- "resample": 3,
30
- "rescale_factor": 0.00392156862745098,
31
- "return_tensors": null,
32
- "size": {
33
- "longest_edge": 12845056,
34
- "shortest_edge": 3136
35
- },
36
- "temporal_patch_size": 2
37
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
models/DreamOmni2/vlm-model/special_tokens_map.json DELETED
@@ -1,31 +0,0 @@
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": {
25
- "content": "<|endoftext|>",
26
- "lstrip": false,
27
- "normalized": false,
28
- "rstrip": false,
29
- "single_word": false
30
- }
31
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
models/DreamOmni2/vlm-model/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
- size 11421896
 
 
 
 
models/DreamOmni2/vlm-model/tokenizer_config.json DELETED
@@ -1,209 +0,0 @@
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
- },
182
- "additional_special_tokens": [
183
- "<|im_start|>",
184
- "<|im_end|>",
185
- "<|object_ref_start|>",
186
- "<|object_ref_end|>",
187
- "<|box_start|>",
188
- "<|box_end|>",
189
- "<|quad_start|>",
190
- "<|quad_end|>",
191
- "<|vision_start|>",
192
- "<|vision_end|>",
193
- "<|vision_pad|>",
194
- "<|image_pad|>",
195
- "<|video_pad|>"
196
- ],
197
- "bos_token": null,
198
- "clean_up_tokenization_spaces": false,
199
- "eos_token": "<|im_end|>",
200
- "errors": "replace",
201
- "extra_special_tokens": {},
202
- "model_max_length": 131072,
203
- "pad_token": "<|endoftext|>",
204
- "padding_side": "right",
205
- "processor_class": "Qwen2_5_VLProcessor",
206
- "split_special_tokens": false,
207
- "tokenizer_class": "Qwen2Tokenizer",
208
- "unk_token": null
209
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
models/DreamOmni2/vlm-model/video_preprocessor_config.json DELETED
@@ -1,43 +0,0 @@
1
- {
2
- "crop_size": null,
3
- "data_format": "channels_first",
4
- "default_to_square": true,
5
- "device": null,
6
- "do_center_crop": null,
7
- "do_convert_rgb": true,
8
- "do_normalize": true,
9
- "do_pad": null,
10
- "do_rescale": true,
11
- "do_resize": true,
12
- "do_sample_frames": false,
13
- "fps": null,
14
- "image_mean": [
15
- 0.48145466,
16
- 0.4578275,
17
- 0.40821073
18
- ],
19
- "image_std": [
20
- 0.26862954,
21
- 0.26130258,
22
- 0.27577711
23
- ],
24
- "input_data_format": null,
25
- "max_frames": 768,
26
- "max_pixels": 12845056,
27
- "merge_size": 2,
28
- "min_frames": 4,
29
- "min_pixels": 3136,
30
- "num_frames": null,
31
- "patch_size": 14,
32
- "processor_class": "Qwen2_5_VLProcessor",
33
- "resample": 3,
34
- "rescale_factor": 0.00392156862745098,
35
- "size": {
36
- "longest_edge": 12845056,
37
- "shortest_edge": 3136
38
- },
39
- "size_divisor": null,
40
- "temporal_patch_size": 2,
41
- "video_metadata": null,
42
- "video_processor_type": "Qwen2VLVideoProcessor"
43
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
models/DreamOmni2/vlm-model/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
models/IndexTTS-1.5/bigvgan_discriminator.pth.url DELETED
@@ -1 +0,0 @@
1
- https://cnb.cool/mamalalala/20250717/-/lfs/46e1f6277f7239363d2393f2f9fe36902cf8995e4acc0ba67ed25a025dbd02f0?name=bigvgan_discriminator.pth
 
 
models/IndexTTS-1.5/bigvgan_generator.pth.url DELETED
@@ -1 +0,0 @@
1
- https://cnb.cool/mamalalala/20250717/-/lfs/a2458834d8277e76eb8614c9751b5e8eaa0474eab706f0ecfafcb600023133ed?name=bigvgan_generator.pth
 
 
models/IndexTTS-1.5/bpe.model DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2a5ce8090d32da3642cc4f81fdc996376bc6dd3f4cd5e3d165f71120d9f2bc8
3
- size 475997
 
 
 
 
models/IndexTTS-1.5/config.yaml DELETED
@@ -1,113 +0,0 @@
1
- dataset:
2
- bpe_model: bpe.model
3
- sample_rate: 24000
4
- squeeze: false
5
- mel:
6
- sample_rate: 24000
7
- n_fft: 1024
8
- hop_length: 256
9
- win_length: 1024
10
- n_mels: 100
11
- mel_fmin: 0
12
- normalize: false
13
-
14
- gpt:
15
- model_dim: 1280
16
- max_mel_tokens: 800
17
- max_text_tokens: 600
18
- heads: 20
19
- use_mel_codes_as_input: true
20
- mel_length_compression: 1024
21
- layers: 24
22
- number_text_tokens: 12000
23
- number_mel_codes: 8194
24
- start_mel_token: 8192
25
- stop_mel_token: 8193
26
- start_text_token: 0
27
- stop_text_token: 1
28
- train_solo_embeddings: false
29
- condition_type: "conformer_perceiver"
30
- condition_module:
31
- output_size: 512
32
- linear_units: 2048
33
- attention_heads: 8
34
- num_blocks: 6
35
- input_layer: "conv2d2"
36
- perceiver_mult: 2
37
-
38
- vqvae:
39
- channels: 100
40
- num_tokens: 8192
41
- hidden_dim: 512
42
- num_resnet_blocks: 3
43
- codebook_dim: 512
44
- num_layers: 2
45
- positional_dims: 1
46
- kernel_size: 3
47
- smooth_l1_loss: true
48
- use_transposed_convs: false
49
-
50
- bigvgan:
51
- adam_b1: 0.8
52
- adam_b2: 0.99
53
- lr_decay: 0.999998
54
- seed: 1234
55
-
56
- resblock: "1"
57
- upsample_rates: [4,4,4,4,2,2]
58
- upsample_kernel_sizes: [8,8,4,4,4,4]
59
- upsample_initial_channel: 1536
60
- resblock_kernel_sizes: [3,7,11]
61
- resblock_dilation_sizes: [[1,3,5], [1,3,5], [1,3,5]]
62
- feat_upsample: false
63
- speaker_embedding_dim: 512
64
- cond_d_vector_in_each_upsampling_layer: true
65
-
66
- gpt_dim: 1280
67
-
68
- activation: "snakebeta"
69
- snake_logscale: true
70
-
71
- use_cqtd_instead_of_mrd: true
72
- cqtd_filters: 128
73
- cqtd_max_filters: 1024
74
- cqtd_filters_scale: 1
75
- cqtd_dilations: [1, 2, 4]
76
- cqtd_hop_lengths: [512, 256, 256]
77
- cqtd_n_octaves: [9, 9, 9]
78
- cqtd_bins_per_octaves: [24, 36, 48]
79
-
80
- resolutions: [[1024, 120, 600], [2048, 240, 1200], [512, 50, 240]]
81
- mpd_reshapes: [2, 3, 5, 7, 11]
82
- use_spectral_norm: false
83
- discriminator_channel_mult: 1
84
-
85
- use_multiscale_melloss: true
86
- lambda_melloss: 15
87
-
88
- clip_grad_norm: 1000
89
-
90
- segment_size: 16384
91
- num_mels: 100
92
- num_freq: 1025
93
- n_fft: 1024
94
- hop_size: 256
95
- win_size: 1024
96
-
97
- sampling_rate: 24000
98
-
99
- fmin: 0
100
- fmax: null
101
- fmax_for_loss: null
102
- mel_type: "pytorch"
103
-
104
- num_workers: 2
105
- dist_config:
106
- dist_backend: "nccl"
107
- dist_url: "tcp://localhost:54321"
108
- world_size: 1
109
-
110
- dvae_checkpoint: dvae.pth
111
- gpt_checkpoint: gpt.pth
112
- bigvgan_checkpoint: bigvgan_generator.pth
113
- version: 1.5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
models/IndexTTS-1.5/dvae.pth.url DELETED
@@ -1 +0,0 @@
1
- https://cnb.cool/mamalalala/20250717/-/lfs/69e841bf8cd97a32806ea8a439c50017c991ac9e8bb795db89ec47828cae4d5d?name=dvae.pth
 
 
models/IndexTTS-1.5/gpt.pth.url DELETED
@@ -1 +0,0 @@
1
- https://cnb.cool/mamalalala/20250717/-/lfs/44460b820a8afd58f68f3d3e69113e7900c8730bf519ecf158c081f2b8991240?name=gpt.pth
 
 
models/IndexTTS-1.5/unigram_12000.vocab DELETED
The diff for this file is too large to render. See raw diff
 
models/IndexTTS-2/README.md DELETED
@@ -1,74 +0,0 @@
1
- ---
2
- license: apache-2.0
3
- language:
4
- - en
5
- ---
6
- ## 👉🏻 IndexTTS2 👈🏻
7
-
8
- <center><h3>IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech</h3></center>
9
-
10
-
11
- <div align="center">
12
- <a href='https://arxiv.org/abs/2506.21619'>
13
- <img src='https://img.shields.io/badge/ArXiv-2506.21619-red?logo=arxiv'/>
14
- </a>
15
- <br/>
16
- <a href='https://github.com/index-tts/index-tts'>
17
- <img src='https://img.shields.io/badge/GitHub-Code-orange?logo=github'/>
18
- </a>
19
- <a href='https://index-tts.github.io/index-tts2.github.io/'>
20
- <img src='https://img.shields.io/badge/GitHub-Demo-orange?logo=github'/>
21
- </a>
22
- <br/>
23
- <!--a href='https://huggingface.co/spaces/IndexTeam/IndexTTS'>
24
- <img src='https://img.shields.io/badge/HuggingFace-Demo-blue?logo=huggingface'/>
25
- </a-->
26
- <a href='https://huggingface.co/IndexTeam/IndexTTS-2'>
27
- <img src='https://img.shields.io/badge/HuggingFace-Model-blue?logo=huggingface' />
28
- </a>
29
- <br/>
30
- <!--a href='https://modelscope.cn/studios/IndexTeam/IndexTTS-Demo'>
31
- <img src='https://img.shields.io/badge/ModelScope-Demo-purple?logo=modelscope'/>
32
- </a-->
33
- <a href='https://modelscope.cn/models/IndexTeam/IndexTTS-2'>
34
- <img src='https://img.shields.io/badge/ModelScope-Model-purple?logo=modelscope'/>
35
- </a>
36
- </div>
37
-
38
-
39
- ## Acknowledge
40
- 1. [tortoise-tts](https://github.com/neonbjb/tortoise-tts)
41
- 2. [XTTSv2](https://github.com/coqui-ai/TTS)
42
- 3. [BigVGAN](https://github.com/NVIDIA/BigVGAN)
43
- 4. [wenet](https://github.com/wenet-e2e/wenet/tree/main)
44
- 5. [icefall](https://github.com/k2-fsa/icefall)
45
- 6. [maskgct](https://github.com/open-mmlab/Amphion/tree/main/models/tts/maskgct)
46
- 7. [seed-vc](https://github.com/Plachtaa/seed-vc)
47
-
48
-
49
- ## 📚 Citation
50
-
51
- 🌟 If you find our work helpful, please leave us a star and cite our paper.
52
-
53
-
54
- IndexTTS2
55
- ```
56
- @article{zhou2025indextts2,
57
- title={IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech},
58
- author={Siyi Zhou, Yiquan Zhou, Yi He, Xun Zhou, Jinchao Wang, Wei Deng, Jingchen Shu},
59
- journal={arXiv preprint arXiv:2506.21619},
60
- year={2025}
61
- }
62
- ```
63
-
64
- IndexTTS
65
- ```
66
- @article{deng2025indextts,
67
- title={IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System},
68
- author={Wei Deng, Siyi Zhou, Jingchen Shu, Jinchao Wang, Lu Wang},
69
- journal={arXiv preprint arXiv:2502.05512},
70
- year={2025},
71
- doi={10.48550/arXiv.2502.05512},
72
- url={https://arxiv.org/abs/2502.05512}
73
- }
74
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
models/IndexTTS-2/bigvgan/bigvgan_v2_22khz_80band_256x/bigvgan_generator.pt.url DELETED
@@ -1 +0,0 @@
1
- https://cnb.cool/mamalalala/20250717/-/lfs/e95ba25972d3de0628d99cd156e9315a9c018899bf739988959ebe3544080ced?name=bigvgan_generator.pt
 
 
models/IndexTTS-2/bigvgan/bigvgan_v2_22khz_80band_256x/config.json DELETED
@@ -1,63 +0,0 @@
1
- {
2
- "resblock": "1",
3
- "num_gpus": 0,
4
- "batch_size": 32,
5
- "learning_rate": 0.0001,
6
- "adam_b1": 0.8,
7
- "adam_b2": 0.99,
8
- "lr_decay": 0.9999996,
9
- "seed": 1234,
10
-
11
- "upsample_rates": [4,4,2,2,2,2],
12
- "upsample_kernel_sizes": [8,8,4,4,4,4],
13
- "upsample_initial_channel": 1536,
14
- "resblock_kernel_sizes": [3,7,11],
15
- "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
16
-
17
- "use_tanh_at_final": false,
18
- "use_bias_at_final": false,
19
-
20
- "activation": "snakebeta",
21
- "snake_logscale": true,
22
-
23
- "use_cqtd_instead_of_mrd": true,
24
- "cqtd_filters": 128,
25
- "cqtd_max_filters": 1024,
26
- "cqtd_filters_scale": 1,
27
- "cqtd_dilations": [1, 2, 4],
28
- "cqtd_hop_lengths": [512, 256, 256],
29
- "cqtd_n_octaves": [9, 9, 9],
30
- "cqtd_bins_per_octaves": [24, 36, 48],
31
-
32
- "mpd_reshapes": [2, 3, 5, 7, 11],
33
- "use_spectral_norm": false,
34
- "discriminator_channel_mult": 1,
35
-
36
- "use_multiscale_melloss": true,
37
- "lambda_melloss": 15,
38
-
39
- "clip_grad_norm": 500,
40
-
41
- "segment_size": 65536,
42
- "num_mels": 80,
43
- "num_freq": 1025,
44
- "n_fft": 1024,
45
- "hop_size": 256,
46
- "win_size": 1024,
47
-
48
- "sampling_rate": 22050,
49
-
50
- "fmin": 0,
51
- "fmax": null,
52
- "fmax_for_loss": null,
53
-
54
- "normalize_volume": true,
55
-
56
- "num_workers": 4,
57
-
58
- "dist_config": {
59
- "dist_backend": "nccl",
60
- "dist_url": "tcp://localhost:54321",
61
- "world_size": 1
62
- }
63
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
models/IndexTTS-2/checkpoints/bigvgan/bigvgan_generator.pt.url DELETED
@@ -1 +0,0 @@
1
- https://cnb.cool/mamalalala/20250717/-/lfs/e95ba25972d3de0628d99cd156e9315a9c018899bf739988959ebe3544080ced?name=bigvgan_generator.pt
 
 
models/IndexTTS-2/checkpoints/bigvgan/config.json DELETED
@@ -1,63 +0,0 @@
1
- {
2
- "resblock": "1",
3
- "num_gpus": 0,
4
- "batch_size": 32,
5
- "learning_rate": 0.0001,
6
- "adam_b1": 0.8,
7
- "adam_b2": 0.99,
8
- "lr_decay": 0.9999996,
9
- "seed": 1234,
10
-
11
- "upsample_rates": [4,4,2,2,2,2],
12
- "upsample_kernel_sizes": [8,8,4,4,4,4],
13
- "upsample_initial_channel": 1536,
14
- "resblock_kernel_sizes": [3,7,11],
15
- "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
16
-
17
- "use_tanh_at_final": false,
18
- "use_bias_at_final": false,
19
-
20
- "activation": "snakebeta",
21
- "snake_logscale": true,
22
-
23
- "use_cqtd_instead_of_mrd": true,
24
- "cqtd_filters": 128,
25
- "cqtd_max_filters": 1024,
26
- "cqtd_filters_scale": 1,
27
- "cqtd_dilations": [1, 2, 4],
28
- "cqtd_hop_lengths": [512, 256, 256],
29
- "cqtd_n_octaves": [9, 9, 9],
30
- "cqtd_bins_per_octaves": [24, 36, 48],
31
-
32
- "mpd_reshapes": [2, 3, 5, 7, 11],
33
- "use_spectral_norm": false,
34
- "discriminator_channel_mult": 1,
35
-
36
- "use_multiscale_melloss": true,
37
- "lambda_melloss": 15,
38
-
39
- "clip_grad_norm": 500,
40
-
41
- "segment_size": 65536,
42
- "num_mels": 80,
43
- "num_freq": 1025,
44
- "n_fft": 1024,
45
- "hop_size": 256,
46
- "win_size": 1024,
47
-
48
- "sampling_rate": 22050,
49
-
50
- "fmin": 0,
51
- "fmax": null,
52
- "fmax_for_loss": null,
53
-
54
- "normalize_volume": true,
55
-
56
- "num_workers": 4,
57
-
58
- "dist_config": {
59
- "dist_backend": "nccl",
60
- "dist_url": "tcp://localhost:54321",
61
- "world_size": 1
62
- }
63
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
models/IndexTTS-2/checkpoints/bpe.model DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2a5ce8090d32da3642cc4f81fdc996376bc6dd3f4cd5e3d165f71120d9f2bc8
3
- size 475997
 
 
 
 
models/IndexTTS-2/checkpoints/campplus_cn_common.bin copy.url DELETED
@@ -1 +0,0 @@
1
- https://cnb.cool/mamalalala/20250717/-/lfs/3388cf5fd3493c9ac9c69851d8e7a8badcfb4f3dc631020c4961371646d5ada8?name=campplus_cn_common.bin
 
 
models/IndexTTS-2/checkpoints/campplus_cn_common.bin.url DELETED
@@ -1 +0,0 @@
1
- https://cnb.cool/ai-models/funasr/campplus/-/lfs/3388cf5fd3493c9ac9c69851d8e7a8badcfb4f3dc631020c4961371646d5ada8?name=campplus_cn_common.bin
 
 
models/IndexTTS-2/checkpoints/config.yaml DELETED
@@ -1,120 +0,0 @@
1
- dataset:
2
- bpe_model: bpe.model
3
- sample_rate: 24000
4
- squeeze: false
5
- mel:
6
- sample_rate: 24000
7
- n_fft: 1024
8
- hop_length: 256
9
- win_length: 1024
10
- n_mels: 100
11
- mel_fmin: 0
12
- normalize: false
13
-
14
- gpt:
15
- model_dim: 1280
16
- max_mel_tokens: 1815
17
- max_text_tokens: 600
18
- heads: 20
19
- use_mel_codes_as_input: true
20
- mel_length_compression: 1024
21
- layers: 24
22
- number_text_tokens: 12000
23
- number_mel_codes: 8194
24
- start_mel_token: 8192
25
- stop_mel_token: 8193
26
- start_text_token: 0
27
- stop_text_token: 1
28
- train_solo_embeddings: false
29
- condition_type: "conformer_perceiver"
30
- condition_module:
31
- output_size: 512
32
- linear_units: 2048
33
- attention_heads: 8
34
- num_blocks: 6
35
- input_layer: "conv2d2"
36
- perceiver_mult: 2
37
- emo_condition_module:
38
- output_size: 512
39
- linear_units: 1024
40
- attention_heads: 4
41
- num_blocks: 4
42
- input_layer: "conv2d2"
43
- perceiver_mult: 2
44
-
45
- semantic_codec:
46
- codebook_size: 8192
47
- hidden_size: 1024
48
- codebook_dim: 8
49
- vocos_dim: 384
50
- vocos_intermediate_dim: 2048
51
- vocos_num_layers: 12
52
-
53
- s2mel:
54
- preprocess_params:
55
- sr: 22050
56
- spect_params:
57
- n_fft: 1024
58
- win_length: 1024
59
- hop_length: 256
60
- n_mels: 80
61
- fmin: 0
62
- fmax: "None"
63
-
64
- dit_type: "DiT"
65
- reg_loss_type: "l1"
66
- style_encoder:
67
- dim: 192
68
- length_regulator:
69
- channels: 512
70
- is_discrete: false
71
- in_channels: 1024
72
- content_codebook_size: 2048
73
- sampling_ratios: [1, 1, 1, 1]
74
- vector_quantize: false
75
- n_codebooks: 1
76
- quantizer_dropout: 0.0
77
- f0_condition: false
78
- n_f0_bins: 512
79
- DiT:
80
- hidden_dim: 512
81
- num_heads: 8
82
- depth: 13
83
- class_dropout_prob: 0.1
84
- block_size: 8192
85
- in_channels: 80
86
- style_condition: true
87
- final_layer_type: 'wavenet'
88
- target: 'mel'
89
- content_dim: 512
90
- content_codebook_size: 1024
91
- content_type: 'discrete'
92
- f0_condition: false
93
- n_f0_bins: 512
94
- content_codebooks: 1
95
- is_causal: false
96
- long_skip_connection: true
97
- zero_prompt_speech_token: false
98
- time_as_token: false
99
- style_as_token: false
100
- uvit_skip_connection: true
101
- add_resblock_in_transformer: false
102
- wavenet:
103
- hidden_dim: 512
104
- num_layers: 8
105
- kernel_size: 5
106
- dilation_rate: 1
107
- p_dropout: 0.2
108
- style_condition: true
109
-
110
- gpt_checkpoint: gpt.pth
111
- w2v_stat: wav2vec2bert_stats.pt
112
- s2mel_checkpoint: s2mel.pth
113
- emo_matrix: feat2.pt
114
- spk_matrix: feat1.pt
115
- emo_num: [3, 17, 2, 8, 4, 5, 10, 24]
116
- qwen_emo_path: qwen0.6bemo4-merge/
117
- vocoder:
118
- type: "bigvgan"
119
- name: "bigvgan"
120
- version: 2.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
models/IndexTTS-2/checkpoints/feat1.pt.url DELETED
@@ -1 +0,0 @@
1
- https://cnb.cool/mamalalala/20250717/-/lfs/f219cb447d80216ba615666da2ff8d63ac544eee26657f3a7b278692bf7a67c4?name=feat1.pt
 
 
models/IndexTTS-2/checkpoints/feat2.pt.url DELETED
@@ -1 +0,0 @@
1
- https://cnb.cool/mamalalala/20250717/-/lfs/9c4292e96dee535aea9a6206e9a0c856dd578dde9212acdb16dd3ada4d12bf80?name=feat2.pt
 
 
models/IndexTTS-2/checkpoints/gpt.pth.url DELETED
@@ -1 +0,0 @@
1
- https://cnb.cool/mamalalala/20250717/-/lfs/baaaeb8b56328da81731dc540a85a7dee32eca9da28f174b05757cb651c602a4?name=gpt.pth
 
 
models/IndexTTS-2/checkpoints/qwen0.6bemo4-merge/Modelfile DELETED
@@ -1,11 +0,0 @@
1
- # ollama modelfile auto-generated by llamafactory
2
-
3
- FROM .
4
-
5
- TEMPLATE """{{ if .System }}System: {{ .System }}<|endoftext|>
6
- {{ end }}{{ range .Messages }}{{ if eq .Role "user" }}Human: {{ .Content }}<|endoftext|>
7
- Assistant:{{ else if eq .Role "assistant" }}{{ .Content }}<|endoftext|>
8
- {{ end }}{{ end }}"""
9
-
10
- PARAMETER stop "<|endoftext|>"
11
- PARAMETER num_ctx 4096
 
 
 
 
 
 
 
 
 
 
 
 
models/IndexTTS-2/checkpoints/qwen0.6bemo4-merge/added_tokens.json DELETED
@@ -1,28 +0,0 @@
1
- {
2
- "</think>": 151668,
3
- "</tool_call>": 151658,
4
- "</tool_response>": 151666,
5
- "<think>": 151667,
6
- "<tool_call>": 151657,
7
- "<tool_response>": 151665,
8
- "<|box_end|>": 151649,
9
- "<|box_start|>": 151648,
10
- "<|endoftext|>": 151643,
11
- "<|file_sep|>": 151664,
12
- "<|fim_middle|>": 151660,
13
- "<|fim_pad|>": 151662,
14
- "<|fim_prefix|>": 151659,
15
- "<|fim_suffix|>": 151661,
16
- "<|im_end|>": 151645,
17
- "<|im_start|>": 151644,
18
- "<|image_pad|>": 151655,
19
- "<|object_ref_end|>": 151647,
20
- "<|object_ref_start|>": 151646,
21
- "<|quad_end|>": 151651,
22
- "<|quad_start|>": 151650,
23
- "<|repo_name|>": 151663,
24
- "<|video_pad|>": 151656,
25
- "<|vision_end|>": 151653,
26
- "<|vision_pad|>": 151654,
27
- "<|vision_start|>": 151652
28
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
models/IndexTTS-2/checkpoints/qwen0.6bemo4-merge/chat_template.jinja DELETED
@@ -1,4 +0,0 @@
1
- {% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ 'System: ' + system_message + '<|endoftext|>' + '
2
- ' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '<|endoftext|>' + '
3
- Assistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '
4
- ' }}{% endif %}{% endfor %}
 
 
 
 
 
models/IndexTTS-2/checkpoints/qwen0.6bemo4-merge/config.json DELETED
@@ -1,30 +0,0 @@
1
- {
2
- "architectures": [
3
- "Qwen3ForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 151643,
8
- "eos_token_id": 151643,
9
- "head_dim": 128,
10
- "hidden_act": "silu",
11
- "hidden_size": 1024,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 3072,
14
- "max_position_embeddings": 32768,
15
- "max_window_layers": 28,
16
- "model_type": "qwen3",
17
- "num_attention_heads": 16,
18
- "num_hidden_layers": 28,
19
- "num_key_value_heads": 8,
20
- "rms_norm_eps": 1e-06,
21
- "rope_scaling": null,
22
- "rope_theta": 1000000,
23
- "sliding_window": null,
24
- "tie_word_embeddings": true,
25
- "torch_dtype": "bfloat16",
26
- "transformers_version": "4.52.1",
27
- "use_cache": true,
28
- "use_sliding_window": false,
29
- "vocab_size": 151936
30
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
models/IndexTTS-2/checkpoints/qwen0.6bemo4-merge/generation_config.json DELETED
@@ -1,6 +0,0 @@
1
- {
2
- "bos_token_id": 151643,
3
- "eos_token_id": 151643,
4
- "max_new_tokens": 2048,
5
- "transformers_version": "4.52.1"
6
- }
 
 
 
 
 
 
 
models/IndexTTS-2/checkpoints/qwen0.6bemo4-merge/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
models/IndexTTS-2/checkpoints/qwen0.6bemo4-merge/model.safetensors.url DELETED
@@ -1 +0,0 @@
1
- https://cnb.cool/mamalalala/20250717/-/lfs/11293257a8df593c154a8ecd5fc039f3076de35411e35f06d41b471e136f6641?name=model.safetensors
 
 
models/IndexTTS-2/checkpoints/qwen0.6bemo4-merge/special_tokens_map.json DELETED
@@ -1,31 +0,0 @@
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": "<|endoftext|>",
19
- "lstrip": false,
20
- "normalized": false,
21
- "rstrip": false,
22
- "single_word": false
23
- },
24
- "pad_token": {
25
- "content": "<|endoftext|>",
26
- "lstrip": false,
27
- "normalized": false,
28
- "rstrip": false,
29
- "single_word": false
30
- }
31
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
models/IndexTTS-2/checkpoints/qwen0.6bemo4-merge/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
- size 11422654
 
 
 
 
models/IndexTTS-2/checkpoints/qwen0.6bemo4-merge/tokenizer_config.json DELETED
@@ -1,240 +0,0 @@
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
- "clean_up_tokenization_spaces": false,
231
- "eos_token": "<|endoftext|>",
232
- "errors": "replace",
233
- "extra_special_tokens": {},
234
- "model_max_length": 131072,
235
- "pad_token": "<|endoftext|>",
236
- "padding_side": "left",
237
- "split_special_tokens": false,
238
- "tokenizer_class": "Qwen2Tokenizer",
239
- "unk_token": null
240
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
models/IndexTTS-2/checkpoints/qwen0.6bemo4-merge/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
models/IndexTTS-2/checkpoints/s2mel.pth.url DELETED
@@ -1 +0,0 @@
1
- https://cnb.cool/mamalalala/20250717/-/lfs/aae1bb12017cbb47e7a5ce537fc82f40b6b1deb71acdb9b8f25686f32714b636?name=s2mel.pth