Hugging Face's logo

Jmica
/
audiobook_models

Safetensors
GGUF
conversational
Model card Files
xet
 Community
Jmica commited on
Commit
bff5c29
·
verified ·
1 Parent(s): 046b280

Upload 29 files

Browse files
Files changed (30) hide show
  1. .gitattributes +4 -0
  2. 1.5v1_base/config.json +115 -0
  3. 1.5v1_base/model-00001-of-00003.safetensors +3 -0
  4. 1.5v1_base/model-00002-of-00003.safetensors +3 -0
  5. 1.5v1_base/model-00003-of-00003.safetensors +3 -0
  6. 1.5v1_base/model.safetensors.index.json +0 -0
  7. 1.5v1_base/preprocessor_config.json +13 -0
  8. 7bv1_base/config.json +116 -0
  9. 7bv1_base/model-00001-of-00010.safetensors +3 -0
  10. 7bv1_base/model-00002-of-00010.safetensors +3 -0
  11. 7bv1_base/model-00003-of-00010.safetensors +3 -0
  12. 7bv1_base/model-00004-of-00010.safetensors +3 -0
  13. 7bv1_base/model-00005-of-00010.safetensors +3 -0
  14. 7bv1_base/model-00006-of-00010.safetensors +3 -0
  15. 7bv1_base/model-00007-of-00010.safetensors +3 -0
  16. 7bv1_base/model-00008-of-00010.safetensors +3 -0
  17. 7bv1_base/model-00009-of-00010.safetensors +3 -0
  18. 7bv1_base/model-00010-of-00010.safetensors +3 -0
  19. 7bv1_base/model.safetensors.index.json +0 -0
  20. 7bv1_base/preprocessor_config.json +13 -0
  21. GLM-OCR-GGUF/.cache/huggingface/.gitignore +1 -0
  22. GLM-OCR-GGUF/.cache/huggingface/download/GLM-OCR-Q8_0.gguf.metadata +3 -0
  23. GLM-OCR-GGUF/.cache/huggingface/download/mmproj-GLM-OCR-Q8_0.gguf.metadata +3 -0
  24. GLM-OCR-GGUF/GLM-OCR-Q8_0.gguf +3 -0
  25. GLM-OCR-GGUF/mmproj-GLM-OCR-Q8_0.gguf +3 -0
  26. Qwen3-VL-4B-Instruct-GGUF/.cache/huggingface/.gitignore +1 -0
  27. Qwen3-VL-4B-Instruct-GGUF/.cache/huggingface/download/Qwen3VL-4B-Instruct-Q4_K_M.gguf.metadata +3 -0
  28. Qwen3-VL-4B-Instruct-GGUF/.cache/huggingface/download/mmproj-Qwen3VL-4B-Instruct-Q8_0.gguf.metadata +3 -0
  29. Qwen3-VL-4B-Instruct-GGUF/Qwen3VL-4B-Instruct-F16.gguf +3 -0
  30. Qwen3-VL-4B-Instruct-GGUF/mmproj-Qwen3VL-4B-Instruct-F16.gguf +3 -0
.gitattributes CHANGED
@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ GLM-OCR-GGUF/GLM-OCR-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
37
+ GLM-OCR-GGUF/mmproj-GLM-OCR-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Qwen3-VL-4B-Instruct-GGUF/mmproj-Qwen3VL-4B-Instruct-F16.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Qwen3-VL-4B-Instruct-GGUF/Qwen3VL-4B-Instruct-F16.gguf filter=lfs diff=lfs merge=lfs -text
1.5v1_base/config.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "acoustic_vae_dim": 64,
3
+ "acoustic_tokenizer_config": {
4
+ "causal": true,
5
+ "channels": 1,
6
+ "conv_bias": true,
7
+ "conv_norm": "none",
8
+ "corpus_normalize": 0.0,
9
+ "decoder_depths": null,
10
+ "decoder_n_filters": 32,
11
+ "decoder_ratios": [
12
+ 8,
13
+ 5,
14
+ 5,
15
+ 4,
16
+ 2,
17
+ 2
18
+ ],
19
+ "disable_last_norm": true,
20
+ "encoder_depths": "3-3-3-3-3-3-8",
21
+ "encoder_n_filters": 32,
22
+ "encoder_ratios": [
23
+ 8,
24
+ 5,
25
+ 5,
26
+ 4,
27
+ 2,
28
+ 2
29
+ ],
30
+ "fix_std": 0.5,
31
+ "layer_scale_init_value": 1e-06,
32
+ "layernorm": "RMSNorm",
33
+ "layernorm_elementwise_affine": true,
34
+ "layernorm_eps": 1e-05,
35
+ "mixer_layer": "depthwise_conv",
36
+ "model_type": "vibevoice_acoustic_tokenizer",
37
+ "pad_mode": "constant",
38
+ "std_dist_type": "gaussian",
39
+ "vae_dim": 64,
40
+ "weight_init_value": 0.01
41
+ },
42
+ "architectures": [
43
+ "VibeVoiceForConditionalGeneration"
44
+ ],
45
+ "decoder_config": {
46
+ "attention_dropout": 0.0,
47
+ "hidden_act": "silu",
48
+ "hidden_size": 1536,
49
+ "initializer_range": 0.02,
50
+ "intermediate_size": 8960,
51
+ "max_position_embeddings": 65536,
52
+ "max_window_layers": 28,
53
+ "model_type": "qwen2",
54
+ "num_attention_heads": 12,
55
+ "num_hidden_layers": 28,
56
+ "num_key_value_heads": 2,
57
+ "rms_norm_eps": 1e-06,
58
+ "rope_scaling": null,
59
+ "rope_theta": 1000000.0,
60
+ "sliding_window": null,
61
+ "tie_word_embeddings": true,
62
+ "torch_dtype": "bfloat16",
63
+ "use_cache": true,
64
+ "use_sliding_window": false,
65
+ "vocab_size": 151936
66
+ },
67
+ "diffusion_head_config": {
68
+ "ddpm_batch_mul": 4,
69
+ "ddpm_beta_schedule": "cosine",
70
+ "ddpm_num_inference_steps": 20,
71
+ "ddpm_num_steps": 1000,
72
+ "diffusion_type": "ddpm",
73
+ "head_ffn_ratio": 3.0,
74
+ "head_layers": 4,
75
+ "hidden_size": 1536,
76
+ "latent_size": 64,
77
+ "model_type": "vibevoice_diffusion_head",
78
+ "prediction_type": "v_prediction",
79
+ "rms_norm_eps": 1e-05,
80
+ "speech_vae_dim": 64
81
+ },
82
+ "model_type": "vibevoice",
83
+ "semantic_tokenizer_config": {
84
+ "causal": true,
85
+ "channels": 1,
86
+ "conv_bias": true,
87
+ "conv_norm": "none",
88
+ "corpus_normalize": 0.0,
89
+ "disable_last_norm": true,
90
+ "encoder_depths": "3-3-3-3-3-3-8",
91
+ "encoder_n_filters": 32,
92
+ "encoder_ratios": [
93
+ 8,
94
+ 5,
95
+ 5,
96
+ 4,
97
+ 2,
98
+ 2
99
+ ],
100
+ "fix_std": 0,
101
+ "layer_scale_init_value": 1e-06,
102
+ "layernorm": "RMSNorm",
103
+ "layernorm_elementwise_affine": true,
104
+ "layernorm_eps": 1e-05,
105
+ "mixer_layer": "depthwise_conv",
106
+ "model_type": "vibevoice_semantic_tokenizer",
107
+ "pad_mode": "constant",
108
+ "std_dist_type": "none",
109
+ "vae_dim": 128,
110
+ "weight_init_value": 0.01
111
+ },
112
+ "semantic_vae_dim": 128,
113
+ "torch_dtype": "bfloat16",
114
+ "transformers_version": "4.51.3"
115
+ }
1.5v1_base/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5f0a61ddeaeb028e3af540ba4dee7933ad30f9f30b6e1320dd9c875a2daa033
3
+ size 1975317828
1.5v1_base/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81c3891f7b2493eb48a9eb6f5be0df48d4f1a4bfd952d84e21683ca6d0bf7969
3
+ size 1983051688
1.5v1_base/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb6e7e5e86b4a41fffbe1f3aaf445d0d50b5e21ed47574101b777f77d75fa196
3
+ size 1449832938
1.5v1_base/model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
1.5v1_base/preprocessor_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "processor_class": "VibeVoiceProcessor",
3
+ "speech_tok_compress_ratio": 3200,
4
+ "db_normalize": true,
5
+ "audio_processor": {
6
+ "feature_extractor_type": "VibeVoiceTokenizerProcessor",
7
+ "sampling_rate": 24000,
8
+ "normalize_audio": true,
9
+ "target_dB_FS": -25,
10
+ "eps": 1e-06
11
+ },
12
+ "language_model_pretrained_name": "Qwen/Qwen2.5-1.5B"
13
+ }
7bv1_base/config.json ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "acostic_vae_dim": 64,
3
+ "acoustic_tokenizer_config": {
4
+ "causal": true,
5
+ "channels": 1,
6
+ "conv_bias": true,
7
+ "conv_norm": "none",
8
+ "corpus_normalize": 0.0,
9
+ "decoder_depths": null,
10
+ "decoder_n_filters": 32,
11
+ "decoder_ratios": [
12
+ 8,
13
+ 5,
14
+ 5,
15
+ 4,
16
+ 2,
17
+ 2
18
+ ],
19
+ "disable_last_norm": true,
20
+ "encoder_depths": "3-3-3-3-3-3-8",
21
+ "encoder_n_filters": 32,
22
+ "encoder_ratios": [
23
+ 8,
24
+ 5,
25
+ 5,
26
+ 4,
27
+ 2,
28
+ 2
29
+ ],
30
+ "fix_std": 0.5,
31
+ "layer_scale_init_value": 1e-06,
32
+ "layernorm": "RMSNorm",
33
+ "layernorm_elementwise_affine": true,
34
+ "layernorm_eps": 1e-05,
35
+ "mixer_layer": "depthwise_conv",
36
+ "model_type": "vibevoice_acoustic_tokenizer",
37
+ "pad_mode": "constant",
38
+ "std_dist_type": "gaussian",
39
+ "vae_dim": 64,
40
+ "weight_init_value": 0.01
41
+ },
42
+ "architectures": [
43
+ "VibeVoiceForConditionalGeneration"
44
+ ],
45
+ "decoder_config": {
46
+ "attention_dropout": 0.0,
47
+ "hidden_act": "silu",
48
+ "hidden_size": 3584,
49
+ "initializer_range": 0.02,
50
+ "intermediate_size": 18944,
51
+ "max_position_embeddings": 32768,
52
+ "max_window_layers": 28,
53
+ "model_type": "qwen2",
54
+ "num_attention_heads": 28,
55
+ "num_hidden_layers": 28,
56
+ "num_key_value_heads": 4,
57
+ "rms_norm_eps": 1e-06,
58
+ "rope_scaling": null,
59
+ "rope_theta": 1000000.0,
60
+ "sliding_window": null,
61
+ "torch_dtype": "bfloat16",
62
+ "use_cache": true,
63
+ "use_mrope": false,
64
+ "use_sliding_window": false,
65
+ "vocab_size": 152064
66
+ },
67
+ "diffusion_head_config": {
68
+ "ddpm_batch_mul": 4,
69
+ "ddpm_beta_schedule": "cosine",
70
+ "ddpm_num_inference_steps": 20,
71
+ "ddpm_num_steps": 1000,
72
+ "diffusion_type": "ddpm",
73
+ "head_ffn_ratio": 3.0,
74
+ "head_layers": 4,
75
+ "hidden_size": 3584,
76
+ "latent_size": 64,
77
+ "model_type": "vibevoice_diffusion_head",
78
+ "prediction_type": "v_prediction",
79
+ "rms_norm_eps": 1e-05,
80
+ "speech_vae_dim": 64
81
+ },
82
+ "model_type": "vibevoice",
83
+ "semantic_tokenizer_config": {
84
+ "causal": true,
85
+ "channels": 1,
86
+ "conv_bias": true,
87
+ "conv_norm": "none",
88
+ "corpus_normalize": 0.0,
89
+ "disable_last_norm": true,
90
+ "encoder_depths": "3-3-3-3-3-3-8",
91
+ "encoder_n_filters": 32,
92
+ "encoder_ratios": [
93
+ 8,
94
+ 5,
95
+ 5,
96
+ 4,
97
+ 2,
98
+ 2
99
+ ],
100
+ "fix_std": 0,
101
+ "layer_scale_init_value": 1e-06,
102
+ "layernorm": "RMSNorm",
103
+ "layernorm_elementwise_affine": true,
104
+ "layernorm_eps": 1e-05,
105
+ "mixer_layer": "depthwise_conv",
106
+ "model_type": "vibevoice_semantic_tokenizer",
107
+ "pad_mode": "constant",
108
+ "std_dist_type": "none",
109
+ "vae_dim": 128,
110
+ "weight_init_value": 0.01
111
+ },
112
+ "semantic_vae_dim": 128,
113
+ "tie_word_embeddings": false,
114
+ "torch_dtype": "bfloat16",
115
+ "transformers_version": "4.51.3"
116
+ }
7bv1_base/model-00001-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae28d5c8f3587b518c7e371e96ebb69f74d854a854119acf433952bbc1926325
3
+ size 1886424044
7bv1_base/model-00002-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c56b1ca707e31e435ded8b03baa4938d88275bf0ba7033935a16d8173a99ff85
3
+ size 1864468520
7bv1_base/model-00003-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48bfb4af453d45e488050e90d3f39da0189f1c10a77d75223c2c2ced8b035baa
3
+ size 1864468520
7bv1_base/model-00004-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4893be477be68e53b8a9616422b99065f3d1431cce9efe0a1653495e9cf4df6
3
+ size 1864468544
7bv1_base/model-00005-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:471690e9846e791def400fefa3d2103c9839dc8a3e987b175f6539c7412422d6
3
+ size 1864468568
7bv1_base/model-00006-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7918d400ba895b15a1126fde242028e5d05b37bab0c0427944de81df80f901f
3
+ size 1864468568
7bv1_base/model-00007-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4f00ebea5a9f76eea891b3457621955433149ae603d921afa1498e46683ba37
3
+ size 1864468568
7bv1_base/model-00008-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc4b6fce97b76e847c742b59ab9463fd04b6d9fa69fc33e747ff722c2ab8cc28
3
+ size 1972552744
7bv1_base/model-00009-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:824db8970518950117f0d6ed859740d973b9436718c24f29bc78854c4587a4b2
3
+ size 1959739938
7bv1_base/model-00010-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc76bba7a46a0a748cc169efb6ccfb7617881e0fc3b533f67887d5957e1836e3
3
+ size 1681341960
7bv1_base/model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
7bv1_base/preprocessor_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "processor_class": "VibeVoiceProcessor",
3
+ "speech_tok_compress_ratio": 3200,
4
+ "db_normalize": true,
5
+ "audio_processor": {
6
+ "feature_extractor_type": "VibeVoiceTokenizerProcessor",
7
+ "sampling_rate": 24000,
8
+ "normalize_audio": true,
9
+ "target_dB_FS": -25,
10
+ "eps": 1e-06
11
+ },
12
+ "language_model_pretrained_name": "Qwen/Qwen2.5-7B"
13
+ }
GLM-OCR-GGUF/.cache/huggingface/.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ *
GLM-OCR-GGUF/.cache/huggingface/download/GLM-OCR-Q8_0.gguf.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ a3f92e10071d8bc099d75f76200813bdf2897d0d
2
+ 58b4b29c3303fc4d7e44d750243b78c475103118ccea1223a8c419f97908c315
3
+ 1771652021.8342786
GLM-OCR-GGUF/.cache/huggingface/download/mmproj-GLM-OCR-Q8_0.gguf.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ a3f92e10071d8bc099d75f76200813bdf2897d0d
2
+ 9c4b58e33e316ed142eb5dcb41abec3844d3e6e5dc361ffb782c3fa9d175141f
3
+ 1771652053.1239173
GLM-OCR-GGUF/GLM-OCR-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58b4b29c3303fc4d7e44d750243b78c475103118ccea1223a8c419f97908c315
3
+ size 950436704
GLM-OCR-GGUF/mmproj-GLM-OCR-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c4b58e33e316ed142eb5dcb41abec3844d3e6e5dc361ffb782c3fa9d175141f
3
+ size 484403648
Qwen3-VL-4B-Instruct-GGUF/.cache/huggingface/.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ *
Qwen3-VL-4B-Instruct-GGUF/.cache/huggingface/download/Qwen3VL-4B-Instruct-Q4_K_M.gguf.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ 1cd86afb9a95c410a6038ab3b40d8b578c892266
2
+ 66358cb18bb6b3b1b6675aa412c7a88ef01d228f481184d13668e5201c730a0a
3
+ 1771652172.6905103
Qwen3-VL-4B-Instruct-GGUF/.cache/huggingface/download/mmproj-Qwen3VL-4B-Instruct-Q8_0.gguf.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ 1cd86afb9a95c410a6038ab3b40d8b578c892266
2
+ 30ba2c7dd3127a4561b6cba9d13d0f711c91bdb38742e2f56d73c8cb596bd06d
3
+ 1771652197.1850743
Qwen3-VL-4B-Instruct-GGUF/Qwen3VL-4B-Instruct-F16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a6fb1ed053e162887bfc372bd7ffaaa9b8e4049ac6e9b9398ae7277162ec761
3
+ size 8051286144
Qwen3-VL-4B-Instruct-GGUF/mmproj-Qwen3VL-4B-Instruct-F16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:256f3a43bd4205ffef48d6b92715e1e70b5b0e9aef06522584967513a9985331
3
+ size 836180256