Hugging Face's logo

stepfun-ai
/
Step-Audio-AQAA

Safetensors
mmgpt_step1_v2
Model card Files Community
2
buyun commited on
Commit
a672832
·
verified ·
1 Parent(s): 0e962db

initial

Browse files
Files changed (32) hide show
  1. config.json +33 -0
  2. model-00001.safetensors +3 -0
  3. model-00002.safetensors +3 -0
  4. model-00003.safetensors +3 -0
  5. model-00004.safetensors +3 -0
  6. model-00005.safetensors +3 -0
  7. model-00006.safetensors +3 -0
  8. model-00007.safetensors +3 -0
  9. model-00008.safetensors +3 -0
  10. model-00009.safetensors +3 -0
  11. model-00010.safetensors +3 -0
  12. model-00011.safetensors +3 -0
  13. model-00012.safetensors +3 -0
  14. model-00013.safetensors +3 -0
  15. model-00014.safetensors +3 -0
  16. model-00015.safetensors +3 -0
  17. model-00016.safetensors +3 -0
  18. model-00017.safetensors +3 -0
  19. model-00018.safetensors +3 -0
  20. model-00019.safetensors +3 -0
  21. model-00020.safetensors +3 -0
  22. model-00021.safetensors +3 -0
  23. model-00022.safetensors +3 -0
  24. model-00023.safetensors +3 -0
  25. model-00024.safetensors +3 -0
  26. model-00025.safetensors +3 -0
  27. model-00026.safetensors +3 -0
  28. model-00027.safetensors +3 -0
  29. model-00028.safetensors +3 -0
  30. model.safetensors.index.json +0 -0
  31. preprocessor_config.json +19 -0
  32. step2_tokenizer_241028.model +3 -0
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MMGPTStep1ForCausalLMV4"
4
+ ],
5
+ "model_type": "mmgpt_step1_v2",
6
+ "hidden_size": 12288,
7
+ "intermediate_size": 31232,
8
+ "num_attention_heads": 96,
9
+ "num_attention_groups": 8,
10
+ "num_hidden_layers": 88,
11
+ "max_seq_len": 999999,
12
+ "vocab_size": 74752,
13
+ "rms_norm_eps": 1e-05,
14
+ "torch_dtype": "bfloat16",
15
+ "im_end_token": "<im_end>",
16
+ "im_patch_token": "<im_patch>",
17
+ "im_start_token": "<im_start>",
18
+ "image_token_len": 169,
19
+ "use_im_start_end": true,
20
+ "vision_select_layer": -1,
21
+ "understand_projector_stride": 2,
22
+ "vit_scale": 1.0,
23
+ "projector_bias": false,
24
+ "vision_tower_config": {
25
+ "hidden_size": 1792,
26
+ "output_hidden_size": 4096,
27
+ "image_size": 728,
28
+ "intermediate_size": 15360,
29
+ "num_attention_heads": 16,
30
+ "num_hidden_layers": 63,
31
+ "patch_size": 14
32
+ }
33
+ }
model-00001.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:401119d809d338614caa2adabe6e55f7d5aad1a7395bf624bdcdc14605de6181
3
+ size 9434733376
model-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:799f7fad3eb75123046be5a822337ed28a405c8136c5243e380d59241a6cd85b
3
+ size 9940651088
model-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb21dfe9f67bde6d78db684419372fd245dcea5e167ad7b2b94ba613db78303b
3
+ size 9940676016
model-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3f6caa5db5606bed09b08a53b51fac44f94701880d5d0cf3cdda42c0370c46b
3
+ size 9991007912
model-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:660af7ae96e6369b92a987327c343adc88706047d991338d890ab3fdde174850
3
+ size 9638661344
model-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2434a2806cc231904ee07bc7575c49c28e4f74f318fb041e37fb8bf2d540b1af
3
+ size 9940676048
model-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:205072bb59dafe89f248968a26298b7f91a06e0150a66690ce99cbcd8bae686b
3
+ size 9991007944
model-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c476603a3cd719dfc2832cfe9c312c459260f90dd6af8125b75e45a0604c8ae7
3
+ size 9638661352
model-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d29cbfce6f0738a4431c6a885ddc4a01ca0831f56d7748d8277971ba268efda0
3
+ size 9940676048
model-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f14f17011d5c36e84b0393611d62c9a26e6fb3a403bae1e26028b6377c183f63
3
+ size 9991007944
model-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ca4a5d29e943b4b4a7e6c11de86e44d40940c739f0fb8801030e86ac54f55d7
3
+ size 9638661352
model-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb1c87ec0c8bc78feba6bb39432bb009b040d2e9eb15d068fd96e824cb88e957
3
+ size 9940676048
model-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9f568cce91b80a44bd5cf9448ac4ff2ac06c847fccf9dce488849152e1e9a89
3
+ size 9991007944
model-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d038f5d81a1eec434acaa4a56c59c7962f012fef531dec1e3784973ea166b68
3
+ size 9638661352
model-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01117629ed25b5991e8321673913cc740ef276d1c36b6a47fa13385ce3fc9b7f
3
+ size 9940676048
model-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a0bb03965b46b712cd9bc786e4e8e8ccdc30bd8dea91d38304afb92a5eaeeb5
3
+ size 9991007944
model-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:951651e97024ad37b9c8cfb323742a511b622e10f1ad48b1eb8896390a580b8c
3
+ size 9638661352
model-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b8a435c4edf2953f52ffd5affdfd31792ef5f8f9d6847ca9aa69c3fbfcfb264
3
+ size 9940676048
model-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a7873f4f8340ac8e7e8240f7230b3c500aa077ea220d51e71a28d52d0641785
3
+ size 9991007944
model-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ce33b95783e549d310b25419ed35d62d2ec9ed18ba8ceedb4a1b3950fed9035
3
+ size 9638661352
model-00021.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba300443554c351ff8106e0532c1c4fb74d143c4e4033b521c75dcd84d055a86
3
+ size 9940676048
model-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0b4e8ca6796eeff46a340a9c5294468d64811d5fdb87786d277000ab48364f0
3
+ size 9991007944
model-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f1bf0a8d954e6cae923f93d9becfbdcb09b7c565389b22a65fbf36b4d0afc7a
3
+ size 9638661352
model-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8ebaf3413cc6060cb19f94f50f286fdc121a00d21fb49c26ee7c376046aef1b
3
+ size 9940676048
model-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24dbceac3ccb0ac1691d4b05b99ef24e1fc39f551b0f6c887c0c915a71f1c0a4
3
+ size 9991007944
model-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:674340fe11ea60213891e8fcd90bbf30dd3b73f29d6bca8de169e23be899db7c
3
+ size 9638661352
model-00027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa6eaa7e7154c490eac6eb233220daec97ae3dc3c9a36a95fc9c14f020d149c6
3
+ size 9940676048
model-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:504b2b0e065e3e97150b9d9e51fb40710d65c814c63e3b32e56313e0bbab59cb
3
+ size 7449184288
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_center_crop": false,
3
+ "do_normalize": true,
4
+ "do_resize": true,
5
+ "feature_extractor_type": "CLIPFeatureExtractor",
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_std": [
12
+ 0.26862954,
13
+ 0.26130258,
14
+ 0.27577711
15
+ ],
16
+ "resample": 3,
17
+ "size": 728,
18
+ "mode": "bilinear"
19
+ }
step2_tokenizer_241028.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22f3dc190340b02713be9cb43d5fcf7e3c01c302d407c4470def4bac5eac9fdc
3
+ size 1264015