Hugging Face's logo

Backup-bdg
/
Xoron-Dev-MultiMoe

Any-to-Any
Transformers
Safetensors
English
xoron
multimodal
Mixture of Experts
text-to-image
image editing
image to video
text-to-video
video editing
text-to-speech
speech-to-text
speech-to-speech
image-to-text
video-to-text
agentic
tool-use
flow-matching
3d-rope
titok
vidtok
dual-stream-attention
zero-shot-voice-cloning
bigvgan
snake-activation
multi-receptive-field-fusion
custom_code
Model card Files
xet
 Community
1
Backup-bdg commited on
Commit
6c5e835
·
verified ·
1 Parent(s): 2575c9d

Update model weights after training (epoch 1, loss 4.0192)

Browse files
Files changed (7) hide show
  1. audio_decoder.safetensors +1 -1
  2. cross_attention.safetensors +1 -1
  3. generator.safetensors +1 -1
  4. llm.safetensors +1 -1
  5. streaming_state.json +15 -15
  6. trainer_state.json +1 -1
  7. training_state.pt +2 -2
audio_decoder.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37e38d5f45ab1bb841c51d43d1a830339c9554d7b7121b40c29543be6b8bb246
3
  size 1458415836
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cc0af3086d6987e71c00b7121394b8ac820d2276ff994014479d4fc2cf094bf
3
  size 1458415836
cross_attention.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7967eb8d40a1c69ade87aaae8872447a9f3b28418fadde6d1a8f876d96a6848
3
  size 174191400
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9034e718a6461ed04d5723c8ecf429d0daedb7fc49274a1fbd17b80bb9dd77b9
3
  size 174191400
generator.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89ea74af2d5ac45430e7dc96fd17ddf368b8baa87a4133046782ec32e7a63224
3
  size 629440508
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02673bab0a9e2949c2f3bfe0725ff77cd631fd89a559d86e9c886c99455a5e72
3
  size 629440508
llm.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96e14153b590b91954c672ba79a681cd40c08dfc82dcb9e5500e87c2d8d23c83
3
  size 1506831304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4ce3c75e0ec09d93c0580ed862f12191e3ea3bd53ab8906e0108cafd5d6fc18
3
  size 1506831304
streaming_state.json CHANGED
@@ -1,26 +1,26 @@
1
  {
2
- "epoch": 4,
3
- "unique_samples": 800,
4
- "total_yields": 1600,
5
  "dataset_positions": {
6
- "WebSight": 136,
7
- "ScienceQA": 114,
8
- "InstructPix2Pix": 136,
9
- "Flickr8k": 136,
10
- "NewYorker": 136,
11
  "Football": 6,
12
- "MagicBrush": 136
13
  },
14
  "modality_positions": {
15
  "text": {},
16
  "image": {
17
- "WebSight": 136,
18
- "ScienceQA": 114,
19
- "InstructPix2Pix": 136,
20
- "Flickr8k": 136,
21
- "NewYorker": 136,
22
  "Football": 6,
23
- "MagicBrush": 136
24
  },
25
  "video": {},
26
  "audio": {}
 
1
  {
2
+ "epoch": 5,
3
+ "unique_samples": 1100,
4
+ "total_yields": 2200,
5
  "dataset_positions": {
6
+ "WebSight": 186,
7
+ "ScienceQA": 164,
8
+ "InstructPix2Pix": 186,
9
+ "Flickr8k": 186,
10
+ "NewYorker": 186,
11
  "Football": 6,
12
+ "MagicBrush": 186
13
  },
14
  "modality_positions": {
15
  "text": {},
16
  "image": {
17
+ "WebSight": 186,
18
+ "ScienceQA": 164,
19
+ "InstructPix2Pix": 186,
20
+ "Flickr8k": 186,
21
+ "NewYorker": 186,
22
  "Football": 6,
23
+ "MagicBrush": 186
24
  },
25
  "video": {},
26
  "audio": {}
trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "best_model_checkpoint": "/kaggle/working/xoron-final",
3
- "best_metric": 4.291641629748046,
4
  "epoch": 1,
5
  "epochs_completed": 1,
6
  "global_step": 37,
 
1
  {
2
  "best_model_checkpoint": "/kaggle/working/xoron-final",
3
+ "best_metric": 4.019162586334472,
4
  "epoch": 1,
5
  "epochs_completed": 1,
6
  "global_step": 37,
training_state.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9329bf26836f4da61c1deaa53cc9d62b880df8b96c33af2739c8288691dd2b3a
3
- size 1419713437
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cff88f1a8ee14094dfffadc0ac06d52480a2d90bd740252423ecf77cdef8f6cc
3
+ size 1419723549