|
|
[h264 @ 0x9b59c40] mmco: unref short failure |
|
|
[h264 @ 0x9b59c40] mmco: unref short failure |
|
|
[h264 @ 0x86a1a40] mmco: unref short failure |
|
|
[h264 @ 0x86a1a40] mmco: unref short failure |
|
|
[h264 @ 0x9eeff00] mmco: unref short failure |
|
|
[h264 @ 0x9eeff00] mmco: unref short failure |
|
|
[h264 @ 0x9741000] mmco: unref short failure |
|
|
[h264 @ 0x8a2a980] mmco: unref short failure |
|
|
[h264 @ 0x8a2a980] mmco: unref short failure |
|
|
[h264 @ 0x8241080] mmco: unref short failure |
|
|
[h264 @ 0x8241080] mmco: unref short failure |
|
|
[h264 @ 0x831f5c0] mmco: unref short failure |
|
|
[h264 @ 0x9064ac0] mmco: unref short failure |
|
|
[h264 @ 0x9064ac0] mmco: unref short failure |
|
|
[h264 @ 0x83a9cc0] mmco: unref short failure |
|
|
[h264 @ 0x83a9cc0] mmco: unref short failure |
|
|
[h264 @ 0xed7b140] mmco: unref short failure |
|
|
[h264 @ 0xed7b140] mmco: unref short failure |
|
|
[h264 @ 0x8892600] mmco: unref short failure |
|
|
[h264 @ 0x20ace480] mmco: unref short failure |
|
|
[h264 @ 0x20ace480] mmco: unref short failure |
|
|
[h264 @ 0x9aedd80] mmco: unref short failure |
|
|
[h264 @ 0x15769000] mmco: unref short failure |
|
|
[h264 @ 0x15769000] mmco: unref short failure |
|
|
[h264 @ 0x9821380] mmco: unref short failure |
|
|
[h264 @ 0x9821380] mmco: unref short failure |
|
|
[h264 @ 0x111680c0] mmco: unref short failure |
|
|
[h264 @ 0x83b4dc0] mmco: unref short failure |
|
|
[h264 @ 0x83b4dc0] mmco: unref short failure |
|
|
[h264 @ 0x9d5e500] mmco: unref short failure |
|
|
[h264 @ 0x9d5e500] mmco: unref short failure |
|
|
[h264 @ 0x12ff4840] mmco: unref short failure |
|
|
[h264 @ 0x12ff4840] mmco: unref short failure |
|
|
[h264 @ 0x976dfc0] mmco: unref short failure |
|
|
[h264 @ 0xd4e1180] mmco: unref short failure |
|
|
[h264 @ 0xd4e1180] mmco: unref short failure |
|
|
[h264 @ 0x976ab80] mmco: unref short failure |
|
|
[h264 @ 0x976ab80] mmco: unref short failure |
|
|
[h264 @ 0x9d6b5c0] mmco: unref short failure |
|
|
[h264 @ 0xfceee00] mmco: unref short failure |
|
|
[h264 @ 0xfceee00] mmco: unref short failure |
|
|
[h264 @ 0x838ff40] mmco: unref short failure |
|
|
[h264 @ 0x838ff40] mmco: unref short failure |
|
|
[h264 @ 0x1e7dba40] mmco: unref short failure |
|
|
[h264 @ 0x1e7dba40] mmco: unref short failure |
|
|
[h264 @ 0x953b3c0] mmco: unref short failure |
|
|
[h264 @ 0x953b3c0] mmco: unref short failure |
|
|
[h264 @ 0x9d5e500] mmco: unref short failure |
|
|
[h264 @ 0x9d5e500] mmco: unref short failure |
|
|
[h264 @ 0x11e6fcc0] mmco: unref short failure |
|
|
[h264 @ 0x93d7480] mmco: unref short failure |
|
|
[h264 @ 0x93d7480] mmco: unref short failure |
|
|
[h264 @ 0x12ff4840] mmco: unref short failure |
|
|
[h264 @ 0x12ff4840] mmco: unref short failure |
|
|
[h264 @ 0xfceee00] mmco: unref short failure |
|
|
[h264 @ 0xfceee00] mmco: unref short failure |
|
|
[h264 @ 0xfceee00] mmco: unref short failure |
|
|
[h264 @ 0x8bc3980] mmco: unref short failure |
|
|
[h264 @ 0x8bc3980] mmco: unref short failure |
|
|
[h264 @ 0x9c304c0] mmco: unref short failure |
|
|
[h264 @ 0x9c304c0] mmco: unref short failure |
|
|
[h264 @ 0xb6e6a40] mmco: unref short failure |
|
|
[h264 @ 0x8b27a00] mmco: unref short failure |
|
|
[h264 @ 0x8b27a00] mmco: unref short failure |
|
|
[h264 @ 0x1b4bdc40] mmco: unref short failure |
|
|
[h264 @ 0x1b4bdc40] mmco: unref short failure |
|
|
[h264 @ 0x175507c0] mmco: unref short failure |
|
|
[h264 @ 0x175507c0] mmco: unref short failure |
|
|
[h264 @ 0x95b2cc0] mmco: unref short failure |
|
|
[h264 @ 0x13094500] mmco: unref short failure |
|
|
[h264 @ 0x97cf300] mmco: unref short failure |
|
|
[h264 @ 0x97cf300] mmco: unref short failure |
|
|
[h264 @ 0x8338900] mmco: unref short failure |
|
|
[h264 @ 0x846fbc0] mmco: unref short failure |
|
|
[h264 @ 0x846fbc0] mmco: unref short failure |
|
|
[h264 @ 0x8654080] mmco: unref short failure |
|
|
[h264 @ 0x15e09fc0] mmco: unref short failure |
|
|
[h264 @ 0x15e09fc0] mmco: unref short failure |
|
|
[h264 @ 0x8654080] mmco: unref short failure |
|
|
[h264 @ 0x120ec300] mmco: unref short failure |
|
|
[h264 @ 0x120ec300] mmco: unref short failure |
|
|
[h264 @ 0x9518d00] mmco: unref short failure |
|
|
[h264 @ 0x9068a00] mmco: unref short failure |
|
|
[h264 @ 0x9068a00] mmco: unref short failure |
|
|
[h264 @ 0x9068a00] mmco: unref short failure |
|
|
[h264 @ 0x9068a00] mmco: unref short failure |
|
|
[h264 @ 0x9068a00] mmco: unref short failure |
|
|
[h264 @ 0x15769000] mmco: unref short failure |
|
|
[h264 @ 0x84bffc0] mmco: unref short failure |
|
|
[h264 @ 0x84bffc0] mmco: unref short failure |
|
|
[h264 @ 0x15769000] mmco: unref short failure |
|
|
[h264 @ 0x1aa11900] mmco: unref short failure |
|
|
[h264 @ 0x1aa11900] mmco: unref short failure |
|
|
[h264 @ 0x82bb480] mmco: unref short failure |
|
|
[h264 @ 0x82bb480] mmco: unref short failure |
|
|
[h264 @ 0x10d43940] mmco: unref short failure |
|
|
[h264 @ 0x9973540] mmco: unref short failure |
|
|
[h264 @ 0x9973540] mmco: unref short failure |
|
|
[h264 @ 0xa2da800] mmco: unref short failure |
|
|
[h264 @ 0xa2da800] mmco: unref short failure |
|
|
[h264 @ 0x9973540] mmco: unref short failure |
|
|
[h264 @ 0x9973540] mmco: unref short failure |
|
|
[h264 @ 0x10d43940] mmco: unref short failure |
|
|
[h264 @ 0x15e09fc0] mmco: unref short failure |
|
|
[h264 @ 0x15e09fc0] mmco: unref short failure |
|
|
[h264 @ 0x10d43940] mmco: unref short failure |
|
|
[h264 @ 0x8bc3980] mmco: unref short failure |
|
|
[h264 @ 0x8bc3980] mmco: unref short failure |
|
|
[h264 @ 0x90b2bc0] mmco: unref short failure |
|
|
[h264 @ 0x715d0d00] mmco: unref short failure |
|
|
[h264 @ 0x28108040] mmco: unref short failure |
|
|
[h264 @ 0x846fbc0] mmco: unref short failure |
|
|
[h264 @ 0x846fbc0] mmco: unref short failure |
|
|
[h264 @ 0x90b2bc0] mmco: unref short failure |
|
|
[h264 @ 0x90b2bc0] mmco: unref short failure |
|
|
[h264 @ 0x9973540] mmco: unref short failure |
|
|
[h264 @ 0x9973540] mmco: unref short failure |
|
|
[h264 @ 0x715d0d00] mmco: unref short failure |
|
|
[h264 @ 0x715d0d00] mmco: unref short failure |
|
|
[h264 @ 0x82bb480] mmco: unref short failure |
|
|
[h264 @ 0x82bb480] mmco: unref short failure |
|
|
[h264 @ 0x13c79580] mmco: unref short failure |
|
|
[h264 @ 0x13c79580] mmco: unref short failure |
|
|
[h264 @ 0x9518d00] mmco: unref short failure |
|
|
[h264 @ 0x85513c0] mmco: unref short failure |
|
|
[h264 @ 0x85513c0] mmco: unref short failure |
|
|
[h264 @ 0x1029a380] mmco: unref short failure |
|
|
[h264 @ 0x1029a380] mmco: unref short failure |
|
|
[h264 @ 0x20e53000] mmco: unref short failure |
|
|
[h264 @ 0x120ec300] mmco: unref short failure |
|
|
[h264 @ 0x93eb780] mmco: unref short failure |
|
|
[h264 @ 0x93eb780] mmco: unref short failure |
|
|
[h264 @ 0xd3c0080] mmco: unref short failure |
|
|
[h264 @ 0xd3c0080] mmco: unref short failure |
|
|
[h264 @ 0x1029a380] mmco: unref short failure |
|
|
[h264 @ 0x1b4bdc40] mmco: unref short failure |
|
|
[h264 @ 0x1b4bdc40] mmco: unref short failure |
|
|
[h264 @ 0x20e53000] mmco: unref short failure |
|
|
[h264 @ 0x20e53000] mmco: unref short failure |
|
|
[h264 @ 0x1aa11900] mmco: unref short failure |
|
|
[h264 @ 0x1aa11900] mmco: unref short failure |
|
|
[h264 @ 0x8b27a00] mmco: unref short failure |
|
|
[h264 @ 0x8b27a00] mmco: unref short failure |
|
|
[h264 @ 0x47b64100] mmco: unref short failure |
|
|
[h264 @ 0x47b64100] mmco: unref short failure |
|
|
[h264 @ 0x8b27a00] mmco: unref short failure |
|
|
[h264 @ 0x8b27a00] mmco: unref short failure |
|
|
[h264 @ 0xe857000] mmco: unref short failure |
|
|
[h264 @ 0xe857000] mmco: unref short failure |
|
|
[h264 @ 0x838ff40] mmco: unref short failure |
|
|
[h264 @ 0x838ff40] mmco: unref short failure |
|
|
[h264 @ 0x97b04c0] mmco: unref short failure |
|
|
[h264 @ 0x66aeab00] mmco: unref short failure |
|
|
[h264 @ 0x66aeab00] mmco: unref short failure |
|
|
[h264 @ 0xf7cf380] mmco: unref short failure |
|
|
[h264 @ 0xf7cf380] mmco: unref short failure |
|
|
[h264 @ 0xf616140] mmco: unref short failure |
|
|
[h264 @ 0xf616140] mmco: unref short failure |
|
|
[h264 @ 0x41642140] mmco: unref short failure |
|
|
[h264 @ 0x41642140] mmco: unref short failure |
|
|
[h264 @ 0x8654080] mmco: unref short failure |
|
|
[h264 @ 0x8654080] mmco: unref short failure |
|
|
[h264 @ 0x8414080] mmco: unref short failure |
|
|
[h264 @ 0xa2da800] mmco: unref short failure |
|
|
[h264 @ 0x47b64100] mmco: unref short failure |
|
|
[h264 @ 0x47b64100] mmco: unref short failure |
|
|
[h264 @ 0x8b27a00] mmco: unref short failure |
|
|
[h264 @ 0x8b27a00] mmco: unref short failure |
|
|
[h264 @ 0x1aa11900] mmco: unref short failure |
|
|
[h264 @ 0x1aa11900] mmco: unref short failure |
|
|
[h264 @ 0x18542300] mmco: unref short failure |
|
|
[h264 @ 0x18542300] mmco: unref short failure |
|
|
[h264 @ 0x1cac37c0] mmco: unref short failure |
|
|
[h264 @ 0x1cac37c0] mmco: unref short failure |
|
|
[h264 @ 0x551b7980] mmco: unref short failure |
|
|
[h264 @ 0x551b7980] mmco: unref short failure |
|
|
[h264 @ 0x130a5d00] mmco: unref short failure |
|
|
[h264 @ 0x130a5d00] mmco: unref short failure |
|
|
[h264 @ 0x47b64100] mmco: unref short failure |
|
|
[h264 @ 0x1029a380] mmco: unref short failure |
|
|
[h264 @ 0x1029a380] mmco: unref short failure |
|
|
[h264 @ 0x551b7980] mmco: unref short failure |
|
|
[h264 @ 0x9518d00] mmco: unref short failure |
|
|
[h264 @ 0x9518d00] mmco: unref short failure |
|
|
[h264 @ 0x12ff4840] mmco: unref short failure |
|
|
[h264 @ 0x12ff4840] mmco: unref short failure |
|
|
[h264 @ 0x37079f80] mmco: unref short failure |
|
|
[h264 @ 0x37079f80] mmco: unref short failure |
|
|
[h264 @ 0x130a5d00] mmco: unref short failure |
|
|
[h264 @ 0x37079f80] mmco: unref short failure |
|
|
[h264 @ 0x37079f80] mmco: unref short failure |
|
|
You are using a model of type llava_next to instantiate a model of type llava_next_video. This is not supported for all configurations of models and can yield errors. |
|
|
[h264 @ 0x838ff40] mmco: unref short failure |
|
|
[h264 @ 0xe857000] mmco: unref short failure |
|
|
[h264 @ 0x13002b80] mmco: unref short failure |
|
|
[h264 @ 0x13002b80] mmco: unref short failure |
|
|
[h264 @ 0x13c79580] mmco: unref short failure |
|
|
[h264 @ 0x13c79580] mmco: unref short failure |
|
|
Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s][h264 @ 0x150d0a00] mmco: unref short failure |
|
|
[h264 @ 0x1cac37c0] mmco: unref short failure |
|
|
[h264 @ 0x1cac37c0] mmco: unref short failure |
|
|
[h264 @ 0x9518d00] mmco: unref short failure |
|
|
[h264 @ 0x9518d00] mmco: unref short failure |
|
|
[h264 @ 0x21946e00] mmco: unref short failure |
|
|
[h264 @ 0x21946e00] mmco: unref short failure |
|
|
[h264 @ 0x869f680] mmco: unref short failure |
|
|
[h264 @ 0x9518d00] mmco: unref short failure |
|
|
Loading checkpoint shards: 33%|███▎ | 1/3 [00:07<00:15, 7.66s/it][h264 @ 0x20e53000] mmco: unref short failure |
|
|
[h264 @ 0x20e53000] mmco: unref short failure |
|
|
[h264 @ 0x37f53c80] mmco: unref short failure |
|
|
[h264 @ 0x37f53c80] mmco: unref short failure |
|
|
Loading checkpoint shards: 67%|██████▋ | 2/3 [00:12<00:06, 6.27s/it][h264 @ 0x2bd85600] mmco: unref short failure |
|
|
[h264 @ 0x2bd85600] mmco: unref short failure |
|
|
[h264 @ 0x175507c0] mmco: unref short failure |
|
|
[h264 @ 0x175507c0] mmco: unref short failure |
|
|
You are using a model of type llava_next to instantiate a model of type llava_next_video. This is not supported for all configurations of models and can yield errors. |
|
|
You are using a model of type llava_next to instantiate a model of type llava_next_video. This is not supported for all configurations of models and can yield errors. |
|
|
[h264 @ 0x37f53c80] mmco: unref short failure |
|
|
You are using a model of type llava_next to instantiate a model of type llava_next_video. This is not supported for all configurations of models and can yield errors. |
|
|
You are using a model of type llava_next to instantiate a model of type llava_next_video. This is not supported for all configurations of models and can yield errors. |
|
|
[h264 @ 0x2034de00] mmco: unref short failure |
|
|
You are using a model of type llava_next to instantiate a model of type llava_next_video. This is not supported for all configurations of models and can yield errors. |
|
|
Loading checkpoint shards: 100%|██████████| 3/3 [00:17<00:00, 5.46s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:17<00:00, 5.82s/it] |
|
|
Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s]You are using a model of type llava_next to instantiate a model of type llava_next_video. This is not supported for all configurations of models and can yield errors. |
|
|
Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s]Chat templates should be in a 'chat_template.json' file but found key='chat_template' in the processor's config. Make sure to move your template to its own file. |
|
|
Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s]You are using a model of type llava_next to instantiate a model of type llava_next_video. This is not supported for all configurations of models and can yield errors. |
|
|
Loading checkpoint shards: 33%|███▎ | 1/3 [00:09<00:18, 9.25s/it]
Loading checkpoint shards: 33%|███▎ | 1/3 [00:10<00:20, 10.44s/it]Expanding inputs for image/video tokens in LLaVa-NeXT-Video should be done in processing. Please add `patch_size` and `vision_feature_select_strategy` to the model's processing config or set directly with `processor.patch_size = {{patch_size}}` and processor.vision_feature_select_strategy = {{vision_feature_select_strategy}}`. Using processors without these attributes in the config is deprecated and will throw an error in v4.47. |
|
|
Loading checkpoint shards: 33%|███▎ | 1/3 [00:13<00:26, 13.49s/it]
Loading checkpoint shards: 67%|██████▋ | 2/3 [00:16<00:08, 8.11s/it]
Loading checkpoint shards: 67%|██████▋ | 2/3 [00:17<00:08, 8.60s/it]Expanding inputs for image.video tokens in LLaVa-NeXT-Video should be done in processing. Please add `patch_size` and `vision_feature_select_strategy` to the model's processing config or set directly with `processor.patch_size = {{patch_size}}` and processor.vision_feature_select_strategy = {{vision_feature_select_strategy}}`. Using processors without these attributes in the config is deprecated and will throw an error in v4.47. |
|
|
Starting from v4.46, the `logits` model output will have the same type as the model (except at train time, where it will always be FP32) |
|
|
Loading checkpoint shards: 33%|███▎ | 1/3 [00:16<00:32, 16.00s/it]
Loading checkpoint shards: 33%|███▎ | 1/3 [00:16<00:32, 16.23s/it]
Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards: 100%|██████████| 3/3 [00:21<00:00, 6.70s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:21<00:00, 7.20s/it] |
|
|
Loading checkpoint shards: 67%|██████▋ | 2/3 [00:20<00:09, 9.58s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:22<00:00, 7.05s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:22<00:00, 7.66s/it] |
|
|
Loading checkpoint shards: 33%|███▎ | 1/3 [00:16<00:32, 16.40s/it]
Loading checkpoint shards: 67%|██████▋ | 2/3 [00:22<00:10, 10.15s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:25<00:00, 7.43s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:25<00:00, 8.40s/it] |
|
|
Loading checkpoint shards: 67%|██████▋ | 2/3 [00:22<00:10, 10.11s/it]
Loading checkpoint shards: 67%|██████▋ | 2/3 [00:21<00:09, 9.62s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:25<00:00, 7.19s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:25<00:00, 8.58s/it] |
|
|
Loading checkpoint shards: 100%|██████████| 3/3 [00:25<00:00, 7.17s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:25<00:00, 8.58s/it] |
|
|
Loading checkpoint shards: 33%|███▎ | 1/3 [00:10<00:20, 10.48s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:22<00:00, 6.01s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:22<00:00, 7.66s/it] |
|
|
Loading checkpoint shards: 67%|██████▋ | 2/3 [00:11<00:05, 5.14s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:13<00:00, 3.36s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:13<00:00, 4.38s/it] |
|
|
Chat templates should be in a 'chat_template.json' file but found key='chat_template' in the processor's config. Make sure to move your template to its own file. |
|
|
Chat templates should be in a 'chat_template.json' file but found key='chat_template' in the processor's config. Make sure to move your template to its own file. |
|
|
Chat templates should be in a 'chat_template.json' file but found key='chat_template' in the processor's config. Make sure to move your template to its own file. |
|
|
Chat templates should be in a 'chat_template.json' file but found key='chat_template' in the processor's config. Make sure to move your template to its own file. |
|
|
Chat templates should be in a 'chat_template.json' file but found key='chat_template' in the processor's config. Make sure to move your template to its own file. |
|
|
Chat templates should be in a 'chat_template.json' file but found key='chat_template' in the processor's config. Make sure to move your template to its own file. |
|
|
Expanding inputs for image/video tokens in LLaVa-NeXT-Video should be done in processing. Please add `patch_size` and `vision_feature_select_strategy` to the model's processing config or set directly with `processor.patch_size = {{patch_size}}` and processor.vision_feature_select_strategy = {{vision_feature_select_strategy}}`. Using processors without these attributes in the config is deprecated and will throw an error in v4.47. |
|
|
Chat templates should be in a 'chat_template.json' file but found key='chat_template' in the processor's config. Make sure to move your template to its own file. |
|
|
Expanding inputs for image.video tokens in LLaVa-NeXT-Video should be done in processing. Please add `patch_size` and `vision_feature_select_strategy` to the model's processing config or set directly with `processor.patch_size = {{patch_size}}` and processor.vision_feature_select_strategy = {{vision_feature_select_strategy}}`. Using processors without these attributes in the config is deprecated and will throw an error in v4.47. |
|
|
Expanding inputs for image/video tokens in LLaVa-NeXT-Video should be done in processing. Please add `patch_size` and `vision_feature_select_strategy` to the model's processing config or set directly with `processor.patch_size = {{patch_size}}` and processor.vision_feature_select_strategy = {{vision_feature_select_strategy}}`. Using processors without these attributes in the config is deprecated and will throw an error in v4.47. |
|
|
Expanding inputs for image/video tokens in LLaVa-NeXT-Video should be done in processing. Please add `patch_size` and `vision_feature_select_strategy` to the model's processing config or set directly with `processor.patch_size = {{patch_size}}` and processor.vision_feature_select_strategy = {{vision_feature_select_strategy}}`. Using processors without these attributes in the config is deprecated and will throw an error in v4.47. |
|
|
Expanding inputs for image/video tokens in LLaVa-NeXT-Video should be done in processing. Please add `patch_size` and `vision_feature_select_strategy` to the model's processing config or set directly with `processor.patch_size = {{patch_size}}` and processor.vision_feature_select_strategy = {{vision_feature_select_strategy}}`. Using processors without these attributes in the config is deprecated and will throw an error in v4.47. |
|
|
Starting from v4.46, the `logits` model output will have the same type as the model (except at train time, where it will always be FP32) |
|
|
Expanding inputs for image/video tokens in LLaVa-NeXT-Video should be done in processing. Please add `patch_size` and `vision_feature_select_strategy` to the model's processing config or set directly with `processor.patch_size = {{patch_size}}` and processor.vision_feature_select_strategy = {{vision_feature_select_strategy}}`. Using processors without these attributes in the config is deprecated and will throw an error in v4.47. |
|
|
Expanding inputs for image/video tokens in LLaVa-NeXT-Video should be done in processing. Please add `patch_size` and `vision_feature_select_strategy` to the model's processing config or set directly with `processor.patch_size = {{patch_size}}` and processor.vision_feature_select_strategy = {{vision_feature_select_strategy}}`. Using processors without these attributes in the config is deprecated and will throw an error in v4.47. |
|
|
Expanding inputs for image.video tokens in LLaVa-NeXT-Video should be done in processing. Please add `patch_size` and `vision_feature_select_strategy` to the model's processing config or set directly with `processor.patch_size = {{patch_size}}` and processor.vision_feature_select_strategy = {{vision_feature_select_strategy}}`. Using processors without these attributes in the config is deprecated and will throw an error in v4.47. |
|
|
Expanding inputs for image/video tokens in LLaVa-NeXT-Video should be done in processing. Please add `patch_size` and `vision_feature_select_strategy` to the model's processing config or set directly with `processor.patch_size = {{patch_size}}` and processor.vision_feature_select_strategy = {{vision_feature_select_strategy}}`. Using processors without these attributes in the config is deprecated and will throw an error in v4.47. |
|
|
Expanding inputs for image.video tokens in LLaVa-NeXT-Video should be done in processing. Please add `patch_size` and `vision_feature_select_strategy` to the model's processing config or set directly with `processor.patch_size = {{patch_size}}` and processor.vision_feature_select_strategy = {{vision_feature_select_strategy}}`. Using processors without these attributes in the config is deprecated and will throw an error in v4.47. |
|
|
Expanding inputs for image.video tokens in LLaVa-NeXT-Video should be done in processing. Please add `patch_size` and `vision_feature_select_strategy` to the model's processing config or set directly with `processor.patch_size = {{patch_size}}` and processor.vision_feature_select_strategy = {{vision_feature_select_strategy}}`. Using processors without these attributes in the config is deprecated and will throw an error in v4.47. |
|
|
Expanding inputs for image.video tokens in LLaVa-NeXT-Video should be done in processing. Please add `patch_size` and `vision_feature_select_strategy` to the model's processing config or set directly with `processor.patch_size = {{patch_size}}` and processor.vision_feature_select_strategy = {{vision_feature_select_strategy}}`. Using processors without these attributes in the config is deprecated and will throw an error in v4.47. |
|
|
Expanding inputs for image.video tokens in LLaVa-NeXT-Video should be done in processing. Please add `patch_size` and `vision_feature_select_strategy` to the model's processing config or set directly with `processor.patch_size = {{patch_size}}` and processor.vision_feature_select_strategy = {{vision_feature_select_strategy}}`. Using processors without these attributes in the config is deprecated and will throw an error in v4.47. |
|
|
Starting from v4.46, the `logits` model output will have the same type as the model (except at train time, where it will always be FP32) |
|
|
Starting from v4.46, the `logits` model output will have the same type as the model (except at train time, where it will always be FP32) |
|
|
Expanding inputs for image.video tokens in LLaVa-NeXT-Video should be done in processing. Please add `patch_size` and `vision_feature_select_strategy` to the model's processing config or set directly with `processor.patch_size = {{patch_size}}` and processor.vision_feature_select_strategy = {{vision_feature_select_strategy}}`. Using processors without these attributes in the config is deprecated and will throw an error in v4.47. |
|
|
Starting from v4.46, the `logits` model output will have the same type as the model (except at train time, where it will always be FP32) |
|
|
Starting from v4.46, the `logits` model output will have the same type as the model (except at train time, where it will always be FP32) |
|
|
Starting from v4.46, the `logits` model output will have the same type as the model (except at train time, where it will always be FP32) |
|
|
Starting from v4.46, the `logits` model output will have the same type as the model (except at train time, where it will always be FP32) |
|
|
|
