Upload folder using huggingface_hub

.job_config.json

@@ -0,0 +1,152 @@
+{
+  "job": "extension",
+  "config": {
+    "name": "Xiang_wan_2_2_lora",
+    "process": [
+      {
+        "type": "ui_trainer",
+        "training_folder": "/home/featurize/ai-toolkit/output",
+        "sqlite_db_path": "/home/featurize/ai-toolkit/aitk_db.db",
+        "device": "cuda",
+        "trigger_word": null,
+        "performance_log_every": 10,
+        "network": {
+          "type": "lora",
+          "linear": 32,
+          "linear_alpha": 32,
+          "conv": 16,
+          "conv_alpha": 16,
+          "lokr_full_rank": true,
+          "lokr_factor": -1,
+          "network_kwargs": {
+            "ignore_if_contains": []
+          }
+        },
+        "save": {
+          "dtype": "bf16",
+          "save_every": 250,
+          "max_step_saves_to_keep": 4000,
+          "save_format": "diffusers",
+          "push_to_hub": false
+        },
+        "datasets": [
+          {
+            "folder_path": "/home/featurize/ai-toolkit/datasets/Xiang_Handsome_Flux_SRPO_Keye_Captioned",
+            "control_path": null,
+            "mask_path": null,
+            "mask_min_value": 0.1,
+            "default_caption": "",
+            "caption_ext": "txt",
+            "caption_dropout_rate": 0.05,
+            "cache_latents_to_disk": false,
+            "is_reg": false,
+            "network_weight": 1,
+            "resolution": [
+              512,
+              768
+            ],
+            "controls": [],
+            "shrink_video_to_frames": true,
+            "num_frames": 1,
+            "do_i2v": true,
+            "flip_x": false,
+            "flip_y": false
+          }
+        ],
+        "train": {
+          "batch_size": 1,
+          "bypass_guidance_embedding": false,
+          "steps": 30000,
+          "gradient_accumulation": 1,
+          "train_unet": true,
+          "train_text_encoder": false,
+          "gradient_checkpointing": true,
+          "noise_scheduler": "flowmatch",
+          "optimizer": "adamw8bit",
+          "timestep_type": "linear",
+          "content_or_style": "balanced",
+          "optimizer_params": {
+            "weight_decay": 0.0001
+          },
+          "unload_text_encoder": false,
+          "cache_text_embeddings": true,
+          "lr": 0.0001,
+          "ema_config": {
+            "use_ema": false,
+            "ema_decay": 0.99
+          },
+          "skip_first_sample": true,
+          "force_first_sample": false,
+          "disable_sampling": true,
+          "dtype": "bf16",
+          "diff_output_preservation": false,
+          "diff_output_preservation_multiplier": 1,
+          "diff_output_preservation_class": "person",
+          "switch_boundary_every": 1
+        },
+        "model": {
+          "name_or_path": "/home/featurize/ai-toolkit/Wan2.2-T2V-A14B-Diffusers-bf16",
+          "quantize": true,
+          "qtype": "uint4|ostris/accuracy_recovery_adapters/wan22_14b_t2i_torchao_uint4.safetensors",
+          "quantize_te": true,
+          "qtype_te": "qfloat8",
+          "arch": "wan22_14b:t2v",
+          "low_vram": true,
+          "model_kwargs": {
+            "train_high_noise": true,
+            "train_low_noise": true
+          }
+        },
+        "sample": {
+          "sampler": "flowmatch",
+          "sample_every": 250,
+          "width": 1024,
+          "height": 1024,
+          "samples": [
+            {
+              "prompt": "woman with red hair, playing chess at the park, bomb going off in the background"
+            },
+            {
+              "prompt": "a woman holding a coffee cup, in a beanie, sitting at a cafe"
+            },
+            {
+              "prompt": "a horse is a DJ at a night club, fish eye lens, smoke machine, lazer lights, holding a martini"
+            },
+            {
+              "prompt": "a man showing off his cool new t shirt at the beach, a shark is jumping out of the water in the background"
+            },
+            {
+              "prompt": "a bear building a log cabin in the snow covered mountains"
+            },
+            {
+              "prompt": "woman playing the guitar, on stage, singing a song, laser lights, punk rocker"
+            },
+            {
+              "prompt": "hipster man with a beard, building a chair, in a wood shop"
+            },
+            {
+              "prompt": "photo of a man, white background, medium shot, modeling clothing, studio lighting, white backdrop"
+            },
+            {
+              "prompt": "a man holding a sign that says, 'this is a sign'"
+            },
+            {
+              "prompt": "a bulldog, in a post apocalyptic world, with a shotgun, in a leather jacket, in a desert, with a motorcycle"
+            }
+          ],
+          "neg": "",
+          "seed": 42,
+          "walk_seed": true,
+          "guidance_scale": 4,
+          "sample_steps": 25,
+          "num_frames": 41,
+          "fps": 16
+        }
+      }
+    ]
+  },
+  "meta": {
+    "name": "[name]",
+    "version": "1.0"
+  }
+}

Xiang_wan_2_2_lora_000000250_high_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de9fbe1802c300b04ef3a6c8ecfce26bcb5e267e15717bcdd84b0c018b23dcc1
+size 306808376

Xiang_wan_2_2_lora_000000250_low_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b013a468d95a58ca7865248d25ec36b33d5c827484216da6ccbf1a96a68ae39
+size 306808376

Xiang_wan_2_2_lora_000000500_high_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbc456c37204c3b36b1633cdb1c8701aefb879241086e658b55226bbbf918eb3
+size 306808376

Xiang_wan_2_2_lora_000000500_low_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daded9ed7d3f44ddabfda621045f2bf8752ab7c5bd66fb6be90f8faf106e232d
+size 306808376

Xiang_wan_2_2_lora_000000750_high_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cc0b2f106f1982941a78245c263d6390426722185ec31109a333de0b5b388b3
+size 306808376

Xiang_wan_2_2_lora_000000750_low_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8616262843f4b5f7fe3897ac8aabbedffaf8290c80aaf648ada9bf5b54367631
+size 306808376

Xiang_wan_2_2_lora_000001000_high_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c0b139cdaf864e3400fefbd732dd294ec156038c86d9b1410ef524dfa5f23c4
+size 306808376

Xiang_wan_2_2_lora_000001000_low_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15127f928c8b773b8ea1d6c89997aeb1ad4a31d9106d4120433246ccb9e03499
+size 306808376

Xiang_wan_2_2_lora_000001250_high_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:793b809be5c44dabbe1115db8c34dd7cdace07f202263d6edaed54bdb25c9c21
+size 306808376

Xiang_wan_2_2_lora_000001250_low_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb3fd5dcc3ce08d8420959c8e47d0dd226fb7ff96aa5764fdc4e1870f62f5802
+size 306808376

Xiang_wan_2_2_lora_000001500_high_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5197a9dd0fc9b50f8360894147167162acc871bc66f1ea9503971dd72f219513
+size 306808376

Xiang_wan_2_2_lora_000001500_low_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e148a2047c488ae24fc83f300f018e81f5f4b967cadb3e20ad2fbd7e6d4af324
+size 306808376

Xiang_wan_2_2_lora_000001750_high_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3fa4aa2b448bdf0aa4d92e1ff632d705695b2c09903a2a77dc8829c48316aca
+size 306808376

Xiang_wan_2_2_lora_000001750_low_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d5f23edbc782984fd5d82d81931a10ce50b67e6c51a9c78f013ac09c67a03b9
+size 306808376

Xiang_wan_2_2_lora_000002000_high_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd46313e292d833c31c5d8f92e2dc34d64ede68eaa44bef5f1a46eb0fe38005b
+size 306808376

Xiang_wan_2_2_lora_000002000_low_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f1835761a4c2796093a0d32f78b2e6269472a9d58708ec37c0ee11088cd415a
+size 306808376

Xiang_wan_2_2_lora_000002250_high_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3edfaedcd963ea3d43eb91e0ea02a3383319b44b27c6170408dacae4f66c2bfb
+size 306808376

Xiang_wan_2_2_lora_000002250_low_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:976001a470a1d8f4452118e24cb349954d2ab018e5ac6b72c97271b1f1287a44
+size 306808376

Xiang_wan_2_2_lora_000002500_high_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e8566f8b1adab4d3ba876494961fba744ecd4beece065d5db7e8454b1797fbb
+size 306808376

Xiang_wan_2_2_lora_000002500_low_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:152c2f291a3e9c4cd2fee05c12593094a4d967d02c4bc86f70c64516de71d7b8
+size 306808376

Xiang_wan_2_2_lora_000002750_high_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b21a51795b81d9f8bc0df9a72f2e3cf1fb68f8b755d2796f747c0e552c43b36
+size 306808376

Xiang_wan_2_2_lora_000002750_low_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e1e73612ef56af5782fb6efb08a9bddc3d3cd1692e40966aec76b56d38fd09a
+size 306808376

Xiang_wan_2_2_lora_000003000_high_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d780cd0107b1b3ddf07babe1c5749a14bac8929ba93b95fb02c3295d14657b9e
+size 306808376

Xiang_wan_2_2_lora_000003000_low_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69af0fce3f269d17b9cf6ee1a58cf823cb3c6a77378a7ceed13de70b45d598ee
+size 306808376

Xiang_wan_2_2_lora_000003250_high_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e85f9e5c4c814ac98b8622f0b2ff0bc5e3e70901446cb4a7461498914f7d02f4
+size 306808376

Xiang_wan_2_2_lora_000003250_low_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e34f1b7c3ad62ce939378131b3e50c4e63159b6a106ccb8bfe7666612a56f320
+size 306808376

Xiang_wan_2_2_lora_000003500_high_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0209d0d9aa302a64b476ab73d0f4bdc8ddad28f87849123bba6253cc42d8cce
+size 306808376

Xiang_wan_2_2_lora_000003500_low_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49aa0d2392cc88dec9b983e6b19569a62abbcfd92c487e4f82bfd91874ab1765
+size 306808376

Xiang_wan_2_2_lora_000003750_high_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13932d97075265fd4c042c361a882d7589f331cde7528b071c0f48f04dd6dd5b
+size 306808376

Xiang_wan_2_2_lora_000003750_low_noise.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7cefa112c15845f0bbb6be7309e3912a31d9cb124b411874e23a44dd4f0e404
+size 306808376

config.yaml

@@ -0,0 +1,117 @@
+job: extension
+config:
+  name: Xiang_wan_2_2_lora
+  process:
+  - type: ui_trainer
+    training_folder: /home/featurize/ai-toolkit/output
+    sqlite_db_path: /home/featurize/ai-toolkit/aitk_db.db
+    device: cuda
+    trigger_word: null
+    performance_log_every: 10
+    network:
+      type: lora
+      linear: 32
+      linear_alpha: 32
+      conv: 16
+      conv_alpha: 16
+      lokr_full_rank: true
+      lokr_factor: -1
+      network_kwargs:
+        ignore_if_contains: []
+    save:
+      dtype: bf16
+      save_every: 250
+      max_step_saves_to_keep: 4000
+      save_format: diffusers
+      push_to_hub: false
+    datasets:
+    - folder_path: /home/featurize/ai-toolkit/datasets/Xiang_Handsome_Flux_SRPO_Keye_Captioned
+      control_path: null
+      mask_path: null
+      mask_min_value: 0.1
+      default_caption: ''
+      caption_ext: txt
+      caption_dropout_rate: 0.05
+      cache_latents_to_disk: false
+      is_reg: false
+      network_weight: 1
+      resolution:
+      - 512
+      - 768
+      controls: []
+      shrink_video_to_frames: true
+      num_frames: 1
+      do_i2v: true
+      flip_x: false
+      flip_y: false
+    train:
+      batch_size: 1
+      bypass_guidance_embedding: false
+      steps: 30000
+      gradient_accumulation: 1
+      train_unet: true
+      train_text_encoder: false
+      gradient_checkpointing: true
+      noise_scheduler: flowmatch
+      optimizer: adamw8bit
+      timestep_type: linear
+      content_or_style: balanced
+      optimizer_params:
+        weight_decay: 0.0001
+      unload_text_encoder: false
+      cache_text_embeddings: true
+      lr: 0.0001
+      ema_config:
+        use_ema: false
+        ema_decay: 0.99
+      skip_first_sample: true
+      force_first_sample: false
+      disable_sampling: true
+      dtype: bf16
+      diff_output_preservation: false
+      diff_output_preservation_multiplier: 1
+      diff_output_preservation_class: person
+      switch_boundary_every: 1
+    model:
+      name_or_path: /home/featurize/ai-toolkit/Wan2.2-T2V-A14B-Diffusers-bf16
+      quantize: true
+      qtype: uint4|ostris/accuracy_recovery_adapters/wan22_14b_t2i_torchao_uint4.safetensors
+      quantize_te: true
+      qtype_te: qfloat8
+      arch: wan22_14b:t2v
+      low_vram: true
+      model_kwargs:
+        train_high_noise: true
+        train_low_noise: true
+    sample:
+      sampler: flowmatch
+      sample_every: 250
+      width: 1024
+      height: 1024
+      samples:
+      - prompt: woman with red hair, playing chess at the park, bomb going off in
+          the background
+      - prompt: a woman holding a coffee cup, in a beanie, sitting at a cafe
+      - prompt: a horse is a DJ at a night club, fish eye lens, smoke machine, lazer
+          lights, holding a martini
+      - prompt: a man showing off his cool new t shirt at the beach, a shark is jumping
+          out of the water in the background
+      - prompt: a bear building a log cabin in the snow covered mountains
+      - prompt: woman playing the guitar, on stage, singing a song, laser lights,
+          punk rocker
+      - prompt: hipster man with a beard, building a chair, in a wood shop
+      - prompt: photo of a man, white background, medium shot, modeling clothing,
+          studio lighting, white backdrop
+      - prompt: a man holding a sign that says, 'this is a sign'
+      - prompt: a bulldog, in a post apocalyptic world, with a shotgun, in a leather
+          jacket, in a desert, with a motorcycle
+      neg: ''
+      seed: 42
+      walk_seed: true
+      guidance_scale: 4
+      sample_steps: 25
+      num_frames: 41
+      fps: 16
+meta:
+  name: Xiang_wan_2_2_lora
+  version: '1.0'

logs/0_log.txt

@@ -0,0 +1,103 @@
+Running 1 job
+Error running job: /environment/miniconda3/lib/python3.11/site-packages/flash_attn_2_cuda.cpython-311-x86_64-linux-gnu.so: undefined symbol: _ZN3c104cuda9SetDeviceEab
+Error running on_error: cannot access local variable 'job' where it is not associated with a value
+
+========================================
+Result:
+ - 0 completed jobs
+ - 1 failure
+========================================
+Traceback (most recent call last):
+Traceback (most recent call last):
+  File "/home/featurize/ai-toolkit/run.py", line 120, in <module>
+  File "/home/featurize/ai-toolkit/run.py", line 120, in <module>
+        main()main()
+
+  File "/home/featurize/ai-toolkit/run.py", line 108, in main
+  File "/home/featurize/ai-toolkit/run.py", line 108, in main
+        raise eraise e
+
+  File "/home/featurize/ai-toolkit/run.py", line 95, in main
+  File "/home/featurize/ai-toolkit/run.py", line 95, in main
+        job = get_job(config_file, args.name)job = get_job(config_file, args.name)
+
+                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+  File "/home/featurize/ai-toolkit/toolkit/job.py", line 28, in get_job
+  File "/home/featurize/ai-toolkit/toolkit/job.py", line 28, in get_job
+        from jobs import ExtensionJobfrom jobs import ExtensionJob
+
+  File "/home/featurize/ai-toolkit/jobs/__init__.py", line 1, in <module>
+  File "/home/featurize/ai-toolkit/jobs/__init__.py", line 1, in <module>
+        from .BaseJob import BaseJobfrom .BaseJob import BaseJob
+
+  File "/home/featurize/ai-toolkit/jobs/BaseJob.py", line 5, in <module>
+  File "/home/featurize/ai-toolkit/jobs/BaseJob.py", line 5, in <module>
+        from jobs.process import BaseProcessfrom jobs.process import BaseProcess
+
+  File "/home/featurize/ai-toolkit/jobs/process/__init__.py", line 1, in <module>
+  File "/home/featurize/ai-toolkit/jobs/process/__init__.py", line 1, in <module>
+        from .BaseExtractProcess import BaseExtractProcessfrom .BaseExtractProcess import BaseExtractProcess
+
+  File "/home/featurize/ai-toolkit/jobs/process/BaseExtractProcess.py", line 7, in <module>
+  File "/home/featurize/ai-toolkit/jobs/process/BaseExtractProcess.py", line 7, in <module>
+        from toolkit.metadata import get_meta_for_safetensorsfrom toolkit.metadata import get_meta_for_safetensors
+
+  File "/home/featurize/ai-toolkit/toolkit/metadata.py", line 9, in <module>
+  File "/home/featurize/ai-toolkit/toolkit/metadata.py", line 9, in <module>
+        from toolkit.train_tools import addnet_hash_legacyfrom toolkit.train_tools import addnet_hash_legacy
+
+  File "/home/featurize/ai-toolkit/toolkit/train_tools.py", line 25, in <module>
+  File "/home/featurize/ai-toolkit/toolkit/train_tools.py", line 25, in <module>
+        from transformers import T5Tokenizer, T5EncoderModel, UMT5EncoderModelfrom transformers import T5Tokenizer, T5EncoderModel, UMT5EncoderModel
+
+  File "/environment/miniconda3/lib/python3.11/site-packages/transformers/utils/import_utils.py", line 2045, in __getattr__
+  File "/environment/miniconda3/lib/python3.11/site-packages/transformers/utils/import_utils.py", line 2045, in __getattr__
+        module = self._get_module(self._class_to_module[name])module = self._get_module(self._class_to_module[name])
+
+                          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+  File "/environment/miniconda3/lib/python3.11/site-packages/transformers/utils/import_utils.py", line 2075, in _get_module
+  File "/environment/miniconda3/lib/python3.11/site-packages/transformers/utils/import_utils.py", line 2075, in _get_module
+        raise eraise e
+
+  File "/environment/miniconda3/lib/python3.11/site-packages/transformers/utils/import_utils.py", line 2073, in _get_module
+  File "/environment/miniconda3/lib/python3.11/site-packages/transformers/utils/import_utils.py", line 2073, in _get_module
+        return importlib.import_module("." + module_name, self.__name__)return importlib.import_module("." + module_name, self.__name__)
+
+                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+  File "/environment/miniconda3/lib/python3.11/importlib/__init__.py", line 126, in import_module
+  File "/environment/miniconda3/lib/python3.11/importlib/__init__.py", line 126, in import_module
+        return _bootstrap._gcd_import(name[level:], package, level)return _bootstrap._gcd_import(name[level:], package, level)
+
+                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+  File "/environment/miniconda3/lib/python3.11/site-packages/transformers/models/t5/modeling_t5.py", line 40, in <module>
+  File "/environment/miniconda3/lib/python3.11/site-packages/transformers/models/t5/modeling_t5.py", line 40, in <module>
+        from ...modeling_utils import PreTrainedModelfrom ...modeling_utils import PreTrainedModel
+
+  File "/environment/miniconda3/lib/python3.11/site-packages/transformers/modeling_utils.py", line 61, in <module>
+  File "/environment/miniconda3/lib/python3.11/site-packages/transformers/modeling_utils.py", line 61, in <module>
+        from .integrations.flash_attention import flash_attention_forwardfrom .integrations.flash_attention import flash_attention_forward
+
+  File "/environment/miniconda3/lib/python3.11/site-packages/transformers/integrations/flash_attention.py", line 5, in <module>
+  File "/environment/miniconda3/lib/python3.11/site-packages/transformers/integrations/flash_attention.py", line 5, in <module>
+        from ..modeling_flash_attention_utils import _flash_attention_forward, flash_attn_supports_top_left_maskfrom ..modeling_flash_attention_utils import _flash_attention_forward, flash_attn_supports_top_left_mask
+
+  File "/environment/miniconda3/lib/python3.11/site-packages/transformers/modeling_flash_attention_utils.py", line 36, in <module>
+  File "/environment/miniconda3/lib/python3.11/site-packages/transformers/modeling_flash_attention_utils.py", line 36, in <module>
+        from flash_attn.bert_padding import index_first_axis, pad_input, unpad_input  # noqafrom flash_attn.bert_padding import index_first_axis, pad_input, unpad_input  # noqa
+
+        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+  File "/environment/miniconda3/lib/python3.11/site-packages/flash_attn/__init__.py", line 3, in <module>
+  File "/environment/miniconda3/lib/python3.11/site-packages/flash_attn/__init__.py", line 3, in <module>
+        from flash_attn.flash_attn_interface import (from flash_attn.flash_attn_interface import (
+
+  File "/environment/miniconda3/lib/python3.11/site-packages/flash_attn/flash_attn_interface.py", line 15, in <module>
+  File "/environment/miniconda3/lib/python3.11/site-packages/flash_attn/flash_attn_interface.py", line 15, in <module>
+        import flash_attn_2_cuda as flash_attn_gpuimport flash_attn_2_cuda as flash_attn_gpu
+
+ImportErrorImportError: : /environment/miniconda3/lib/python3.11/site-packages/flash_attn_2_cuda.cpython-311-x86_64-linux-gnu.so: undefined symbol: _ZN3c104cuda9SetDeviceEab/environment/miniconda3/lib/python3.11/site-packages/flash_attn_2_cuda.cpython-311-x86_64-linux-gnu.so: undefined symbol: _ZN3c104cuda9SetDeviceEab
+

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1018e7a50001489d791c5df1b08ff97f47207af9fe1b492247dca56333bcd02e
+size 624884069