init repo

.gitattributes

@@ -0,0 +1,34 @@
+rrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,3 @@
+wandb/
+script.sh
+environ.txt

arguments.yaml

@@ -0,0 +1,49 @@
+data_cfgs:
+  eval_data_files: null
+  eval_datasets: null
+  eval_optional_args: []
+  eval_size: null
+  eval_split: null
+  eval_subset: null
+  eval_template: null
+  train_data_files: 8713_tokenized_v2.pt
+  train_datasets: /aifs4su/yaodong/datasets/llava_annotated
+  train_optional_args: []
+  train_size: null
+  train_split: train
+  train_subset: null
+  train_template: ANYTHING_TI2TI
+logger_cfgs:
+  cache_dir: null
+  log_project: align-anything
+  log_run_name: sft
+  log_type: wandb
+  output_dir: ../outputs/sft_chameleon_0727_0802_v2.1_1e-4_6ep
+  save_interval: 500.0
+model_cfgs:
+  model_max_length: 4096
+  model_name_or_path: ../outputs/sft_chameleon_0727_0802_v2.1_1e-4
+  trust_remote_code: true
+special_tokens: null
+train_cfgs:
+  adam_betas:
+  - 0.9
+  - 0.95
+  adam_epsilon: 1.0e-08
+  bf16: true
+  ds_cfgs: ds_z3_config.json
+  epochs: 3
+  eval_interval: 1000
+  eval_strategy: steps
+  fp16: false
+  freeze_language_model: false
+  gradient_accumulation_steps: 2.0
+  gradient_checkpointing: true
+  learning_rate: 0.0001
+  lr_scheduler_type: cosine
+  lr_warmup_ratio: 0.03
+  max_grad_norm: 1.0
+  per_device_eval_batch_size: 2.0
+  per_device_train_batch_size: 2.0
+  seed: 42
+  weight_decay: 0.0

preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 512,
+    "width": 512
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    1.0,
+    1.0,
+    1.0
+  ],
+  "image_processor_type": "ChameleonImageProcessor",
+  "image_std": [
+    1.0,
+    1.0,
+    1.0
+  ],
+  "processor_class": "ChameleonProcessor",
+  "resample": 1,
+  "rescale_factor": 0.0078,
+  "size": {
+    "shortest_edge": 512
+  }
+}

processor_config.json

@@ -0,0 +1,5 @@
+{
+  "image_seq_length": 1024,
+  "image_token": "<image>",
+  "processor_class": "ChameleonProcessor"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de106848c5751c5bc497c40b05e340396da5f99b785e6f852e241a056eaafb01
+size 14165009930

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "<reserved08706>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}