UniX

config.json

@@ -0,0 +1,66 @@
+{
+  "aligner_config": {
+    "cls": "MlpProjector",
+    "model_type": "aligner",
+    "params": {
+      "depth": 2,
+      "input_dim": 1024,
+      "n_embed": 2048,
+      "projector_type": "mlp_gelu"
+    }
+  },
+  "architectures": [
+    "MultiModalityCausalLM"
+  ],
+  "gen_aligner_config": {
+    "cls": "MlpProjector",
+    "model_type": "gen_aligner",
+    "params": {
+      "depth": 2,
+      "input_dim": 8,
+      "n_embed": 2048,
+      "projector_type": "mlp_gelu"
+    }
+  },
+  "gen_head_config": {
+    "cls": "vision_head",
+    "model_type": "gen_head",
+    "params": {
+      "image_token_embed": 2048,
+      "image_token_size": 16384,
+      "n_embed": 2048
+    }
+  },
+  "gen_vision_config": {
+    "cls": "VQ-16",
+    "model_type": "gen_vision",
+    "params": {
+      "image_token_size": 16384,
+      "n_embed": 8
+    }
+  },
+  "language_config": {
+    "hidden_size": 2048,
+    "intermediate_size": 5632,
+    "max_position_embeddings": 16384,
+    "model_type": "llama",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 16,
+    "torch_dtype": "bfloat16",
+    "vocab_size": 102400
+  },
+  "model_type": "multi_modality",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.33.1",
+  "vision_config": {
+    "cls": "CLIPVisionTower",
+    "model_type": "vision",
+    "params": {
+      "image_size": 384,
+      "model_name": "siglip_large_patch16_384",
+      "select_feature": "same",
+      "select_layer": -1
+    }
+  }
+}

preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "background_color": [
+    127,
+    127,
+    127
+  ],
+  "do_normalize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "VLMImageProcessor",
+  "image_size": 384,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "min_size": 14,
+  "processor_class": "VLChatProcessor",
+  "rescale_factor": 0.00392156862745098
+}

processor_config.json

@@ -0,0 +1,9 @@
+{
+  "add_special_token": false,
+  "ignore_id": -100,
+  "image_tag": "<image_placeholder>",
+  "mask_prompt": true,
+  "num_image_tokens": 576,
+  "processor_class": "VLChatProcessor",
+  "sft_format": "deepseek"
+}

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "additional_special_tokens": [
+    "<image_placeholder>",
+    "<patch_placeholder>",
+    "<|ref|>",
+    "<|/ref|>",
+    "<|det|>",
+    "<|/det|>",
+    "<|grounding|>",
+    "<|User|>",
+    "<|Assistant|>"
+  ],
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "pad_token": "<｜▁pad▁｜>"
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "model_max_length": 16384,
+  "pad_token": null,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": true
+}

vae/config.yaml

@@ -0,0 +1,44 @@
+model:
+  base_learning_rate: 4.5e-06
+  target: ldm.models.autoencoder.AutoencoderKL
+  params:
+    monitor: val/rec_loss
+    embed_dim: 16
+    lossconfig:
+      target: ldm.modules.losses.LPIPSWithDiscriminator
+      params:
+        disc_start: 50001
+        kl_weight: 1.0e-06
+        disc_weight: 0.5
+    ddconfig:
+      double_z: true
+      z_channels: 16
+      resolution: 256
+      in_channels: 3
+      out_ch: 3
+      ch: 128
+      ch_mult:
+      - 1
+      - 1
+      - 2
+      - 2
+      - 4
+      num_res_blocks: 2
+      attn_resolutions:
+      - 16
+      dropout: 0.0
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 6
+    wrap: true
+    train:
+      target: ldm.data.openimages.FullOpenImagesTrain
+      params:
+        size: 384
+        crop_size: 256
+    validation:
+      target: ldm.data.openimages.FullOpenImagesValidation
+      params:
+        size: 384
+        crop_size: 256

vae/kl-f16d16.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:800019757fb0942448c7bcc955cb60744a349cdc986e0879564b0a1fbe65f835
+size 927775203