Upload config

config.json

@@ -0,0 +1,164 @@
+{
+  "arch_specifier": "no-align+gelu-mlp",
+  "architectures": [
+    "OpenVLAForActionPrediction"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_prismatic.OpenVLAConfig"
+  },
+  "hf_llm_id": "lmsys/vicuna-7b-v1.5",
+  "image_resize_strategy": "letterbox",
+  "image_sizes": [
+    224
+  ],
+  "llm_backbone_id": "vicuna-v15-7b",
+  "llm_max_length": 2048,
+  "model_type": "openvla",
+  "n_action_bins": 256,
+  "norm_stats": {
+    "bridge_orig": {
+      "action": {
+        "mask": [
+          true,
+          true,
+          true,
+          true,
+          true,
+          true,
+          false
+        ],
+        "max": [
+          0.41691166162490845,
+          0.25864794850349426,
+          0.21218234300613403,
+          3.122201919555664,
+          1.8618112802505493,
+          6.280478477478027,
+          1.0
+        ],
+        "mean": [
+          0.00023341893393080682,
+          0.0001300494186580181,
+          -0.0001276240509469062,
+          -0.00015565630747005343,
+          -0.0004039352061226964,
+          0.00023557755048386753,
+          0.5764579772949219
+        ],
+        "min": [
+          -0.4007510244846344,
+          -0.13874775171279907,
+          -0.22553899884223938,
+          -3.2010786533355713,
+          -1.8618112802505493,
+          -6.279075622558594,
+          0.0
+        ],
+        "q01": [
+          -0.02872725307941437,
+          -0.04170349963009357,
+          -0.026093858778476715,
+          -0.08092105075716972,
+          -0.09288699507713317,
+          -0.20718276381492615,
+          0.0
+        ],
+        "q99": [
+          0.028309678435325586,
+          0.040855254605412394,
+          0.040161586627364146,
+          0.08192047759890528,
+          0.07792850524187081,
+          0.20382574498653397,
+          1.0
+        ],
+        "std": [
+          0.009765958413481712,
+          0.01368918176740408,
+          0.012667348608374596,
+          0.02853415347635746,
+          0.03063797391951084,
+          0.07691441476345062,
+          0.4973689615726471
+        ]
+      },
+      "num_trajectories": 60064,
+      "num_transitions": 2135463,
+      "proprio": {
+        "max": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "mean": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "min": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "q01": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "q99": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ],
+        "std": [
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0,
+          0.0
+        ]
+      }
+    }
+  },
+  "output_projector_states": false,
+  "pad_to_multiple_of": 64,
+  "pad_token_id": 32000,
+  "text_config": {
+    "model_type": "llama",
+    "pad_token_id": 32000,
+    "torch_dtype": "bfloat16",
+    "vocab_size": 32064
+  },
+  "timm_model_ids": [
+    "vit_so400m_patch14_siglip_224"
+  ],
+  "timm_override_act_layers": [
+    null
+  ],
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.1",
+  "use_fused_vision_backbone": false,
+  "vision_backbone_id": "siglip-vit-so400m"
+}

configuration_prismatic.py

@@ -0,0 +1,140 @@
+"""
+configuration_prismatic.py
+
+HuggingFace-style configuration definition for Prismatic VLMs, inheriting from `transformers.PretrainedConfig`.
+Default configuration specifies `siglip-224px+7b`.
+"""
+
+from typing import Any, Dict, List, Optional
+
+from transformers import PretrainedConfig
+from transformers.models.auto import CONFIG_MAPPING
+
+# === Utilities for Mapping Prismatic names to HF names ===
+# fmt: off
+VISION_BACKBONE_TO_RESOLUTION: Dict[str, List[int]] = {
+    "clip-vit-l": [224], "siglip-vit-so400m": [224], "dinov2-vit-l": [224], "in1k-vit-l": [224],
+
+    "clip-vit-l-336px": [336],
+    "siglip-vit-so400m-384px": [384],
+
+    "dinoclip-vit-l-336px": [336, 336],
+    "dinosiglip-vit-so-224px": [224, 224],
+    "dinosiglip-vit-so-384px": [384, 384],
+}
+VISION_BACKBONE_TO_TIMM_ID: Dict[str, List[str]] = {
+    "clip-vit-l": ["vit_large_patch14_clip_224.openai"],
+    "clip-vit-l-336px": ["vit_large_patch14_clip_336.openai"],
+
+    "dinov2-vit-l": ["vit_large_patch14_reg4_dinov2.lvd142m"],
+    "in1k-vit-l": ["vit_large_patch16_224.augreg_in21k_ft_in1k"],
+
+    "siglip-vit-so400m": ["vit_so400m_patch14_siglip_224"],
+    "siglip-vit-so400m-384px": ["vit_so400m_patch14_siglip_384"],
+
+    "dinoclip-vit-l-336px": ["vit_large_patch14_reg4_dinov2.lvd142m", "vit_large_patch14_clip_336.openai"],
+    "dinosiglip-vit-so-224px": ["vit_large_patch14_reg4_dinov2.lvd142m", "vit_so400m_patch14_siglip_224"],
+    "dinosiglip-vit-so-384px": ["vit_large_patch14_reg4_dinov2.lvd142m", "vit_so400m_patch14_siglip_384"],
+}
+TIMM_OVERRIDE_ACT_LAYER: Dict[str, List[Optional[str]]] = {
+    "clip-vit-l": ["quick_gelu"], "clip-vit-l-336px": ["quick_gelu"],
+    "dinov2-vit-l": [None], "in1k-vit-l": [None],
+    "siglip-vit-so400m": [None], "siglip-vit-so400m-384px": [None],
+    "dinoclip-vit-l-336px": [None, "quick_gelu"],
+    "dinosiglip-vit-so-224px": [None, None], "dinosiglip-vit-so-384px": [None, None]
+}
+
+LLM_BACKBONE_TO_HF_PATH = {
+    "llama2-7b-pure": "meta-llama/Llama-2-7b-hf", "llama2-13b-pure": "meta-llama/Llama-2-13b-hf",
+    "llama2-7b-chat": "meta-llama/Llama-2-7b-chat-hf", "llama2-13b-chat": "meta-llama/Llama-2-13b-chat-hf",
+
+    "vicuna-v15-7b": "lmsys/vicuna-7b-v1.5", "vicuna-v15-13b": "lmsys/vicuna-13b-v1.5",
+
+    "mistral-v0.1-7b-pure": "mistralai/Mistral-7B-v0.1",
+    "mistral-v0.1-7b-instruct": "mistralai/Mistral-7B-Instruct-v0.1",
+
+    "phi-2-3b": "microsoft/phi-2",
+}
+LLM_BACKBONE_TO_HF_METACLASS = {
+    "llama2-7b-pure": "llama", "llama2-13b-pure": "llama", "llama2-7b-chat": "llama", "llama2-13b-chat": "llama",
+    "vicuna-v15-7b": "llama", "vicuna-v15-13b": "llama",
+
+    "mistral-v0.1-7b-pure": "mistral", "mistral-v0.1-7b-instruct": "mistral",
+
+    "phi-2-3b": "phi",
+}
+
+VALID_VISION_BACKBONES = set(VISION_BACKBONE_TO_RESOLUTION.keys())
+VALID_LLM_BACKBONES = set(LLM_BACKBONE_TO_HF_PATH)
+# fmt: on
+
+
+class PrismaticConfig(PretrainedConfig):
+    model_type: str = "prismatic"
+    is_composition: bool = False
+
+    def __init__(
+        self,
+        vision_backbone_id: str = "siglip-vit-so400m",
+        llm_backbone_id: str = "vicuna-v15-7b",
+        arch_specifier: str = "no-align+gelu-mlp",
+        use_fused_vision_backbone: Optional[bool] = None,
+        image_resize_strategy: str = "letterbox",
+        text_config: Optional[Dict[str, Any]] = None,
+        llm_max_length: int = 2048,
+        pad_token_id: int = 32000,
+        pad_to_multiple_of: int = 64,
+        output_projector_states: bool = False,
+        **kwargs: str,
+    ) -> None:
+        if vision_backbone_id not in VALID_VISION_BACKBONES:
+            raise ValueError(f"Vision backbone `{vision_backbone_id}` not in {VALID_VISION_BACKBONES = }")
+
+        if llm_backbone_id not in VALID_LLM_BACKBONES:
+            raise ValueError(f"LLM backbone `{llm_backbone_id}` not in {VALID_LLM_BACKBONES = }")
+
+        # Set Prismatic Configuration Fields
+        self.vision_backbone_id = vision_backbone_id
+        self.llm_backbone_id = llm_backbone_id
+        self.arch_specifier = arch_specifier
+        self.output_projector_states = output_projector_states
+
+        # [Contract] All vision backbone parameters are lists =>> supports fused backbones with different preprocessing
+        self.use_fused_vision_backbone = (
+            use_fused_vision_backbone
+            if use_fused_vision_backbone is not None
+            else any(self.vision_backbone_id.startswith(v) for v in ["dinoclip", "dinosiglip"])
+        )
+
+        self.timm_model_ids = VISION_BACKBONE_TO_TIMM_ID[self.vision_backbone_id]
+        self.timm_override_act_layers = TIMM_OVERRIDE_ACT_LAYER[self.vision_backbone_id]
+        self.image_sizes = VISION_BACKBONE_TO_RESOLUTION[self.vision_backbone_id]
+        self.image_resize_strategy = image_resize_strategy
+
+        self.hf_llm_id = LLM_BACKBONE_TO_HF_PATH[self.llm_backbone_id]
+        self.llm_max_length = llm_max_length
+        self.pad_token_id, self.pad_to_multiple_of = pad_token_id, pad_to_multiple_of
+
+        # [IMPORTANT] HF Utilities actually look for a `text_config` field... we need to use that specific naming!
+        self.text_config = (
+            CONFIG_MAPPING[LLM_BACKBONE_TO_HF_METACLASS[self.llm_backbone_id]](**text_config)
+            if text_config is not None
+            else CONFIG_MAPPING[LLM_BACKBONE_TO_HF_METACLASS[self.llm_backbone_id]]()
+        )
+
+        # Dispatch **kwargs to super() =>> note that `pad_token_id` collides, so we pass it in here as well...
+        super().__init__(pad_token_id=pad_token_id, **kwargs)
+
+
+class OpenVLAConfig(PrismaticConfig):
+    model_type: str = "openvla"
+
+    def __init__(
+        self,
+        norm_stats: Optional[Dict[str, Dict[str, Dict[str, Dict[str, List[float]]]]]] = None,
+        n_action_bins: int = 256,
+        **kwargs: str,
+    ) -> None:
+        self.norm_stats, self.n_action_bins = norm_stats, n_action_bins
+
+        super().__init__(**kwargs)