Upload TrajectoryVLA

config.json

@@ -1,74 +1,36 @@
 {
   "arch_specifier": "no-align+gelu-mlp",
+  "architectures": [
+    "TrajectoryVLA"
+  ],
   "auto_map": {
-    "AutoConfig": "prismatic_config.TrajectoryVLAConfig"
+    "AutoModelForVision2Seq": "prismatic_model.TrajectoryVLA"
   },
-  "cheat": false,
+  "hf_llm_id": "meta-llama/Llama-2-7b-hf",
   "image_resize_strategy": "letterbox",
+  "image_sizes": [
+    224,
+    224
+  ],
   "llm_backbone_id": "llama2-7b-pure",
   "llm_max_length": 2048,
-  "model_type": "trajectoryvla",
-  "num_timesteps": 6,
+  "model_type": "prismatic",
   "output_projector_states": false,
   "pad_to_multiple_of": 64,
   "pad_token_id": 32000,
-  "prismatic_config": {
-    "architectures": [
-      "TrajectoryVLA"
-    ],
-    "auto_map": {
-      "AutoModelForVision2Seq": "prismatic_model.TrajectoryVLA"
-    },
-    "model_type": "prismatic",
-    "return_dict": false,
-    "torch_dtype": "bfloat16"
-  },
   "return_dict": false,
-  "rotation_components": 9,
-  "seperate_control_proj": true,
-  "text_config": null,
-  "timestep_proj_config": {
-    "num_tokens": 3,
-    "pos_embed_scale": 8,
-    "proj_layers": [
-      128,
-      512,
-      1024
-    ],
-    "time_delta_sec": 0.1
-  },
-  "token_proj_config": {
-    "control_tokens_layers": [
-      4096,
-      2048,
-      1024
-    ],
-    "image_tokens_mode": "vit",
-    "llm_image_tokens_layers": [],
-    "vit_tokens_layers": [
-      2176,
-      1024
-    ]
-  },
-  "token_size": 1024,
-  "transformer_config": {
-    "decoder_block_config": {
-      "dropout": 0.0,
-      "feature_size": 1024,
-      "head_dim": 64,
-      "num_heads": 16
-    },
-    "encoder_block_config": {
-      "feature_size": 1024,
-      "head_dim": 64,
-      "num_heads": 16
-    },
-    "num_blocks": 2,
-    "pos_embed_config": {
-      "embedding_dim": 1024,
-      "num_embeddings": 300
-    }
+  "text_config": {
+    "model_type": "llama"
   },
+  "timm_model_ids": [
+    "vit_large_patch14_reg4_dinov2.lvd142m",
+    "vit_so400m_patch14_siglip_224"
+  ],
+  "timm_override_act_layers": [
+    null,
+    null
+  ],
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
   "use_fused_vision_backbone": true,
   "vision_backbone_id": "dinosiglip-vit-so-224px"