Merge pull request #10 from StarrickLiu/main

Fix tokenizer reading and update README

wall_x/data/load_lerobot_dataset.py

@@ -216,25 +216,15 @@ class DataCollator:
             if self.config.get("padding_side", "left") == "left":
                 self._processor_cache[processor_path].tokenizer.padding_side = "left"
 
-        if action_tokenizer_path not in self._action_tokenizer_cache:
+        if self.use_fast_tokenizer and action_tokenizer_path not in self._action_tokenizer_cache:
             self._action_tokenizer_cache[action_tokenizer_path] = AutoProcessor.from_pretrained(action_tokenizer_path, trust_remote_code=True)
 
         self.processor = self._processor_cache[processor_path]
-        self.val_processor = self._processor_cache[processor_path]
-        self.train_action_tokenizer = self._action_tokenizer_cache[action_tokenizer_path]
-        self.val_action_tokenizer = self._action_tokenizer_cache[action_tokenizer_path]
 
-        new_tokens = ["<|propri|>", "<|action|>"]
-
-        new_tokens += [f"<|action_token_{i}|>" for i in range(self.train_action_tokenizer.vocab_size)]
         if not self.use_fast_tokenizer:
             self.train_action_tokenizer = None
-            self.val_action_tokenizer = None
-
-        # Only add tokens if not already added
-        if "<|propri|>" not in self.processor.tokenizer.get_vocab():
-            num_added_tokens = self.processor.tokenizer.add_tokens(new_tokens)
-            self.val_processor.tokenizer.add_tokens(new_tokens)
+        else:
+            self.train_action_tokenizer = self._action_tokenizer_cache[action_tokenizer_path]
 
         if self.use_fast_tokenizer:
             self.action_mapper = {}

workspace/README.md

@@ -19,10 +19,10 @@ git clone https://huggingface.co/physical-intelligence/fast
 
 ## Required Paths (Must Modify)
 ```yaml
-pretrained_wallx_path: "/path/to/wallx_model/"      # Path to pretrained Qwen VL model
-use_fast_tokenizer: false                           # True: train FAST, False: train Flow
-action_tokenizer_path: "/path/to/fast/"             # Path to action tokenizer
+pretrained_wallx_path: "/path/to/wallx_model/"      # Path to pretrained wallx model
 save_path: "/path/to/workspace/"                    # Path to save training outputs
+use_fast_tokenizer: False                           # True: train FAST, False: train Flow
+action_tokenizer_path: "/path/to/fast/"             # Must set if use_fast_tokenizer is True
 ```
 
 ## Training Parameters (Commonly Modified)

workspace/lerobot_example/config_qact.yml

@@ -5,10 +5,10 @@
 log_name: "robotic_training"
 log_project: "vla_training"
 model_type: qwen2_5
-pretrained_wallx_path: "/path/to/wallx_model/"
-use_fast_tokenizer: false # True: train FAST, False: train Flow
-action_tokenizer_path: "/path/to/fast/"
-save_path: "/path/to/workspace/"
+pretrained_wallx_path: "/path/to/wallx_model/"  # Must set
+save_path: "/path/to/workspace/"                # Must set
+use_fast_tokenizer: False                       # True: train FAST, False: train Flow
+action_tokenizer_path: "/path/to/fast/"         # Must set if use_fast_tokenizer is true
 
 # Torch Profile
 profile: False