diff --git a/README.md b/README_cn.md similarity index 67% rename from README.md rename to README_cn.md index a35dd3e..89d5e8c 100644 --- a/README.md +++ b/README_cn.md @@ -1,6 +1,11 @@ +**其他语言版本: [English](README_en.md), [中文](README_zh.md).** # OpenVLA Lightweight Version -OpenVLA的轻量化版本 +OpenVLA的轻量化版本，基于llava-next框架 +特点： +1.主体模型仅0.5B，使用qwen2-0.5B +2.不使用RLDS格式数据集，使用mllm格式进行微调 +3.不占用LLM模型固有tokens,使用新增的271个tokens表示动作 ## Installation @@ -26,7 +31,7 @@ pip install -e ".[train]" ``` ## Acknowledgements -I would like to express our gratitude to the following repositories: +I would like to express my gratitude to the following repositories: - [OpenVLA](https://github.com/openvla/openvla) - For providing the core structure and functionality that inspired OpenVLA-Qwen. - [LLaVA_OpenVLA](https://github.com/Darren-greenhand/LLaVA-Next) - For his contribution to data preprocessing techniques. diff --git a/README_en.md b/README_en.md new file mode 100644 index 0000000..c26c250 --- /dev/null +++ b/README_en.md @@ -0,0 +1,37 @@ +**Read this in other languages: [English](README_en.md), [中文](README_zh.md).** +# OpenVLA Lightweight Version + +OpenVLA的轻量化版本，基于llava-next框架 +特点： +1.主体模型仅0.5B，使用qwen2-0.5B +2.不使用RLDS格式数据集，使用mllm格式进行微调 +3.不占用LLM模型固有tokens,使用新增的271个tokens表示动作 + +## Installation + +Follow the steps below to install the OpenVLA-Qwen lightweight version. + +### 1. Clone the repository + +Clone the repository to your local machine: + +```bash +git clone https://github.com/IP127000/openVLA-Qwen.git +cd openVLA-Qwen +``` +### 2. Create a new conda environment and activate it: +```bash +conda create -n vla-qwen python=3.10 -y +conda activate vla-qwen +``` +### 3. Install the required dependencies +```bash +pip install --upgrade pip +pip install -e ".[train]" +``` +## Acknowledgements + +I would like to express my gratitude to the following repositories: + +- [OpenVLA](https://github.com/openvla/openvla) - For providing the core structure and functionality that inspired OpenVLA-Qwen. +- [LLaVA_OpenVLA](https://github.com/Darren-greenhand/LLaVA-Next) - For his contribution to data preprocessing techniques. diff --git a/llava/actiontokenizer.py b/llava/actiontokenizer.py index b0980fb..f920e91 100644 --- a/llava/actiontokenizer.py +++ b/llava/actiontokenizer.py @@ -8,72 +8,10 @@ from typing import List, Union import numpy as np from transformers import PreTrainedTokenizerBase - - -# class ActionTokenizer: -# def __init__( -# self, tokenizer: PreTrainedTokenizerBase, bins: int = 256, min_action: int = -1, max_action: int = 1 -# ) -> None: -# """ -# Discretizes continuous robot actions into N bins per dimension and maps to the least used tokens. - -# NOTE =>> by default, assumes a BPE-style tokenizer akin to the LlamaTokenizer, where *the least used tokens* -# appear at the end of the vocabulary! - -# :param tokenizer: Base LLM/VLM tokenizer to extend. -# :param bins: Number of bins for each continuous value; we'll adopt a uniform binning strategy. -# :param min_action: Minimum action value (for clipping, setting lower bound on bin interval). -# :param max_action: Maximum action value (for clipping, setting upper bound on bin interval). -# """ -# self.tokenizer, self.n_bins, self.min_action, self.max_action = tokenizer, bins, min_action, max_action - -# # Create Uniform Bins + Compute Bin Centers -# self.bins = np.linspace(min_action, max_action, self.n_bins) -# self.bin_centers = (self.bins[:-1] + self.bins[1:]) / 2.0 - -# # [Contract] Set "action_token_begin_idx" based on `self.tokenizer.vocab_size - (self.n_bins + 1)` -# # =>> Assumes we're always overwriting the final `n_bins` tokens of the vocabulary! -# self.action_token_begin_idx: int = int(self.tokenizer.vocab_size - (self.n_bins + 1)) - -# def __call__(self, action: np.ndarray) -> Union[str, List[str]]: -# """Clip & bin actions to *the last `n_bins` tokens* of the vocabulary (e.g., tokenizer.vocab[-256:]).""" -# action = np.clip(action, a_min=float(self.min_action), a_max=float(self.max_action)) -# discretized_action = np.digitize(action, self.bins) - -# # Handle single element vs. batch -# if len(discretized_action.shape) == 1: -# return self.tokenizer.decode(list(self.tokenizer.vocab_size - discretized_action)) -# else: -# return self.tokenizer.batch_decode((self.tokenizer.vocab_size - discretized_action).tolist()) - -# def decode_token_ids_to_actions(self, action_token_ids: np.ndarray) -> np.ndarray: -# """ -# Returns continuous actions for discrete action token IDs. - -# NOTE =>> Because of the way the actions are discretized w.r.t. the bins (and not the bin centers), the -# digitization returns bin indices between [1, # bins], inclusive, when there are actually only -# (# bins - 1) bin intervals. - -# Therefore, if the digitization returns the last possible index, we map this to the last bin interval. - -# EXAMPLE =>> Let's say self._bins has 256 values. Then self._bin_centers has 255 values. Digitization returns -# indices between [1, 256]. We subtract 1 from all indices so that they are between [0, 255]. There -# is still one index (i==255) that would cause an out-of-bounds error if used to index into -# self._bin_centers. Therefore, if i==255, we subtract 1 from it so that it just becomes the index of -# the last bin center. We implement this simply via clipping between [0, 255 - 1]. -# """ -# discretized_actions = self.tokenizer.vocab_size - action_token_ids -# discretized_actions = np.clip(discretized_actions - 1, a_min=0, a_max=self.bin_centers.shape[0] - 1) - -# return self.bin_centers[discretized_actions] - -# @property -# def vocab_size(self) -> int: -# return self.n_bins class ActionTokenizer: def __init__( - self, tokenizer: PreTrainedTokenizerBase, bins: int = 285, min_action = -0.0025, max_action = 0.0025 + self, tokenizer: PreTrainedTokenizerBase, bins: int = 271, min_action = -1.0, max_action = 1.0 # self, tokenizer: PreTrainedTokenizerBase, bins: int = 256, min_action: int = -1, max_action: int = 1 ) -> None: self.tokenizer, self.n_bins, self.min_action, self.max_action = tokenizer, bins, min_action, max_action @@ -93,8 +31,6 @@ class ActionTokenizer: # print('initializing action tokenizer, the new len(tokenizer) is:', len(self.tokenizer)) def __call__(self, action: np.ndarray) -> Union[str, List[str]]: - - action = np.clip(action, a_min=float(self.min_action), a_max=float(self.max_action)) discretized_action = np.digitize(action, self.bins) - 1 discretized_action = np.clip(discretized_action, a_min=0, a_max=self.n_bins - 1) @@ -114,7 +50,36 @@ class ActionTokenizer: action_indices = vectorized_lookup(action_token_ids) return self.bin_centers[action_indices] - # 返回所有 tokens 的数量，包括动作 tokens + def actionValue_to_actionName(self,action): + action_token_ids=self.__call__(action) + actionName=self.tokenizer.decode(action_token_ids) + return actionName + + def actionName_to_actionValue(self,actionName): + action_ids=self.tokenizer(actionName) + action_ids=action_ids["input_ids"] + actionValue=self.decode_token_ids_to_actions(action_ids) + return actionValue + + def str_to_mllm(self, result_str): + new_result=result_str + for token in self.action_tokens: + value=self.actionName_to_actionValue(token) + new_result=new_result.replace(token, str(value[0])) + return new_result + + def value_to_mllm(self, result_str): + new_result=result_str + data=[] + for token in self.action_tokens: + if new_result.startswith(token): + value=self.actionName_to_actionValue(token) + data.append(float(value)) + elif token in new_result: + value=self.actionName_to_actionValue(token) + data.append(float(value)) + return data + @property def vocab_size(self) -> int: return len(self.tokenizer) @@ -125,4 +90,4 @@ class ActionTokenizer: @property def action_vocab_size(self) -> int: - return len(self.action_tokens) \ No newline at end of file + return len(self.action_tokens) diff --git a/scripts/train/finetune_ov_vla.sh b/scripts/train/finetune_ov_vla.sh index 2a5d012..a47fed5 100644 --- a/scripts/train/finetune_ov_vla.sh +++ b/scripts/train/finetune_ov_vla.sh @@ -3,22 +3,11 @@ export NCCL_IB_DISABLE=0 export NCCL_IB_GID_INDEX=3 export NCCL_SOCKET_IFNAME=eth0 export NCCL_DEBUG=INFO -VISION_MODEL_VERSION="google/siglip-so400m-patch14-384" -VISION_MODEL_VERSION_CLEAN="${VISION_MODEL_VERSION//\//_}" - -############### Pretrain ################ - -BASE_RUN_NAME="llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-mlp2x_gelu-pretrain_blip558k_plain" -echo "BASE_RUN_NAME: ${BASE_RUN_NAME}" - ############### Finetune ################ MIXTURE="qwen" - -# Stage 2 PROMPT_VERSION="qwen_vla" -RUN_NAME="llava-openvla-${MIXTURE}" -PREV_STAGE_CHECKPOINT="/mnt/d/temp/huggingface/hub/llava_qwen_vla" -# PREV_STAGE_CHECKPOINT="/mnt/d/ckpt/llava-openvla-qwen" +RUN_NAME="openvla-${MIXTURE}" +PREV_STAGE_CHECKPOINT="models" echo "PREV_STAGE_CHECKPOINT: ${PREV_STAGE_CHECKPOINT}" echo "MID_RUN_NAME: ${RUN_NAME}" @@ -30,8 +19,8 @@ ACCELERATE_CPU_AFFINITY=1 torchrun --nproc_per_node="${NUM_GPUS}" --nnodes="${NN --deepspeed scripts/zero2.json \ --model_name_or_path $PREV_STAGE_CHECKPOINT \ --version $PROMPT_VERSION \ - --data_path /root/code/openvla-llava/LLaVA-Next/scripts/train/vla.yaml \ - --image_folder /root/code/openvla-llava/LLaVA-Next/images \ + --data_path scripts/train/vla.yaml \ + --image_folder /images \ --mm_tunable_parts="mm_language_model" \ --mm_vision_tower_lr=2e-6 \ --vision_tower google/siglip-so400m-patch14-384 \ @@ -45,7 +34,7 @@ ACCELERATE_CPU_AFFINITY=1 torchrun --nproc_per_node="${NUM_GPUS}" --nnodes="${NN --mm_patch_merge_type spatial_unpad \ --bf16 True \ --run_name $RUN_NAME \ - --output_dir /mnt/d/ckpt_3_28/$RUN_NAME \ + --output_dir /$RUN_NAME \ --num_train_epochs 5 \ --per_device_train_batch_size 8 \ --per_device_eval_batch_size 100 \ @@ -70,5 +59,3 @@ ACCELERATE_CPU_AFFINITY=1 torchrun --nproc_per_node="${NUM_GPUS}" --nnodes="${NN --dataloader_drop_last True \ --frames_upbound 1 exit 0; - -# You can delete the sdpa attn_implementation if you want to use flash attn