first commit

README.md

@@ -0,0 +1,80 @@
+---
+library_name: peft
+datasets:
+- liuhaotian/LLaVA-Pretrain
+- liuhaotian/LLaVA-Instruct-150K
+pipeline_tag: visual-question-answering
+---
+
+<div align="center">
+  <img src="https://github.com/InternLM/lmdeploy/assets/36994684/0cf8d00f-e86b-40ba-9b54-dc8f1bc6c8d8" width="600"/>
+
+
+[![Generic badge](https://img.shields.io/badge/GitHub-%20XTuner-black.svg)](https://github.com/InternLM/xtuner)
+
+
+</div>
+
+## Model
+
+llava-v1.5-13b-xtuner is a LLaVA model fine-tuned from [Vicuna-v1.5-13B](https://huggingface.co/lmsys/vicuna-13b-v1.5) and [CLIP-ViT-Large-patch14-336](https://huggingface.co/openai/clip-vit-large-patch14-336) with [LLaVA-Pretrain](https://huggingface.co/datasets/liuhaotian/LLaVA-Pretrain) and [LLaVA-Instruct](https://huggingface.co/datasets/liuhaotian/LLaVA-Instruct-150K) by [XTuner](https://github.com/InternLM/xtuner).
+
+
+## Quickstart
+
+### Installation
+
+```shell
+pip install -U 'xtuner[deepspeed]'
+```
+
+### Chat
+
+```shell
+xtuner chat lmsys/vicuna-13b-v1.5 \
+  --visual-encoder openai/clip-vit-large-patch14 \
+  --llava xtuner/llava-v1.5-13b-xtuner \
+  --prompt-template vicuna \
+  --image $IMAGE_PATH
+```
+
+### Training
+
+1. Alignment module pretraining (saved by default in `./work_dirs/`)
+
+```shell
+NPROC_PER_NODE=8 xtuner train llava_vicuna_v15_13b_clip_vit_large_p14_336_e1_gpu8_pretrain --deepspeed deepspeed_zero2
+```
+
+2. Instruction following fine-tuning (saved by default in `./work_dirs/`)
+
+```shell
+NPROC_PER_NODE=8 xtuner train llava_vicuna_v15_13b_qlora_clip_vit_large_p14_336_lora_e1_gpu8_finetune --deepspeed deepspeed_zero2
+```
+
+
+### MMBench Evaluation
+
+XTuner integrates the MMBench evaluation, and you can perform evaluations with the following command!
+
+```bash
+xtuner mmbench lmsys/vicuna-13b-v1.5 \
+  --visual-encoder openai/clip-vit-large-patch14 \
+  --llava xtuner/llava-v1.5-13b-xtuner \
+  --prompt-template vicuna \
+  --data-path $MMBENCH_DATA_PATH \
+  --work-dir $RESULT_PATH
+```
+
+After the evaluation is completed, if it's a development set, it will directly print out the results; If it's a test set, you need to submit `mmbench_result.xlsx` to the official MMBench for final evaluation to obtain precision results!
+
+## Citation
+
+```bibtex
+@misc{2023xtuner,
+    title={XTuner: A Toolkit for Efficiently Fine-tuning LLM},
+    author={XTuner Contributors},
+    howpublished = {\url{https://github.com/InternLM/xtuner}},
+    year={2023}
+}
+```

llm_adapter/README.md

@@ -0,0 +1,220 @@
+---
+library_name: peft
+base_model: lmsys/vicuna-13b-v1.5
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.2

llm_adapter/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "lmsys/vicuna-13b-v1.5",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 256,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 512,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

llm_adapter/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebdb98c7f4cf16ecadbc36f60b2b52fd1d0cb9df8a0feda2a3a40f84dddfc8e7
+size 4005763658

projector/config.json

@@ -0,0 +1,17 @@
+{
+  "architectures": [
+    "ProjectorModel"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_projector.ProjectorConfig",
+    "AutoModel": "modeling_projector.ProjectorModel"
+  },
+  "bias": true,
+  "depth": 2,
+  "hidden_act": "gelu",
+  "llm_hidden_size": 5120,
+  "model_type": "projector",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "visual_hidden_size": 1024
+}

projector/configuration_projector.py

@@ -0,0 +1,23 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+from transformers import PretrainedConfig
+
+
+class ProjectorConfig(PretrainedConfig):
+    model_type = 'projector'
+    _auto_class = 'AutoConfig'
+
+    def __init__(
+        self,
+        visual_hidden_size=4096,
+        llm_hidden_size=4096,
+        depth=2,
+        hidden_act='gelu',
+        bias=True,
+        **kwargs,
+    ):
+        self.visual_hidden_size = visual_hidden_size
+        self.llm_hidden_size = llm_hidden_size
+        self.depth = depth
+        self.hidden_act = hidden_act
+        self.bias = bias
+        super().__init__(**kwargs)

projector/modeling_projector.py

@@ -0,0 +1,51 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+import torch
+import torch.nn as nn
+from transformers import PreTrainedModel
+from transformers.activations import ACT2FN
+
+from .configuration_projector import ProjectorConfig
+
+
+class ProjectorModel(PreTrainedModel):
+    _auto_class = 'AutoModel'
+    config_class = ProjectorConfig
+    base_model_prefix = 'model'
+    supports_gradient_checkpointing = True
+
+    def __init__(self, config: ProjectorConfig) -> None:
+        super().__init__(config)
+        self.gradient_checkpointing = False
+
+        modules = [
+            nn.Linear(
+                config.visual_hidden_size,
+                config.llm_hidden_size,
+                bias=config.bias)
+        ]
+        for _ in range(1, config.depth):
+            modules.append(ACT2FN[config.hidden_act])
+            modules.append(
+                nn.Linear(
+                    config.llm_hidden_size,
+                    config.llm_hidden_size,
+                    bias=config.bias))
+        self.model = nn.Sequential(*modules)
+
+    def enable_input_require_grads(self):
+
+        def make_inputs_require_grad(module, input, output):
+            output.requires_grad_(True)
+
+        self.model.register_forward_hook(make_inputs_require_grad)
+
+    def _set_gradient_checkpointing(self, module, value=False):
+        if isinstance(module, ProjectorModel):
+            module.gradient_checkpointing = value
+
+    def forward(self, x):
+        if self.gradient_checkpointing and self.training:
+            layer_outputs = torch.utils.checkpoint.checkpoint(self.model, x)
+        else:
+            layer_outputs = self.model(x)
+        return layer_outputs

projector/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a7866d703d4b9aec350b9cdacd02c6b8eaa826e81c66396cff5e374e51911ad
+size 125872128

visual_encoder_adapter/README.md

@@ -0,0 +1,208 @@
+---
+library_name: peft
+base_model: openai/clip-vit-large-patch14-336
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+## Training procedure
+
+
+### Framework versions
+
+
+- PEFT 0.6.2

visual_encoder_adapter/adapter_config.json

@@ -0,0 +1,30 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "CLIPVisionModel",
+    "parent_library": "transformers.models.clip.modeling_clip"
+  },
+  "base_model_name_or_path": "openai/clip-vit-large-patch14-336",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "fc2",
+    "out_proj",
+    "k_proj",
+    "fc1"
+  ],
+  "task_type": null
+}

visual_encoder_adapter/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d54c1966f2c3117044d8066eab859cd4f1d0883d39d2571c22b5ed442c63f1fc
+size 113350282

xtuner_config.py

@@ -0,0 +1,208 @@
+SYSTEM = ''
+accumulative_counts = 1
+batch_size = 16
+betas = (
+    0.9,
+    0.999,
+)
+custom_hooks = [
+    dict(
+        tokenizer=dict(
+            padding_side='right',
+            pretrained_model_name_or_path='lmsys/vicuna-13b-v1.5',
+            trust_remote_code=True,
+            type='transformers.AutoTokenizer.from_pretrained'),
+        type='xtuner.engine.DatasetInfoHook'),
+    dict(
+        evaluation_images='https://llava-vl.github.io/static/images/view.jpg',
+        evaluation_inputs=[
+            '请描述一下这张照片',
+            'Please describe this picture',
+        ],
+        every_n_iters=500,
+        image_processor=dict(
+            pretrained_model_name_or_path='openai/clip-vit-large-patch14-336',
+            trust_remote_code=True,
+            type='transformers.CLIPImageProcessor.from_pretrained'),
+        prompt_template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
+        system='',
+        tokenizer=dict(
+            padding_side='right',
+            pretrained_model_name_or_path='lmsys/vicuna-13b-v1.5',
+            trust_remote_code=True,
+            type='transformers.AutoTokenizer.from_pretrained'),
+        type='xtuner.engine.EvaluateChatHook'),
+]
+data_path = './data/llava_data/LLaVA-Instruct-150K/llava_v1_5_mix665k.json'
+data_root = './data/llava_data/'
+dataloader_num_workers = 0
+default_hooks = dict(
+    checkpoint=dict(interval=1, type='mmengine.hooks.CheckpointHook'),
+    logger=dict(interval=10, type='mmengine.hooks.LoggerHook'),
+    param_scheduler=dict(type='mmengine.hooks.ParamSchedulerHook'),
+    sampler_seed=dict(type='mmengine.hooks.DistSamplerSeedHook'),
+    timer=dict(type='mmengine.hooks.IterTimerHook'))
+env_cfg = dict(
+    cudnn_benchmark=False,
+    dist_cfg=dict(backend='nccl'),
+    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0))
+evaluation_freq = 500
+evaluation_images = 'https://llava-vl.github.io/static/images/view.jpg'
+evaluation_inputs = [
+    '请描述一下这张照片',
+    'Please describe this picture',
+]
+image_folder = './data/llava_data/llava_images'
+image_processor = dict(
+    pretrained_model_name_or_path='openai/clip-vit-large-patch14-336',
+    trust_remote_code=True,
+    type='transformers.CLIPImageProcessor.from_pretrained')
+launcher = 'pytorch'
+llava_dataset = dict(
+    data_path='./data/llava_data/LLaVA-Instruct-150K/llava_v1_5_mix665k.json',
+    dataset_map_fn='xtuner.dataset.map_fns.llava_map_fn',
+    image_folder='./data/llava_data/llava_images',
+    image_processor=dict(
+        pretrained_model_name_or_path='openai/clip-vit-large-patch14-336',
+        trust_remote_code=True,
+        type='transformers.CLIPImageProcessor.from_pretrained'),
+    max_length=1472,
+    pad_image_to_square=True,
+    template_map_fn=dict(
+        template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
+        type='xtuner.dataset.map_fns.template_map_fn_factory'),
+    tokenizer=dict(
+        padding_side='right',
+        pretrained_model_name_or_path='lmsys/vicuna-13b-v1.5',
+        trust_remote_code=True,
+        type='transformers.AutoTokenizer.from_pretrained'),
+    type='xtuner.dataset.LLaVADataset')
+llm_name_or_path = 'lmsys/vicuna-13b-v1.5'
+load_from = None
+log_level = 'INFO'
+lr = 0.0002
+max_epochs = 1
+max_length = 1472
+max_norm = 1
+model = dict(
+    freeze_llm=True,
+    freeze_visual_encoder=True,
+    llm=dict(
+        pretrained_model_name_or_path='lmsys/vicuna-13b-v1.5',
+        quantization_config=dict(
+            bnb_4bit_compute_dtype='torch.float16',
+            bnb_4bit_quant_type='nf4',
+            bnb_4bit_use_double_quant=True,
+            llm_int8_has_fp16_weight=False,
+            llm_int8_threshold=6.0,
+            load_in_4bit=True,
+            load_in_8bit=False,
+            type='transformers.BitsAndBytesConfig'),
+        torch_dtype='torch.float16',
+        trust_remote_code=True,
+        type='transformers.AutoModelForCausalLM.from_pretrained'),
+    llm_lora=dict(
+        bias='none',
+        lora_alpha=256,
+        lora_dropout=0.05,
+        r=512,
+        task_type='CAUSAL_LM',
+        type='peft.LoraConfig'),
+    pretrained_pth=
+    './work_dirs/llava_vicuna_13b_v15_clip_vit_large_p14_336_e1_gpu8_pretrain/epoch_1.pth',
+    type='xtuner.model.LLaVAModel',
+    visual_encoder=dict(
+        pretrained_model_name_or_path='openai/clip-vit-large-patch14-336',
+        type='transformers.CLIPVisionModel.from_pretrained'),
+    visual_encoder_lora=dict(
+        bias='none',
+        lora_alpha=16,
+        lora_dropout=0.05,
+        r=64,
+        type='peft.LoraConfig'))
+optim_type = 'torch.optim.AdamW'
+optim_wrapper = dict(
+    optimizer=dict(
+        betas=(
+            0.9,
+            0.999,
+        ),
+        lr=0.0002,
+        type='torch.optim.AdamW',
+        weight_decay=0),
+    type='DeepSpeedOptimWrapper')
+param_scheduler = [
+    dict(
+        begin=0,
+        by_epoch=True,
+        convert_to_iter_based=True,
+        end=0.03,
+        start_factor=1e-05,
+        type='mmengine.optim.LinearLR'),
+    dict(
+        T_max=1,
+        begin=0.03,
+        by_epoch=True,
+        convert_to_iter_based=True,
+        eta_min=0.0,
+        type='mmengine.optim.CosineAnnealingLR'),
+]
+pretrained_pth = './work_dirs/llava_vicuna_13b_v15_clip_vit_large_p14_336_e1_gpu8_pretrain/epoch_1.pth'
+prompt_template = 'xtuner.utils.PROMPT_TEMPLATE.vicuna'
+randomness = dict(deterministic=False, seed=None)
+resume = False
+runner_type = 'FlexibleRunner'
+strategy = dict(
+    config=dict(
+        bf16=dict(enabled=True),
+        fp16=dict(enabled=False, initial_scale_power=16),
+        gradient_accumulation_steps='auto',
+        gradient_clipping='auto',
+        train_micro_batch_size_per_gpu='auto',
+        zero_allow_untested_optimizer=True,
+        zero_force_ds_cpu_optimizer=False,
+        zero_optimization=dict(overlap_comm=True, stage=2)),
+    exclude_frozen_parameters=True,
+    gradient_accumulation_steps=1,
+    gradient_clipping=1,
+    train_micro_batch_size_per_gpu=16,
+    type='xtuner.engine.DeepSpeedStrategy')
+tokenizer = dict(
+    padding_side='right',
+    pretrained_model_name_or_path='lmsys/vicuna-13b-v1.5',
+    trust_remote_code=True,
+    type='transformers.AutoTokenizer.from_pretrained')
+train_cfg = dict(by_epoch=True, max_epochs=1, val_interval=1)
+train_dataloader = dict(
+    batch_size=16,
+    collate_fn=dict(type='xtuner.dataset.collate_fns.default_collate_fn'),
+    dataset=dict(
+        data_path=
+        './data/llava_data/LLaVA-Instruct-150K/llava_v1_5_mix665k.json',
+        dataset_map_fn='xtuner.dataset.map_fns.llava_map_fn',
+        image_folder='./data/llava_data/llava_images',
+        image_processor=dict(
+            pretrained_model_name_or_path='openai/clip-vit-large-patch14-336',
+            trust_remote_code=True,
+            type='transformers.CLIPImageProcessor.from_pretrained'),
+        max_length=1472,
+        pad_image_to_square=True,
+        template_map_fn=dict(
+            template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
+            type='xtuner.dataset.map_fns.template_map_fn_factory'),
+        tokenizer=dict(
+            padding_side='right',
+            pretrained_model_name_or_path='lmsys/vicuna-13b-v1.5',
+            trust_remote_code=True,
+            type='transformers.AutoTokenizer.from_pretrained'),
+        type='xtuner.dataset.LLaVADataset'),
+    num_workers=0,
+    sampler=dict(
+        length_property='modality_length',
+        per_device_batch_size=16,
+        type='xtuner.dataset.samplers.LengthGroupedSampler'))
+visual_encoder_name_or_path = 'openai/clip-vit-large-patch14-336'
+visualizer = None
+warmup_ratio = 0.03
+weight_decay = 0
+work_dir = './work_dirs/llava_vicuna_13b_v15_qlora_clip_vit_large_p14_336_lora_e1_gpu8_finetune'