README.md

---
license: mit
datasets:
- Vi-VLM/Vista
language:
- vi
---

LLaVA-Qwen1.5-1.8b model trained with LoRA, on a subset of Vista Vi LLaVA Complex Reasoning. 
Loss: ~1.5

Training script
```bash
deepspeed moellava/train/train_mem.py \
    --lora_enable True --lora_r 128 --lora_alpha 256 --mm_projector_lr 0.00000125 \
    --lora_path /kaggle/temp/lora-llavaqwen \
    --deepspeed ./scripts/zero3.json \
    --model_name_or_path Qwen/Qwen1.5-1.8B \
    --version qwen \
    --data_path /kaggle/temp/vi_llava_train.json \
    --image_folder /kaggle/input/coco-2017-dataset/coco2017/train2017 \
    --image_tower google/siglip-base-patch16-256-multilingual \
    --image_projector_type mlp2x_gelu \
    --pretrain_mm_mlp_adapter /kaggle/temp/pt-llavaqwen1.5-1.8b/mm_projector.bin \
    --mm_vision_select_layer -2 \
    --mm_use_im_start_end False \
    --mm_use_im_patch_token False \
    --image_aspect_ratio pad \
    --group_by_modality_length True \
    --fp16 True \
    --output_dir ./checkpoints/ft-lora-llavaqwen1.5-1.8b-complex_reasoning \
    --num_train_epochs 1 \
    --per_device_train_batch_size 2 \
    --per_device_eval_batch_size 4 \
    --gradient_accumulation_steps 8 \
    --evaluation_strategy "no" \
    --save_strategy "steps" \
    --save_steps 100 \
    --save_total_limit 1 \
    --learning_rate 1e-5 \
    --weight_decay 0. \
    --warmup_ratio 0 \
    --lr_scheduler_type "cosine" \
    --logging_steps 5 \
    --tf32 False \
    --model_max_length 1024 \
    --gradient_checkpointing True \
    --dataloader_num_workers 4 \
    --lazy_preprocess True \
    --report_to wandb \
    --run_name ft-llava-qwen1.5-1.8b-lora-vista_reasoning-cont \
    --push_to_hub True
```

Python code to merge LoRA
```python
from typing import Optional, List
class ModelArguments:
    model_name_or_path: Optional[str] = "facebook/opt-125m"
    version: Optional[str] = "v0"
    freeze_backbone: bool = False
    tune_mm_mlp_adapter: bool = False
    mm_vision_select_layer: Optional[int] = -1   # default to the last layer
    pretrain_mm_mlp_adapter: Optional[str] = None
    mm_use_im_start_end: bool = False
    mm_use_im_patch_token: bool = True
    mm_vision_select_feature: Optional[str] = "patch"
    # ===================================================================
    image_tower: Optional[str] = 'google/siglip-base-patch16-256-multilingual'
    video_tower: Optional[str] = None
    image_projector_type: Optional[str] = 'linear'
    video_projector_type: Optional[str] = 'linear'
    video_global_proj: bool = False
    video_temproal_proj: bool = False
    video_spatial_proj: bool = False
    # ===================================================================

    # =============================================================
    only_lora_ffn: bool = True
    moe_enable: bool = False
    train_modules: Optional[List[str]] = None
    moe_mode: str = "sparse"
    moe_layers_idx: Optional[List[int]] = None
    ep_size: int = 1
    num_experts: Optional[List[int]] = 4
    top_k_experts: int = 2
    capacity_factor: float = 1.
    eval_capacity_factor: float = 2.
    min_capacity: int = 0
    use_residual: bool = False
    router_aux_loss_coef: float = 0.01

class DataArguments:
    lazy_preprocess: bool = False
    is_multimodal: bool = False
    image_aspect_ratio: str = 'pad'
    # ===================================================================
    data_path: Optional[List[str]] = None
    image_folder: Optional[str] = None
    video_folder: Optional[str] = None
    num_frames: int = 8

model_args = ModelArguments()
data_args = DataArguments()

import torch 
from peft import PeftModel
from moellava.model import LlavaQwen1_5ForCausalLM

model_name_or_path = 'Qwen/Qwen1.5-1.8B'
lora_path = 'llavaqwen1.5-lora'

model = LlavaQwen1_5ForCausalLM.from_pretrained(
    model_name_or_path,
)

model.to(torch.float16)
model = PeftModel.from_pretrained(model, lora_path)
model

import transformers

tokenizer = transformers.AutoTokenizer.from_pretrained(
    model_args.model_name_or_path,
    model_max_length=1024,
    padding_side="right",
    use_fast=False,
)
tokenizer.add_special_tokens({'unk_token': '<|extra_0|>'})

model.get_model().initialize_vision_modules(
    model_args=model_args,
)

image_tower = model.get_image_tower()
image_tower.to(dtype=torch.float16)

data_args.image_processor = image_tower.image_processor
data_args.is_multimodal = True

model.config.image_aspect_ratio = data_args.image_aspect_ratio
model.config.tokenizer_padding_side = tokenizer.padding_side

model.config.mm_use_im_start_end = data_args.mm_use_im_start_end = model_args.mm_use_im_start_end
model.config.mm_use_im_patch_token = model_args.mm_use_im_patch_token
model.initialize_vision_tokenizer(model_args, tokenizer=tokenizer)

merged_model = model.merge_and_unload()
merged_model.save_pretrained("llava-qwen1.5-1.8b-complex_reasoning-merged")
```