unsloth/llava-1.5-7b-hf-bnb-4bit

Finetune Llama 3.2, Qwen 2.5, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth!

We have a free Google Colab Tesla T4 notebook for Llava 1.5 (7B) here: https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing

And a free notebook for Llama 3.2 Vision (11B) here

unsloth/llava-1.5-7b-hf-bnb-4bit

For more details on the model, please go to the original model card

✨ Finetune for Free

All notebooks are beginner friendly! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.

Unsloth supports	Free Notebooks	Performance	Memory use
Llama-3.2 (3B)	▶️ Start on Colab	2.4x faster	58% less
Llama-3.2 (11B vision)	▶️ Start on Colab	2x faster	40% less
Qwen2 VL (7B)	▶️ Start on Colab	1.8x faster	40% less
Qwen2.5 (7B)	▶️ Start on Colab	2x faster	60% less
Llama-3.1 (8B)	▶️ Start on Colab	2.4x faster	58% less
Phi-3.5 (mini)	▶️ Start on Colab	2x faster	50% less
Gemma 2 (9B)	▶️ Start on Colab	2.4x faster	58% less
Mistral (7B)	▶️ Start on Colab	2.2x faster	62% less
DPO - Zephyr	▶️ Start on Colab	1.9x faster	19% less

• This conversational notebook is useful for ShareGPT ChatML / Vicuna templates.
• This text completion notebook is for raw text. This DPO notebook replicates Zephyr.
• * Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.

Llava 1.5 Details

Model type: LLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture.

Model date: LLaVA-v1.5-7B was trained in September 2023.

Paper or resources for more information: https://llava-vl.github.io/

How to use the model

First, make sure to have transformers >= 4.35.3. The model supports multi-image and multi-prompt generation. Meaning that you can pass multiple images in your prompt. Make sure also to follow the correct prompt template (USER: xxx\nASSISTANT:) and add the token <image> to the location where you want to query images:

Using pipeline:

Below we used "llava-hf/llava-1.5-7b-hf" checkpoint.

from transformers import pipeline, AutoProcessor
from PIL import Image    
import requests

model_id = "llava-hf/llava-1.5-7b-hf"
pipe = pipeline("image-to-text", model=model_id)
url = "https://huggingface.co./datasets/huggingface/documentation-images/resolve/main/transformers/tasks/ai2d-demo.jpg"
image = Image.open(requests.get(url, stream=True).raw)

# Define a chat history and use `apply_chat_template` to get correctly formatted prompt
# Each value in "content" has to be a list of dicts with types ("text", "image") 
conversation = [
    {
      "role": "user",
      "content": [
          {"type": "text", "text": "What does the label 15 represent? (1) lava (2) core (3) tunnel (4) ash cloud"},
          {"type": "image"},
        ],
    },
]
processor = AutoProcessor.from_pretrained(model_id)

prompt = processor.apply_chat_template(conversation, add_generation_prompt=True)

outputs = pipe(image, prompt=prompt, generate_kwargs={"max_new_tokens": 200})
print(outputs)
>>> {"generated_text": "\nUSER: What does the label 15 represent? (1) lava (2) core (3) tunnel (4) ash cloud\nASSISTANT: Lava"}

Using pure transformers:

Below is an example script to run generation in float16 precision on a GPU device:

import requests
from PIL import Image

import torch
from transformers import AutoProcessor, LlavaForConditionalGeneration

model_id = "llava-hf/llava-1.5-7b-hf"
model = LlavaForConditionalGeneration.from_pretrained(
    model_id, 
    torch_dtype=torch.float16, 
    low_cpu_mem_usage=True, 
).to(0)

processor = AutoProcessor.from_pretrained(model_id)

# Define a chat histiry and use `apply_chat_template` to get correctly formatted prompt
# Each value in "content" has to be a list of dicts with types ("text", "image") 
conversation = [
    {

      "role": "user",
      "content": [
          {"type": "text", "text": "What are these?"},
          {"type": "image"},
        ],
    },
]
prompt = processor.apply_chat_template(conversation, add_generation_prompt=True)

image_file = "http://images.cocodataset.org/val2017/000000039769.jpg"
raw_image = Image.open(requests.get(image_file, stream=True).raw)
inputs = processor(images=raw_image, text=prompt, return_tensors='pt').to(0, torch.float16)

output = model.generate(**inputs, max_new_tokens=200, do_sample=False)
print(processor.decode(output[0][2:], skip_special_tokens=True))

Model optimization

4-bit quantization through bitsandbytes library

First make sure to install bitsandbytes, pip install bitsandbytes and make sure to have access to a CUDA compatible GPU device. Simply change the snippet above with:

model = LlavaForConditionalGeneration.from_pretrained(
    model_id, 
    torch_dtype=torch.float16, 
    low_cpu_mem_usage=True,
+   load_in_4bit=True
)

Use Flash-Attention 2 to further speed-up generation

First make sure to install flash-attn. Refer to the original repository of Flash Attention regarding that package installation. Simply change the snippet above with:

model = LlavaForConditionalGeneration.from_pretrained(
    model_id, 
    torch_dtype=torch.float16, 
    low_cpu_mem_usage=True,
+   use_flash_attention_2=True
).to(0)

License

Llama 2 is licensed under the LLAMA 2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved.