README.md

---
base_model: unsloth/llama-3.2-11b-vision-instruct-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- mllama
license: apache-2.0
language:
- en
---

# Uploaded  model

- **Developed by:** pollitoconpapass
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3.2-11b-vision-instruct-bnb-4bit

This mllama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.

[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)


# Implementation
```py
from datasets import load_dataset
from unsloth import FastVisionModel

model, tokenizer = FastVisionModel.from_pretrained(
    # "unsloth/Llama-3.2-11B-Vision-Instruct",
    "pollitoconpapass/Llama-3.2-11B-Vision-Radiology-mini",
    load_in_4bit = True, # Use 4bit to reduce memory use. False for 16bit LoRA.
    use_gradient_checkpointing = "unsloth", # True or "unsloth" for long context
)

model = FastVisionModel.get_peft_model(
    model,
    finetune_vision_layers     = True, # False if not finetuning vision layers
    finetune_language_layers   = True, # False if not finetuning language layers
    finetune_attention_modules = True, # False if not finetuning attention layers
    finetune_mlp_modules       = True, # False if not finetuning MLP layers

    r = 16,           # The larger, the higher the accuracy, but might overfit
    lora_alpha = 16,  # Recommended alpha == r at least
    lora_dropout = 0,
    bias = "none",
    random_state = 3407,
    use_rslora = False,  # We support rank stabilized LoRA
    loftq_config = None, # And LoftQ
    # target_modules = "all-linear", # Optional now! Can specify a list if needed
)

dataset = load_dataset("unsloth/Radiology_mini", split = "train")
instruction = "You are an expert radiographer. Describe accurately what you see in this image."

def convert_to_conversation(sample):
    conversation = [
        { "role": "user",
          "content" : [
            {"type" : "text",  "text"  : instruction},
            {"type" : "image", "image" : sample["image"]} ]
        },
        { "role" : "assistant",
          "content" : [
            {"type" : "text",  "text"  : sample["caption"]} ]
        },
    ]
    return { "messages" : conversation }
pass

converted_dataset = [convert_to_conversation(sample) for sample in dataset]

FastVisionModel.for_inference(model) # Enable for inference!

image = dataset[0]["image"]
instruction = "You are an expert radiographer. Describe accurately what you see in this image."

messages = [
    {"role": "user", "content": [
        {"type": "image"},
        {"type": "text", "text": instruction}
    ]}
]
input_text = tokenizer.apply_chat_template(messages, add_generation_prompt = True)
inputs = tokenizer(
    image,
    input_text,
    add_special_tokens = False,
    return_tensors = "pt",
).to("cuda")

from transformers import TextStreamer
text_streamer = TextStreamer(tokenizer, skip_prompt = True)
_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 500,
                   use_cache = True, temperature = 1.5, min_p = 0.1)

```