Added Implementation Script

README.md

@@ -19,3 +19,79 @@ language:
 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)
+
+```