Upload README.md with huggingface_hub

README.md

@@ -1,60 +1,42 @@
 ---
-library_name: peft
 license: other
 base_model: Qwen/Qwen2-VL-2B-Instruct
+library_name: transformers
 tags:
-- llama-factory
+- qwen2-vl
 - lora
-- generated_from_trainer
-model-index:
-- name: qwen-vl-amazon-ft
-  results: []
+- multimodal
+- amazon-listing
+- kaggle
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
+# Qwen2-VL LoRA — Amazon Listing Generator
 
-# qwen-vl-amazon-ft
+Lightweight LoRA adapter trained with **LLaMA-Factory** to turn a product image into an Amazon-style listing (title, bullets, description).
 
-This model is a fine-tuned version of [Qwen/Qwen2-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct) on the amazon_qwen dataset.
+> **Note:** This repo ships the **adapter only**. Load it on top of `Qwen/Qwen2-VL-2B-Instruct`.
 
-## Model description
+## Quickstart
 
-More information needed
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+from PIL import Image
 
-## Intended uses & limitations
+base = "Qwen/Qwen2-VL-2B-Instruct"
+adapter = "soupstick/qwen2vl-amazon-ft-lora"
 
-More information needed
+model = AutoModelForCausalLM.from_pretrained(base, trust_remote_code=True, device_map="auto")
+model = PeftModel.from_pretrained(model, adapter)
+tok = AutoTokenizer.from_pretrained(base, trust_remote_code=True)
 
-## Training and evaluation data
+img = Image.open("sample.png").convert("RGB")
+resp, _ = model.chat(tok, query="<image>\nGenerate Amazon listing.", history=[], image=img)
+print(resp)
+Training
 
-More information needed
+Framework: LLaMA-Factory (LoRA)
 
-## Training procedure
+Task: Multimodal instruction-following for e-commerce listings
 
-### Training hyperparameters
-
-The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 1
-- eval_batch_size: 8
-- seed: 42
-- gradient_accumulation_steps: 16
-- total_train_batch_size: 16
-- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 50
-- training_steps: 500
-- mixed_precision_training: Native AMP
-
-### Training results
-
-
-
-### Framework versions
-
-- PEFT 0.15.2
-- Transformers 4.55.0
-- Pytorch 2.6.0+cu118
-- Datasets 3.6.0
-- Tokenizers 0.21.1
+Data: community dataset (see the dataset card linked below)