Downloads · 30 days
0
Kavin60606/qwen3-vl-2b-affordance-checkpoint3500
qwen3-vl-2b-affordance-checkpoint3500 is a machine learning model from Kavin60606. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Fine-tuned Qwen3-VL-2B-Instruct for egocentric visual affordance detection.
Downloads · 30 days
0
Access
Public
Updated Feb 11, 2026
Repo size
117 MB
Likes
0
Public
Click a slice to open those files.
.safetensors140 MB · 55%
From the Hugging Face model README
Fine-tuned Qwen3-VL-2B-Instruct for egocentric visual affordance detection.
Evaluation Results (30 validation samples):
from unsloth import FastVisionModel
from peft import PeftModel
from PIL import Image
# Load base model
model, processor = FastVisionModel.from_pretrained(
"unsloth/Qwen3-VL-2B-Instruct",
load_in_4bit=True,
max_seq_length=2048,
)
# Load LoRA adapter
model = PeftModel.from_pretrained(model, "sanskxr02/qwen3-vl-2b-affordance-checkpoint3500")
FastVisionModel.for_inference(model)
# Run inference
image = Image.open("frame.jpg").convert("RGB").resize((384, 216))
messages = [{
"role": "user",
"content": [
{"type": "image", "image": image},
{"type": "text", "text": "What is the affordance in this scene?"},
],
}]
text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=False)
inputs = processor(text=[text], images=[image], return_tensors="pt", padding=True).to(model.device)
output_ids = model.generate(**inputs, max_new_tokens=20, temperature=0.0, do_sample=False)
prediction = processor.tokenizer.decode(output_ids[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
print(f"Affordance: {prediction}")
adapter_config.json, adapter_model.safetensors - LoRA adapter weightscheckpoint-3500/ - Full checkpoint with trainer stateevaluation/ - Evaluation results with annotated images and training curvesdataset/ - Training data files (annotations, train/val splits)train.py, inference.py - Training and inference scriptsgrasp, pull, push, rotate, press, lift, slide, place, open, close, insert, remove, pour, cut, stir, scoop, squeeze, turn_on, turn_off
@model{qwen3vl_affordance_ckpt3500,
title={Qwen3-VL-2B Affordance Detection - Checkpoint 3500},
author={Kavin (sanskxr02)},
year={2026},
publisher={HuggingFace},
url={https://huggingface.co/sanskxr02/qwen3-vl-2b-affordance-checkpoint3500}
}
Same as base Qwen3-VL-2B-Instruct model.
Checkpoint saved at step 3500 (Epoch 1.53), training stopped for evaluation.