Add files using upload-large-folder tool

README.md

@@ -0,0 +1,27 @@
+---
+license: apache-2.0
+library_name: peft
+base_model: Qwen/Qwen3-VL-8B-Instruct
+pipeline_tag: image-text-to-text
+tags:
+- gui-grounding
+- computer-use
+- qwen3-vl
+datasets:
+- ruotian/SelectGround-8B-Data
+---
+
+# SelectGround-8B
+
+SelectGround-8B is a GUI grounding model built from Qwen3-VL-8B-Instruct with standard SFT and a target–distractor selection loss. It returns one click point as `[x, y]` in normalized `[0, 1000]` coordinates.
+
+This repository contains the LoRA checkpoint and the visual-merger state used for exact reproduction. `selection_head.pt` is the training-only layer/head aggregation state; inference does not add a router or residual module.
+
+| Method | ScreenSpot-Pro | UI-Vision | OSWorld-G |
+|---|---:|---:|---:|
+| SelectGround-8B | 64.96 | 38.68 | 70.00 |
+| + ConGround | 72.17 | 44.39 | 70.00 |
+
+OSWorld-G excludes refusal cases. UI-Vision is the equal-weight mean over basic, functional, and spatial element grounding.
+
+Code and usage are in the [SelectGround repository](https://github.com/zhangruotian/SelectGround). Training data are in [SelectGround-8B-Data](https://huggingface.co/datasets/ruotian/SelectGround-8B-Data).

adapter_config.json

@@ -0,0 +1,15 @@
+{
+  "base_model_name_or_path": "Qwen/Qwen3-VL-8B-Instruct",
+  "bias": "none",
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "lora_alpha": 128,
+  "lora_dropout": 0.05,
+  "peft_type": "LORA",
+  "r": 64,
+  "revision": "0c351dd01ed87e9c1b53cbc748cba10e6187ff3b",
+  "target_modules": ["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa33306498c323fea5405798a8feded09f4e5dfda386dd412c48cf174d1581cd
+size 349251816

selection_head.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:456e706f68b76c64f3a7db24ee2e220711d7b16adffee1f4e7b02b938c3f9d77
+size 2586

visual_merger.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:125b9b37b243724cee09eb064650a6e14d23f186097738b5144170e870da2fab
+size 80241309