Instructions to use EvanSirius/leap-ckpts with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use EvanSirius/leap-ckpts with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="EvanSirius/leap-ckpts")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("EvanSirius/leap-ckpts", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use EvanSirius/leap-ckpts with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "EvanSirius/leap-ckpts" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "EvanSirius/leap-ckpts", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/EvanSirius/leap-ckpts
- SGLang
How to use EvanSirius/leap-ckpts with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "EvanSirius/leap-ckpts" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "EvanSirius/leap-ckpts", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "EvanSirius/leap-ckpts" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "EvanSirius/leap-ckpts", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use EvanSirius/leap-ckpts with Docker Model Runner:
docker model run hf.co/EvanSirius/leap-ckpts
LEAP Checkpoints (leap-ckpts): Full-Parameter SFT Trajectory on Qwen3-VL-2B-Instruct
Model Summary
EvanSirius/leap-ckpts hosts the full-parameter supervised fine-tuning (Full SFT) checkpoint trajectory (checkpoint-200 through checkpoint-7000, saved every 200 optimization steps) of Qwen/Qwen3-VL-2B-Instruct for "Structured Supervision Targets as a Knowledge Interface for Reliable Parser-Gated Plan Generation in Compact Vision-Language Models".
All checkpoints are trained on 151,230 single-frame ordered-step instances (EvanSirius/leap-agibot-processed) using BF16 precision, SDPA attention, response-only loss masking, cosine learning rate decay (peak LR $1.5\times 10^{-5}$, 800-step linear warmup), and effective batch size 36 (6Γ6 gradient accumulation).
VLABench Evaluation Summary (checkpoint-5000 Canonical Release)
Evaluated across 4,500 episodes spanning all six VLABench capability dimensions under deterministic greedy decoding:
| Evaluation Regime | Qwen3-VL-2B (Base) |
Same-Domain Control ($\mathcal{T}_{\mathrm{ctrl}}$) |
LoRA r=16 (5k) |
Full SFT (checkpoint-5000) |
|---|---|---|---|---|
| Strict Parser-Gated Macro Score ($\psi_{\mathrm{raw}}$) | 25.10 | 25.15 | 28.22 | 28.38 ([28.01, 28.75]) |
| Stage 1 Syntax Parse Survival Rate | 99.18% | β | 87.75% | 96.00% |
| Stage 2 Entity Type-Normalized Macro Score ($\psi_{\mathrm{norm}}$) | 35.66 | β | 33.58 | 38.90 |
| Stage 2 Skill-Sequence Match Rate | 62.52% | β | 60.12% | 70.68% |
| Stage 2 Joint Step Match Rate | 18.13% | β | 18.31% | 22.05% |
| Stage 2 Exact Plan Match Rate | 4.33% | β | 2.41% | 6.60% |
Usage
import torch
from transformers import AutoModelForImageTextToText, AutoProcessor
model_id = "EvanSirius/leap-ckpts"
subfolder = "checkpoint-5000"
processor = AutoProcessor.from_pretrained("Qwen/Qwen3-VL-2B-Instruct")
model = AutoModelForImageTextToText.from_pretrained(
model_id,
subfolder=subfolder,
torch_dtype=torch.bfloat16,
device_map="auto",
).eval()
Related Resources
- Official Code & Audit Scripts: GitHub
Evan-Joseph/leap-code - Processed Supervision Dataset: HuggingFace
EvanSirius/leap-agibot-processed - Source Keyframe Corpus: HuggingFace
EvanSirius/LOVE-Agibot-Beta
Citation
@article{gao2026structured,
title={Structured Supervision Targets as a Knowledge Interface for Reliable Parser-Gated Plan Generation in Compact Vision-Language Models},
author={Shenzhou Gao and Peijian Zhang},
year={2026}
}
Model tree for EvanSirius/leap-ckpts
Base model
Qwen/Qwen3-VL-2B-Instruct