GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
pourasrp
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
pourasrp
Model Tree
Qwen/Qwen3-8B
Input Modalities
Output Modalities
Supported Functionality
Authors: Chaitanya Medidar, Manasi Ghalsasi, Pouras Patil, Rushil Patil (Vivekanand Education Society's Institute of Technology, Mumbai)
Part of STAR: Execution-Grounded, Typed Recovery Supervision for Coding-Agent SFT. Code, paper materials and manifests: https://github.com/chaitanyamedidar/STAR
Qwen/Qwen3-8B (revision b968826d9c46dd6066d109eabc6255188de91218), not included; LoRA r=64, alpha=128, all attention+MLP projections.run_manifest.json. Dataset (adapters, weights, labels, records): pourasrp/star_v1, DOI 10.57967/hf/11003. Per-token weight files are also in pourasrp/star-weights.| file | sha256 |
|---|---|
| adapter_model.safetensors | 4dfe92988fc312d53e8196986e74fda7070f22eef30b8e55b77589079e782cf8 |
| adapter_config.json | 1448204e3648947def36dc5e38f69d4b55d124a95256cba00066a8a5c27d7414 |
Verify with sha256sum adapter_model.safetensors.
python
from peft import PeftModel; from transformers import AutoModelForCausalLMm = PeftModel.from_pretrained(AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B"), "pourasrp/star-A2")License: Apache-2.0 (matches the GitHub repo). Training data came from SWE-Lego Real. No trajectory text is redistributed here.