Open-weight model
scottyrl-a3-p5_textcraft_grpo
by Rishiraj Nagarajan rishinagarajan/scottyrl-a3-p5_textcraft_grpo
scottyrl-a3-p5_textcraft_grpo is an open-weight model from Rishiraj Nagarajan. Its published files total 169.9 MB.
LoRA adapter (rank 32) on Qwen/Qwen3.5-4B, trained with the scottyrl framework for 11-768 (AI Agents, CMU), Assignment 3.
Model Card
LoRA adapter (rank 32) on Qwen/Qwen3.5-4B, trained with the scottyrl framework for 11-768 (AI Agents, CMU), Assignment 3. - runname: p5textcraftgrpo Graders serve the adapter with vLLM and run the course evaluation script against the server, on the medium and hard TextCraft-Synth validation
Excerpt from the card by Rishiraj Nagarajan.
Identity and Version
- Repository
- rishinagarajan/scottyrl-a3-p5_textcraft_grpo
- Publisher
- Rishiraj Nagarajan
- Task
- Not stated by the source
- Modality
- Other
- Library
- peft
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 5bcb9da146088c1a0a724d4b97ab604cd07c1164
- First published
- 2026-10-13
- Last updated
- 2026-10-13
Files and Weights
4 files, 169.9 MB in total. The weights are 1 file totalling 169.9 MB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| adapter_model.safetensors | Weights | 169.9 MB | 5f187d17e784 |
| adapter_config.json | Configuration | 590 B | — |
| README.md | Documentation | 1.1 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 169.9 MB
Released by Rishiraj Nagarajan through its official repository on Hugging Face.
Built From
- Adapter of Qwen/Qwen3.5-4B
- Derived from Qwen/Qwen3.5-4B
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 169.9 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.