Open-weight model
Qwen2.5-3B-Instruct-Sheldon-RLAIF-grpo-v2-LoRA
by Sam EnMin Huang tbooy/Qwen2.5-3B-Instruct-Sheldon-RLAIF-grpo-v2-LoRA
Qwen2.5-3B-Instruct-Sheldon-RLAIF-grpo-v2-LoRA is an open-weight model from Sam EnMin Huang, released under other. Its published files total 1.4 GB.
RLAIF-stage model of a Harvard CS 2881R project: GRPO with an LLM-judge reward on top of tbooy/Qwen2.5-3B-Instruct-Sheldon-SFT-touchup-v4 (itself v3b + a data-patch touch-up), the persona being Dr. Sheldon Cooper and the protected STEM task GSM8K.
Model Card
RLAIF-stage model of a Harvard CS 2881R project: GRPO with an LLM-judge reward on top of tbooy/Qwen2.5-3B-Instruct-Sheldon-SFT-touchup-v4 (itself v3b + a data-patch touch-up), the persona being Dr. Sheldon Cooper and the protected STEM task GSM8K. Files: finaladapter/ (PEFT LoRA on the touch-up model, step 109) and checkpoint-{25,50,75,100,109}/ with trainer states (per-step reward components under sheldon/). Apply to tbooy/Qwen2.5-3B-Instruct-Sheldon-SFT-touchup-v4. Reward R = G (2 P + F) - rules - 0.5 falseclaim - batchtax: a persona-blind task gate G (asks satisfied, refusal, harm, self-contradiction, false claims about the user), a pairwise persona score P from sibling comparisons…
Excerpt from the card by Sam EnMin Huang, licensed other.
Identity and Version
- Repository
- tbooy/Qwen2.5-3B-Instruct-Sheldon-RLAIF-grpo-v2-LoRA
- Publisher
- Sam EnMin Huang
- Task
- Not stated by the source
- Modality
- Other
- Library
- peft
- Parameters
- Not stated by the source
- Languages
- en
- Revision
- ca04ae60034ae6a42a070224e8dab1787acc13b6
- First published
- 2026-09-21
- Last updated
- 2026-09-21
Files and Weights
28 files, 1.4 GB in total. The weights are 6 files totalling 1.4 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| checkpoint-100/adapter_model.safetensors | Weights | 239.5 MB | a3597ae25984 |
| checkpoint-109/adapter_model.safetensors | Weights | 239.5 MB | 17a7b35240c5 |
| checkpoint-25/adapter_model.safetensors | Weights | 239.5 MB | c992cff79a82 |
| checkpoint-50/adapter_model.safetensors | Weights | 239.5 MB | d10e89618915 |
| checkpoint-75/adapter_model.safetensors | Weights | 239.5 MB | ec5441373519 |
| final_adapter/adapter_model.safetensors | Weights | 239.5 MB | 17a7b35240c5 |
| checkpoint-100/adapter_config.json | Configuration | 1.2 KB | — |
| checkpoint-100/trainer_state.json | Configuration | 362.5 KB | — |
| checkpoint-109/adapter_config.json | Configuration | 1.2 KB | — |
| checkpoint-109/trainer_state.json | Configuration | 395.1 KB | — |
| checkpoint-25/adapter_config.json | Configuration | 1.2 KB | — |
| checkpoint-25/trainer_state.json | Configuration | 91.3 KB | — |
| checkpoint-50/adapter_config.json | Configuration | 1.2 KB | — |
| checkpoint-50/trainer_state.json | Configuration | 181.6 KB | — |
| checkpoint-75/adapter_config.json | Configuration | 1.2 KB | — |
| checkpoint-75/trainer_state.json | Configuration | 271.8 KB | — |
| final_adapter/adapter_config.json | Configuration | 1.2 KB | — |
| README.md | Documentation | 2.9 KB | — |
| checkpoint-100/README.md | Documentation | 5.3 KB | — |
| checkpoint-109/README.md | Documentation | 5.3 KB | — |
| checkpoint-25/README.md | Documentation | 5.3 KB | — |
| checkpoint-50/README.md | Documentation | 5.3 KB | — |
| checkpoint-75/README.md | Documentation | 5.3 KB | — |
| final_adapter/README.md | Documentation | 5.3 KB | — |
| final_adapter/chat_template.jinja | Other | 2.5 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| final_adapter/tokenizer.json | Tokenizer | 11.4 MB | 3fd169731d2c |
| final_adapter/tokenizer_config.json | Tokenizer | 693 B | — |
License and Download
- License
- other
- Access
- Open weights, no gate
- Download size
- 1.4 GB
Released by Sam EnMin Huang through its official repository on Hugging Face. Read the license.
Built From
- Trained on (disclosed) openai/gsm8k
- Trained on (disclosed) tbooy/sheldon-cooper-sft-20k
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 1.4 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Qwen2.5-3B-Instruct-Sheldon-RLAIF-grpo-v2-LoRA
What license is Qwen2.5-3B-Instruct-Sheldon-RLAIF-grpo-v2-LoRA released under?
other, as its publisher declares it. Read the license text before commercial use.