Downloads · 30 days
0
or-reasoning-7b-sft
alirezaaminzadeh/or-reasoning-7b-sft
or-reasoning-7b-sft is a text generation model from alirezaaminzadeh. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
QLoRA supervised fine-tuning of Qwen2.5-Coder-7B-Instruct on the OR Reasoning multi-task corpus.
Access
Public
Updated Aug 9, 2026
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
Other1.5 KB · 47%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Access
- Public
- Created
- Aug 9, 2026
- Updated
- Aug 9, 2026
- SHA
- c7278c06
Try a prompt
Base models
Model card
From the Hugging Face model README
OR Reasoning 7B SFT
QLoRA supervised fine-tuning of Qwen2.5-Coder-7B-Instruct on the OR Reasoning multi-task corpus.
Training
| Parameter | Value |
|---|---|
| Method | SFT with QLoRA (PEFT + bitsandbytes 4-bit) |
| LoRA rank | 64 |
| LoRA alpha | 128 |
| Learning rate | 2e-4 |
| Max length | 4096 |
| Epochs | 2 |
| Hardware | a10g-large (HF Jobs) |
| Dataset | alirezaaminzadeh/or-reasoning-sft-corpus |
Tasks
Problem classification, formulation, constraint extraction, Pyomo codegen, code repair, solution explanation.
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
base = "Qwen/Qwen2.5-Coder-7B-Instruct"
model = PeftModel.from_pretrained(
AutoModelForCausalLM.from_pretrained(base, device_map="auto"),
"alirezaaminzadeh/or-reasoning-7b-sft",
)
tokenizer = AutoTokenizer.from_pretrained(base)
Next Stage
Fine-tuned further with GRPO using solver-verifiable rewards → alirezaaminzadeh/or-reasoning-7b-grpo.
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Created
- Aug 9, 2026
- Updated
- Aug 9, 2026