RexTRO111/Qwen3-4B-MegaR3ASONER-LoRA-v1

Qwen3-4B-MegaR3ASONER-LoRA-v1

Reasoning-focused PEFT LoRA adapter for `Qwen/Qwen3-4B-Thinking-2507`.

Important

This repository contains LoRA adapter weights only. Load it on the exact base checkpoint:

Qwen/Qwen3-4B-Thinking-2507

Do not attach it to Qwen/Qwen3-4B-Instruct-2507 or another base model.

Training overview

• —Method: BF16 16-bit LoRA
• —Hardware: NVIDIA A10G on Modal
• —Focus: mathematical, scientific, coding, and general reasoning
• —Training sources:
• —HuggingFaceH4/Bespoke-Stratos-17k
• —nvidia/OpenMathReasoning
• —nvidia/OpenCodeReasoning
• —nvidia/OpenScienceReasoning-2
• —lordx64/reasoning-distill-opus-4-7-max-sft

Preliminary evaluation

On the first 100 examples selected by EleutherAI's gsm8k_cot task:

• —Flexible extraction exact match: 88%
• —Strict match: 83%

This was a limited 100-question run, not the complete GSM8K test set and not a controlled base-versus-adapter comparison.

Loading

import torch
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base_id = "Qwen/Qwen3-4B-Thinking-2507"
adapter_id = "RexTRO111/Qwen3-4B-MegaR3ASONER-LoRA-v1"

tokenizer = AutoTokenizer.from_pretrained(base_id)

base = AutoModelForCausalLM.from_pretrained(
    base_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

model = PeftModel.from_pretrained(
    base,
    adapter_id,
    is_trainable=False,
)
model.eval()

Limitations

• —The model may produce incorrect intermediate reasoning even when its final answer is correct.
• —It can overthink simple prompts.
• —Long reasoning traces increase latency.
• —Benchmark contamination has not been exhaustively ruled out.
• —Verify outputs before high-stakes use.

Licensing note

The base model and each training dataset retain their own licenses and upstream terms. Review all of them before redistribution or commercial use.