base_model, library_name, pipeline_tag, tags

base_model	library_name	pipeline_tag	tags
Qwen/Qwen3-0.6B-Base	transformers	text-generation	qwen3 math sft qlora merged-lora fp16

qwen3-0.6b-math-l45-qlora-merged-fp16-v2

Merged fp16 model from Qwen/Qwen3-0.6B-Base plus a QLoRA SFT adapter trained for MATH level 4-5 problem solving.

This is the corrected SFT v2 run using the train split for training. Final 500-question evaluation is intentionally separate.

Training Summary

• Base model: Qwen/Qwen3-0.6B-Base
• Train file: /kaggle/input/datasets/anurhalizah/math-he/math_level45_train.parquet
• Test file: /kaggle/input/datasets/anurhalizah/math-he/math_level45_test.parquet
• Train rows used: 3994
• Train subset size: 3994
• Smoke loss eval rows: 200
• Max sequence length: 2048
• Epochs: 3
• Learning rate: 0.0002
• Precision: fp16
• Merge method: manual_lora_cpu
• Merged LoRA matrices: 196

Prompt Format

### System:
{system_prompt}

### Problem:
{problem}

### Solution:

System prompt:

You are a precise mathematical problem solver.
Follow this exact output contract:
1. Solve the problem step by step with concise reasoning.
2. Use valid LaTeX math notation for mathematical expressions.
3. Preserve LaTeX commands such as \frac{...}{...}, \sqrt{...}, x^{...}, subscripts, equations, and inequalities.
4. Put the final answer on its own last line exactly in this form: Final Answer: \boxed{...}
5. Do not use Markdown code fences.
6. Do not switch to a different answer format.

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

repo_id = "zannvznn/qwen3-0.6b-math-l45-qlora-merged-fp16-v2"
tokenizer = AutoTokenizer.from_pretrained(repo_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    repo_id,
    torch_dtype=torch.float16,
    device_map="auto",
    trust_remote_code=True,
)