README.md

metadata

license: apache-2.0
base_model: mistralai/Mathstral-7B-v0.1
library_name: peft
pipeline_tag: text-generation
tags:
  - lora
  - peft
  - grpo
  - dr-grpo
  - mathematical-reasoning
  - math
datasets:
  - hugruby/mismatched-wrong-drafts
language:
  - en

Mathstral-7B · No draft (GRPO baseline)

On-policy Dr. GRPO baseline — no draft injected.

LoRA adapter for mistralai/Mathstral-7B-v0.1, trained with Dr. GRPO as the No draft (GRPO baseline) condition in "Weak-to-Strong Elicitation via Mismatched Wrong Drafts" (Wei Deng, arXiv:2605.17314).

• Base model: mistralai/Mathstral-7B-v0.1 (Apache-2.0)
• Adapter: LoRA r=16, α=32 (167 MB), released at global step 2000
• Training data: config no_draft of hugruby/mismatched-wrong-drafts — 8,888 Level 3–5 MATH problems (MATH-500 held out)
• License: Apache-2.0

How to use

This is a LoRA adapter — load it on top of the base model.

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

BASE    = "mistralai/Mathstral-7B-v0.1"
ADAPTER = "hugruby/mathstral-7b-grpo-no-draft"

tok   = AutoTokenizer.from_pretrained(ADAPTER)
model = PeftModel.from_pretrained(
    AutoModelForCausalLM.from_pretrained(BASE, torch_dtype=torch.bfloat16, device_map="auto"),
    ADAPTER,
).eval()

problem = "If $x+y=6$ and $xy=5$, find $x^2+y^2$."
gen = dict(max_new_tokens=4096, do_sample=False)

# CANONICAL — the plain draft-free prompt the model was trained and evaluated on (no [INST]):
PROMPT = (
    "Problem: " + problem + "\n\n"
    "Thinking: N/A\n\n"
    "The thinking section may contain errors. Solve the math problem step by step. "
    "Write your own correct solution. Put your final answer within \\boxed{}.\n\n"
    "Correct Solution:"
)
ids = tok(PROMPT, return_tensors="pt").to(model.device)
print(tok.decode(model.generate(**ids, **gen)[0][ids.input_ids.shape[1]:], skip_special_tokens=True))

Optional: the [INST] chat format (out-of-distribution)

The shipped chat_template.jinja is Mathstral's original [INST] chat template. This adapter was not trained in that format, so apply_chat_template(...) is out-of-distribution and generally underperforms the plain prompt above — it is included only so you can A/B both:

ids = tok.apply_chat_template(
    [{"role": "user",
      "content": problem + "\n\nPlease reason step by step, and put your final answer within \\boxed{}."}],
    add_generation_prompt=True, return_tensors="pt").to(model.device)
print(tok.decode(model.generate(ids, **gen)[0][ids.shape[1]:], skip_special_tokens=True))

How it was trained

Trained with Dr. GRPO (loss_type=dr_grpo, scale_rewards=False) using TRL GRPOTrainer on top of Unsloth FastLanguageModel, on the no_draft data config. The reward is binary mathematically_quasi_correct. The correction-bonus, copy-penalty, and corrupt-penalty terms are all 0, and the reward is pure binary.

Training command:

python scripts/train.py \
  --model mistralai/Mathstral-7B-v0.1 \
  --dataset-path data/no_draft \
  --output-dir outputs/no_draft \
  --max-steps 2222 \
  --gradient-accumulation-steps 4 \
  --max-completion-length 4096 \
  --max-seq-length 7168 \
  --learning-rate 5e-6 --lr-scheduler-type constant \
  --beta 0 \
  --correction-bonus 0.0 --copy-penalty 0.0 --corrupt-penalty 0.0 \
  --adam-beta2 0.99 \
  --save-steps 50 --gpu-mem-util 0.5

Hyperparameter	Value
Base model	mistralai/Mathstral-7B-v0.1
Method	Dr. GRPO (loss_type=dr_grpo, scale_rewards=False)
LoRA rank / alpha	r = 16, α = 32 → scaling γ = α/r = 2
LoRA targets / dropout	q,k,v,o,gate,up,down (7 projections) / 0.0
KL coefficient β	0
Reward bonuses	correction 0, copy-penalty 0, corrupt-penalty 0
Generations per prompt	16
Per-device batch	1
Gradient accumulation	4 → 4 problems × 16 = 64 completions/step
Learning rate	5e-6, constant schedule
Adam β₂	0.99
Max completion length	4096
Max sequence length	7168
Max prompt tokens	Disabled and no truncation. Since no drafts, prompts are short — longest 1,899 tok, well under the implicit 3,072 = 7,168 − 4,096 budget. As a result, disabling is equivalent to setting it to 3,072.
Max steps	2222
Released checkpoint	global step 2000 (epoch 0.900)
Random seed	42

Files

• adapter_model.safetensors, adapter_config.json — the LoRA adapter (load with PEFT on the base model)
• tokenizer.json, tokenizer.model, tokenizer_config.json, special_tokens_map.json — tokenizer
• chat_template.jinja — Mathstral's [INST] template (see the out-of-distribution note above)

Citation

@article{deng2026mismatched,
  title   = {Weak-to-Strong Elicitation via Mismatched Wrong Drafts},
  author  = {Deng, Wei},
  journal = {arXiv preprint arXiv:2605.17314},
  year    = {2026},
  url     = {https://arxiv.org/abs/2605.17314}
}

License

Apache-2.0. The base model (Mathstral-7B-v0.1) and the draft model (Qwen2.5-Math-1.5B) are both Apache-2.0.