ssurface

cot-dialect-math-olmo3-7b-think-grpo-cf-s1337-l1

README

License: apache-2.0

Results

Table with columns: Accuracy
	Accuracy
This adapter	58.6%

MATH-500 (n=500), greedy decoding, single-turn, no exemplars, no self-consistency.

Scored with the project's LaTeX-aware grader (see the scoring note below).

Scoring note. MATH answers are \boxed{}, and the harness that produced the first pass of these evals looked for GSM8K's #### n. That silently scored three of these models at ~0%% when they were near 60%%. Numbers here come from the project's LaTeX-aware grader, which normalizes equivalent forms (\frac{14}{3} == 14/3).

Training data

MATH training problems re-expressed at level L1 by a teacher model. MATH ships three levels rather than five — L1 anchor, L3 symbolic middle, L5 extreme — with the notation rules held identical to the GSM8K dialects and only the answer convention changed to \boxed{}.

Training setup

GRPO on top of the merged level-1 SFT model.

Table

Engine	`trl.GRPOTrainer` on stock `transformers`, attention `sdpa`
Reward	`correctness`, `format`
Loss type	dapo
Generations per prompt	8
Batch	32 x 2 accum
Max completion	256 tokens

Reward components

correctness — +/- the gold solution's step count on an answer match, so harder problems are worth more
format — the response must be one <think>...</think> block then #### <answer>

Engine note. Stock transformers with sdpa attention, not a fused-kernel wrapper. The fused path produced adapters whose lora_B matrices were all zero — mathematically inert despite loading without error. Every adapter in this collection was verified lora_B != 0 before publishing; 13 that failed that check were withheld.

Usage

markdown
Solve this using Level 1 (Verbose).
Problem: {your problem}

Stacks on the SFT model, not the raw base. Trained against the merged SFT model, so loading it straight onto allenai/Olmo-3-7B-Think will not reproduce the number above.

python
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

model = AutoModelForCausalLM.from_pretrained("allenai/Olmo-3-7B-Think", torch_dtype="bfloat16", device_map="auto")
model = PeftModel.from_pretrained(model, "ssurface/cot-dialect-math-olmo3-7b-think-sft-unfiltered-l1")   # 1. SFT for this level
model = model.merge_and_unload()
model = PeftModel.from_pretrained(model, "ssurface/cot-dialect-math-olmo3-7b-think-grpo-cf-s1337-l1")   # 2. this adapter
tok = AutoTokenizer.from_pretrained("allenai/Olmo-3-7B-Think")

Limitations

Trained and evaluated on math word problems only.
Accuracy falls with problem difficulty, fastest at the compressed levels.
Single seed unless the repo name says otherwise; differences of a couple of points are within noise (95% half-width ~2.7 pp at n=1317, ~4.4 pp at n=500).

Citation

bibtex
@misc{cot-compression-dialects,
  title  = {Chain-of-Thought Compression Dialects},
  author = {Frolov, Anatolii},
  year   = {2026}
}

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

ssurface

Model Tree

Base

allenai/Olmo-3-7B-Think

Adapter

this model

Input Modalities

Text

Output Modalities