Modelpublic

AdarshSingh7647/Eklav-8B-Math

sourceHugging Faceupdated 19d agoView on Hugging Face

0likes2kdownloads

Model Card

Eklav-8B-Math

Eklav trains a model to pick up a teacher's reasoning mid thought rather than imitate it end to end. The student sees a partial reasoning trace from the teacher, with the answer revealing tail removed, and learns to continue reasoning and produce the answer on its own. The model's own reasoning is conditioned on the teacher's partial trace during training rather than trained to reproduce it word for word. Same base model, same training data as standard full trace CoT distillation, only the training objective changes.

Highlights

—+0.6% average pass@1 across 6 math benchmarks vs. standard full trace CoT SFT, same base model and training data (MMLU excluded, general knowledge check not a math benchmark)

Model details


Base model	Qwen/Qwen3-8B
Task	Math reasoning
Training method	Eklav (hint conditioned SFT)
Format	Merged bf16 checkpoint

Results

Pass@1 (%), single evaluation run per benchmark.

Benchmark	AIME 2025	AIME 1983-2024	GPQA-Diamond	GSM8K	MATH-500	Omni-MATH	MMLU
CotGen	28.3	54.0	51.4	95.3	89.4	36.0	82.2
Eklav	28.1	51.8	52.9	95.1	90.8	37.7	81.8

Usage

python

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "AdarshSingh7647/Eklav-8B-Math"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")