license, library_name, pipeline_tag, language, tags, base_model, datasets

license	library_name	pipeline_tag	language	tags	base_model	datasets
apache-2.0	transformers	text-generation	en	math reasoning reasoning-compression self-distillation crisp	deepseek-ai/DeepSeek-R1-Distill-Llama-8B	pb09204048/CRISP

CRISP-DeepSeek-R1-Distill-Llama-8B-v2

DeepSeek-R1-Distill-Llama-8B trained with CRISP (Compressed Reasoning via Iterative Self-Policy Distillation) using the v2 conciseness teacher. Step-99 checkpoint.

Paper: https://arxiv.org/abs/2603.05433

CRISP teaches a reasoning model to think concisely by distilling its own concise behavior back into itself: the teacher is the same model conditioned on a conciseness instruction, the student has no instruction, and training minimizes per-token reverse KL from student to teacher on the student's own rollouts (teacher refreshed every M=50 steps). No ground-truth answers, token budgets, or difficulty estimators enter the loss.

This checkpoint uses the v2 teacher prompt: v2 (difficulty-aware, default): adds a caveat to not over-compress hard/multi-step problems (keep case analysis, edge cases, a final check).

Other CRISP checkpoints: Qwen3-8B (v2), Qwen3-14B (v2), DeepSeek-R1-Distill-Llama-8B (v2). Training data: pb09204048/CRISP.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("pb09204048/CRISP-DeepSeek-R1-Distill-Llama-8B-v2")
model = AutoModelForCausalLM.from_pretrained("pb09204048/CRISP-DeepSeek-R1-Distill-Llama-8B-v2", device_map="auto")

Benchmark results (DeepSeek-R1-Distill-Llama-8B)

Accuracy (mean@8, %) and token reduction (Red., % vs. base) at a 30K-token budget. Math is scored with a dual-path grader (Answer: or \boxed{}); GPQA-Diamond and MMLU use exact letter-match. This model is the CRISP (v2) row.

Setting	MATH-500	AIME 2024	AIME 2025	GPQA-D	MMLU
Base	71.3 / —	33.3 / —	25.0 / —	47.0 / —	71.5 / —
Concise prompt (v2)	79.7 / 20.5%	42.1 / 2.5%	28.8 / 3.8%	46.0 / 9.4%	73.9 / 9.2%
Concise prompt (v1)	80.8 / 25.1%	45.0 / 10.2%	29.2 / 9.8%	46.5 / 10.2%	74.1 / 9.2%
CRISP (v2)	79.8 / 23.2%	42.1 / −2.5%	26.2 / 0.1%	46.7 / 7.0%	71.4 / 11.4%
CRISP (v1)	82.1 / 31.6%	39.2 / 6.3%	27.1 / 7.1%	48.3 / 10.2%	71.7 / 17.6%

Citation

@article{sang2026crisp,
  title={Crisp: Compressed reasoning via iterative self-policy distillation},
  author={Sang, Hejian and Xu, Yuanda and Zhou, Zhengze and He, Ran and Wang, Zhipeng and Sun, Jiachen},
  journal={arXiv preprint arXiv:2603.05433},
  year={2026}
}