DeepCoder-14B-Preview is a code reasoning LLM fine-tuned from DeepSeek-R1-Distilled-Qwen-14B using distributed reinforcement learning (RL) to scale up to long context lengths. The model achieves 60.6% Pass@1 accuracy on LiveCodeBench v5 (8/1/24-2/1/25), representing a 8% improvement over the base model (53%) and achieving similar performance to OpenAI's o3-mini with just 14B parameters.
We enhance the original GRPO algorithm with insights from DAPO to enable more stable training:
Offline Difficulty Filtering: DAPO employs online dynamic sampling, discarding both entirely correct and entirely incorrect samples on the fly. While this helps maintain a more stable effective batch size, it introduces significant runtime overhead due to rejection sampling. Instead, we perform offline difficulty filtering on a subset of coding problems to ensure the training dataset remains within a suitable difficulty range.
No Entropy Loss: We observed that including an entropy loss term often led to instability, with entropy growing exponentially and ultimately collapsing training. To mitigate this, we eliminate the entropy loss entirely.
No KL Loss: Eliminating KL loss prevents the LLM from staying within trust region of the original SFT model. This removal also obviates the need to compute log probabilities for the reference policy, thereby accelerating training.
Overlong Filtering(from DAPO): To preserve long-context reasoning, we mask the loss for truncated sequences. This technique enables DeepCoder to generalize to 64K-context inference despite being trained with a 32K context.
Clip High (from DAPO): By increasing the upper bound in GRPO/PPO’s surrogate loss, we encourage more exploration and more stable entropy.
Our original Deepscaler-1.5B-Preview scaled long context training from 8K→16K→24K, achieving 33→38→43% on AIME respectively. Similarly, Deepcoder-14B-Preview is trained on 16K→32K, achieving 54→58% on LiveCodeBench (v5). DeepCoder-14B-Preview successfully generalizes to longer contexts when evaluated at 64K context, reaching 60.6%.
DeepCoder generalizes better to long contexts than the base distilled model, due to DAPO's overlong filtering. However, it's longer responses are often truncated when the max length is capped at 16K, which can lower its scores.
Model
16K
32K
64K
DeepCoder-14B-Preview
45.6
57.9
60.6
DeepSeek-R1-Distill-Qwen-14B
50.2
53.0
53.0
A more detailed description of the training recipe can be found in our blog post.
This project is released under the MIT License, reflecting our commitment to open and accessible AI development. We believe in democratizing AI technology by making our work freely available for anyone to use, modify, and build upon. This permissive license ensures that researchers, developers, and enthusiasts worldwide can leverage and extend our work without restrictions, fostering innovation and collaboration in the AI community.
@misc{deepcoder2025,
title={DeepCoder: A Fully Open-Source 14B Coder at O3-mini Level},
author={Michael Luo and Sijun Tan and Roy Huang and Ameen Patel and Alpay Ariyak and Qingyang Wu and Xiaoxiang Shi and Rachel Xin and Colin Cai and Maurice Weber and Ce Zhang and Li Erran Li and Raluca Ada Popa and Ion Stoica},
howpublished={\url{https://pretty-radio-b75.notion.site/DeepCoder-A-Fully-Open-Source-14B-Coder-at-O3-mini-Level-1cf81902c14680b3bee5eb349a512a51}},
note={Notion Blog},
year={2025}
}
Files
21 files · 59.1 GBWeights 59.1 GB (safetensors). Sizes and sha256 from the signed manifest.
import os
os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com"
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("agentica-org/DeepCoder-14B-Preview", revision="cfa11a3b8e32163123776df78ab1e95adf0ca58d")
model = AutoModelForCausalLM.from_pretrained("agentica-org/DeepCoder-14B-Preview", revision="cfa11a3b8e32163123776df78ab1e95adf0ca58d", device_map="auto")
